phenomenon · claim-type · cross-domain-transfer · mechanism · claim-relation · replication-status · limitation — grounded in the full text| phenomenon | human-like learning and thinking in machines— “In this article, we view this excitement as an opportunity to examine what it means for a machine to learn or think like a person.” | |
| claim-type | critique— “Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways.” | |
| method — evidence | — “We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it.” | |
| transfer | from physics simulation engines (game engines): the simulation engine that renders a game world is used as the model of intuitive physics: the mind is proposed to run something like it to predict what happens next in a scene— “This is directly analogous to how simulation engines can be used for intuitive physics, to predict what will happen next in a scene or to infer objects’ dynamical properties from how they move.” | transfers[0] |
| transfer | from neuroscience (into connectionist AI): the representations and algorithms of the connectionist approach were drawn from neuroscience rather than from cognitive psychology, and the paper marks that as the choice which shaped it— “The representations and algorithms used by this approach were more directly inspired by neuroscience than by cognitive psychology, although ultimately it would flower into an influential school of thought about the nature of cognition—parallel distributed processing (PDP) (McClelland et al., 1986; Rumelhart, McClelland, & the PDP Research… | transfers[1] |
| mechanism | PERFORMANCE PARITY IS GRANTED AND SIMILARITY DENIED IN CONSECUTIVE SENTENCES: these systems achieve performance that EQUALS OR EVEN BEATS HUMANS IN SOME RESPECTS - DESPITE their biological inspiration and performance achievements, they DIFFER FROM HUMAN INTELLIGENCE IN CRUCIAL WAYS. Matching a score is separated from being alike, and the concession comes first— “Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial… | mechanisms[0] |
| mechanism | THE CRITERION IS SPLIT INTO TWO DIMENSIONS SO THAT A SYSTEM CAN FAIL ON EITHER: truly HUMAN-LIKE learning and thinking machines will have to reach beyond current engineering trends in BOTH WHAT THEY LEARN, AND HOW THEY LEARN IT. One adjective, two independent requirements— “We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it.” | mechanisms[1] |
| mechanism | A QUESTION IS DECLARED OLDER THAN THE NAMES OF BOTH FIELDS THAT ASK IT: the questions of whether and how AI should relate to human cognitive psychology are OLDER THAN THE TERMS ARTIFICIAL INTELLIGENCE AND COGNITIVE PSYCHOLOGY. The problem existed before either vocabulary did, which means neither vocabulary was built to state it— “The questions of whether and how AI should relate to human cognitive psychology are older than the terms ‘artificial intelligence’ and ‘cognitive psychology.’” | mechanisms[2] |
| mechanism | THE POSITION BEING ARGUED AGAINST IS QUOTED FROM A TEXTBOOK, AS AN ANALOGY ABOUT ABANDONING IMITATION: the quest for ARTIFICIAL FLIGHT succeeded WHEN THE WRIGHT BROTHERS AND OTHERS STOPPED IMITATING BIRDS and started using wind tunnels and learning about aerodynamics. The rival view is presented in its own strongest form, in its own words, with a page reference— “The quest for ‘artificial flight’ succeeded when the Wright brothers and others stopped imitating birds and started using wind tunnels and learning about aerodynamics.” (p. 3).” | mechanisms[3] |
| mechanism | A DEFENDER'S HOPE IS GRANTED SYMPATHY AND THEN DOUBTED, WITH THE DOUBT MARKED AS UNCERTAIN: WE CAN SYMPATHIZE WITH THAT HOPE AND BELIEVE IT DESERVES FURTHER EXPLORATION, ALTHOUGH WE ARE NOT SURE IT IS A REALISTIC ONE. Disagreement stated as an uncertainty about the opponent's prospects rather than as a refutation— “We can sympathize with that hope and believe it deserves further exploration, although we are not sure it is a realistic one.” | mechanisms[4] |
| mechanism | THE BENCHMARK'S SCALE IS MADE CONCRETE BY NAMING THE OBJECTS: benchmark tasks provide HUNDREDS OR THOUSANDS OF EXAMPLES PER CLASS - 1000 HAIRBRUSHES, 1000 PINEAPPLES, etc. - and one dataset includes 6000 examples of each handwritten digit. An abstract quantity is turned into a picture of what the quantity is made of— “Benchmark tasks such as the ImageNet data set for object recognition provides hundreds or thousands of examples per class (Krizhevsky et al., 2012; Russakovsky et al., 2015) – 1000 hairbrushes, 1000 pineapples, etc. In the context of learning new handwritten characters or learning to play Frostbite, the MNIST benchmark includes 6000 examples… | mechanisms[5] |
| mechanism | TWO QUANTITIES A SINGLE COMPARISON CONFLATES ARE SEPARATED IN A FOOTNOTE: the time required to train the network - **COMPUTE TIME** - IS NOT THE SAME AS THE GAME (EXPERIENCE) TIME, and compute time CAN BE LONGER. Two clocks under one word, distinguished where a reader might not look— “The time required to train the DQN (compute time) is not the same as the game (experience) time. Compute time can be longer.” | mechanisms[6] |
| mechanism | A METRIC IS DESCRIBED AS DESIGNED TO BLOCK ONE SPECIFIC CHEAT, AND ITS RIVALS' STATUS IS DECLARED UNKNOWN: the reported scores use the HUMAN STARTS measure, DESIGNED TO PREVENT NETWORKS FROM JUST MEMORIZING LONG SEQUENCES OF SUCCESSFUL ACTIONS FROM A SINGLE STARTING POINT - and faster learning and higher scores HAVE BEEN REPORTED USING OTHER METRICS, BUT IT IS UNCLEAR HOW WELL THE NETWORKS ARE GENERALIZING WITH THESE ALTERNATIVE METRICS. The number depends on which measure, and only one of them is known to mean what it says— “The reported scores use the “human starts” measure of test performance, designed to prevent networks from just memorizing long sequences of successful actions from a single starting point. Both faster learning (Blundell et al., 2016) and higher scores (Wang et al., 2016) have been reported using other metrics, but it is unclear how well the… | mechanisms[7] |
| mechanism | AN OPPOSING SCHOOL'S POSITION IS SUMMARISED AS A CLAIM ABOUT METAPHOR: proponents maintain that classic types of structured knowledge - graphs, grammars, rules, objects, programs - CAN BE USEFUL YET MISLEADING METAPHORS for characterizing thought, and that these structures are MORE EPIPHENOMENAL THAN REAL. The disagreement is over whether the vocabulary names things or describes them— “Proponents of this approach maintain that many classic types of structured knowledge, such as graphs, grammars, rules, objects, structural descriptions, programs, etc. can be useful yet misleading metaphors for characterizing thought. These structures are more epiphenomenal than real, emergent properties of more fundamental sub-symbolic… | mechanisms[8] |
| mechanism | THE OBJECTION TO THE PAPER'S OWN COMPARISON IS RAISED BY THE PAPER, EARLY, AND FLAGGED AS ANTICIPATED: one might object that both challenges draw an UNFAIR COMPARISON between the speed of human learning and neural network learning - discussed in detail later, BUT WE FEEL IT IS IMPORTANT TO ANTICIPATE HERE AS WELL. The strongest attack on the paper's method is placed before the method is used— “One might object that both the Frostbite and Characters challenges draw an unfair comparison between the speed of human learning and neural network learning. We discuss this objection in detail in Section 5, but we feel it is important to anticipate here as well.” | mechanisms[9] |
| mechanism | AND THE REFRAMING THE PAPER ADOPTS IS QUOTED FROM AN ANONYMOUS REVIEWER OF AN EARLIER DRAFT: THEY MAY BE BETTER SEEN AS SOLVING DIFFERENT TASKS - the human ENCOUNTERING ONE IN A YEARS-LONG STRING OF PROBLEMS WITH RICH OVERLAPPING STRUCTURE, the network STARTING COMPLETELY FROM SCRATCH. The comparison fails not through a confound but because one phrase, `the task`, was covering two different things - and the authors reply WE AGREE— “They may be better seen as solving different tasks. Human learners – unlike DQN and many other deep learning systems – approach new problems armed with extensive prior experience. The human is encountering one in a years-long string of problems, with rich overlapping structure. Humans as a result often have important domain-specific knowledge… | mechanisms[10] |
| mechanism | A CAPACITY IS SHOWN TO PERSIST DESPITE THE PRACTICE THAT WOULD EXPLAIN IT: children are FAR MORE PRACTICED than adults at learning new concepts - ROUGHLY NINE OR TEN NEW WORDS EACH DAY - YET the ability for rapid ONE-SHOT learning DOES NOT DISAPPEAR IN ADULTHOOD. The obvious explanation for the skill is present in one group and the skill in both— “Children are far more practiced than adults at learning new concepts – learning roughly nine or ten new words each day after beginning to speak through the end of high school (Bloom, 2000; Carey, 1978) – yet the ability for rapid “one-shot” learning does not disappear in adulthood.” | mechanisms[11] |
| mechanism | THE PAPER'S OWN CRITERIA ARE CALLED INGREDIENTS AND PLACED AFTER A REVIEW OF OTHER PEOPLE'S: first the criteria PREVIOUSLY OFFERED by cognitive scientists, developmental psychologists and AI researchers are reviewed - THEN what the authors VIEW AS THE ESSENTIAL INGREDIENTS is articulated. The list is presented as a synthesis with a named provenance, not as a definition— “We first review some of the criteria previously offered by cognitive scientists, developmental psychologists, and AI researchers. Second, we articulate what we view as the essential ingredients for building such a machine that learns or thinks like a person, synthesizing theoretical ideas and experimental data from research in cognitive… | mechanisms[12] |
| contradicts | the view that current deep-learning systems capture human intelligence— “these systems differ from human intelligence in crucial ways” | claim_relations[0] |
| builds-on | Lake, Salakhutdinov, & Tenenbaum (2015) probabilistic program induction for handwritten characters— “We recently reported progress on this challenge using probabilistic program induction (Lake, Salakhutdinov, & Tenenbaum, 2015), yet aspects of the full human cognitive ability remain out of reach.” | claim_relations[1] |
| contradicts | V. Mnih et al. (2015) Deep Q-Network playing Atari games— “Although it is interesting that the DQN learns to play games at human-level performance while assuming very little prior knowledge, the DQN may be learning to play Frostbite and other games in a very different way than people do.” | claim_relations[2] |
| contradicts | AlphaGo (Silver et al., 2016) as a system that understands the game— “As impressive as AlphaGo is in beating the world’s best players at the standard game – and it is extremely impressive – the fact that it cannot even conceive of these variants, let alone adapt to them autonomously, is a sign that it does not understand the game as humans do.” | claim_relations[3] |
| sense | equal benchmark performance - NOT EQUAL CAPABILITY: the authors state that humans and networks may score the same on MNIST and other large-scale image classification tasks while not learning or thinking in the same way, and name two respects in which they differ - the number of examples needed and the richness of what is learned— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two important differences: people learn from fewer examples and they learn richer representations” | senses[0] |
| sense | human-level performance - A PHRASE ATTACHED TO PARTICULAR DATA SETS: reported as an error rate very close to human on one task and as within reach on another, so the expression names a relation to a specific benchmark rather than a general parity— “The best results achieved using deep convolutional nets are very close to human-level performance at an error rate of 0.2% (Ciresan, Meier, & Schmidhuber, 2012). Similarly, recent results applying convolutional nets to the far more challenging ImageNet object recognition benchmark have shown that human-level performance is within reach on… | senses[1] |
| sense | the list of differences - A FLOOR, NOT A SET: the authors write that there are AT LEAST two important differences before naming two, so the enumeration is explicitly open and a reader who treats the two as the complete account has closed a list the authors left open— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two important differences: people learn from fewer examples and they learn richer representations” | senses[2] |
| sense | `deep learning` / `PDP models` - A RENAMING ACROSS THIRTY YEARS, AND THE PAPER SAYS THE CONTENT DID NOT CHANGE WITH THE NAME. `The resurgence of recent interest in neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models.` Both names describe the same objects and neither is wrong; what changed is which property the field chose to put in the name - PDP named the computation (parallel, distributed), `deep` names the layer count. The paper then glosses the new name explicitly: `“Deep” refers to the fact that more powerful models can be built by composing many layers of representation.`— “The resurgence of recent interest in neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models. “Deep” refers to the fact that more powerful models can be built by composing many layers of representation” | senses[3] |
| differs in | neural networks —contrasted-with→ people — how many examples are needed and how rich the learned representation is - a list the authors mark as at least two— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two important differences: people learn from fewer examples and they learn richer representations”— “people learn from fewer examples and they learn richer representations” | concept_edges[0] |
| audit | deep learning —renamed-across-fields→ PDP models — Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says deep learning shares the representational commitments of the earlier PDP models; renamed-across-fields is loose.— “The resurgence of recent interest in neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models. “Deep” refers to the fact that more powerful models can be built by composing many layers of representation” | concept_edges[1] |
| note | deep learning —renamed-across-fields→ PDP models — Both names sit inside the one span, as the type requires. Weight 0.9 rather than 1.0: the paper says 'often even the same learning algorithms' - the identity is asserted for the commitments and hedged for the algorithms. The split is across TIME rather than across a field boundary, which is the nearest type available and is recorded here as such.— “The resurgence of recent interest in neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models. “Deep” refers to the fact that more powerful models can be built by composing many layers of representation” | concept_edges[1] |
| relation | deep learning —renamed-across-fields→ PDP models — neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models— “The resurgence of recent interest in neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models. “Deep” refers to the fact that more powerful models can be built by composing many layers of representation” | concept_edges[1] |
| weight | deep learning —renamed-across-fields→ PDP models — 0.9— “The resurgence of recent interest in neural networks, more commonly referred to as “deep learning,” share the same representational commitments and often even the same learning algorithms as the earlier PDP models. “Deep” refers to the fact that more powerful models can be built by composing many layers of representation” | concept_edges[1] |
| for which use | limitation — the real-time control claim: PLANNING IN COMPLEX MODELS IS CUMBERSOME AND SLOW— “planning in complex models is cumbersome and slow” | limitations[0] |
| for which use | limitation — the scope of the whole article: WE HAVE SAID LITTLE ... ABOUT PEOPLE'S ABILITY TO COMMUNICATE AND THINK IN NATURAL LANGUAGE, A DISTINCTIVELY HUMAN COGNITIVE CAPACITY WHERE MACHINE CAPABILITIES LAG STRIKINGLY— “We have said little in this article about people’s ability to communicate and think in natural language, a distinctively human cognitive capacity where machine capabilities lag strikingly.” | limitations[1] |
| for which use | limitation — the list of core ingredients: WE DID NOT INTEND OUR LIST TO BE COMPLETE— “These are important questions for future work with the potential to expand the list of key ingredients; we did not intend our list to be complete.” | limitations[2] |
| for which use | limitation — the human-machine comparison: humans bring far richer prior experience to a new task than a network does, which the authors concede as an objection— “We agree that humans have a much richer starting point than neural networks when learning most new tasks, including learning a new concept or to play a new video game.” | limitations[3] |
| for which use | limitation — any comparison of human and network ability based on these benchmarks: the authors state that performing equally well on MNIST and other large-scale image classification tasks does not mean humans and networks learn and think in the same way— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two important differences: people learn from fewer examples and they learn richer representations” | limitations[5] |
| for which use | limitation — any claim that networks have matched human performance: the authors report an error rate very close to human-level on one task and describe human-level performance as within reach on the ImageNet benchmark— “The best results achieved using deep convolutional nets are very close to human-level performance at an error rate of 0.2% (Ciresan, Meier, & Schmidhuber, 2012). Similarly, recent results applying convolutional nets to the far more challenging ImageNet object recognition benchmark have shown that human-level performance is within reach on… | limitations[6] |
| evidence status note | mechanism — EXTENDED so the span carries the authors' assent in full - "We agree, and indeed this is another way of putting our point here" - rather than stopping at "We agree". The two words alone would have left it unclear whether they were conceding the objection or adopting the reframing. They adopt it: an anonymous reviewer's sentence becomes the paper's own statement of its point. NOTE ALSO that the reviewer quotation has a PAGE NUMBER spliced inside it a few words earlier - "solving the same task 14 differently" - which is why the span starts at the following sentence.— “They may be better seen as solving different tasks. Human learners – unlike DQN and many other deep learning systems – approach new problems armed with extensive prior experience. The human is encountering one in a years-long string of problems, with rich overlapping structure. Humans as a result often have important domain-specific knowledge… | mechanisms[10] |
| replication | untested | |
| limitation | planning in complex (model-based) systems is cumbersome and slow for real-time control— “planning in complex models is cumbersome and slow” | limitations[0] |
| limitation | The article says very little about natural language, a capacity the authors concede is central to human intelligence.— “We have said little in this article about people’s ability to communicate and think in natural language, a distinctively human cognitive capacity where machine capabilities lag strikingly.” | limitations[1] |
| limitation | The proposed list of core ingredients is explicitly not claimed to be complete.— “These are important questions for future work with the potential to expand the list of key ingredients; we did not intend our list to be complete.” | limitations[2] |
| limitation | The authors concede the objection that humans bring far richer prior experience to a new task than a network does, which complicates the learning-speed comparisons the paper rests on.— “We agree that humans have a much richer starting point than neural networks when learning most new tasks, including learning a new concept or to play a new video game.” | limitations[3] |
| limitation | Their own prior model of the Characters Challenge does not capture the full human ability.— “We recently reported progress on this challenge using probabilistic program induction (Lake, Salakhutdinov, & Tenenbaum, 2015), yet aspects of the full human cognitive ability remain out of reach.” | limitations[4] |
| limitation | Equal performance on the benchmark is stated not to indicate equal capability.— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two important differences: people learn from fewer examples and they learn richer representations” | limitations[5] |
| limitation | The human-level comparison is stated for specific data sets, with one described as within reach rather than reached.— “The best results achieved using deep convolutional nets are very close to human-level performance at an error rate of 0.2% (Ciresan, Meier, & Schmidhuber, 2012). Similarly, recent results applying convolutional nets to the far more challenging ImageNet object recognition benchmark have shown that human-level performance is within reach on… | limitations[6] |
finding · quantity · variable · definition · key-term — grounded in the full text| finding | these systems differ in crucial ways from how humans think— “these systems differ from human intelligence in crucial ways” | content_tags.findings[0] |
| finding | human-like machines should build causal models of the world— “Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding” | content_tags.findings[1] |
| finding | learning should be grounded in intuitive physics and psychology— “ground learning in intuitive theories of physics and psychology” | content_tags.findings[2] |
| finding | machines should harness compositionality and learning-to-learn— “harness compositionality and learning-to-learn” | content_tags.findings[3] |
| quantity | 3 arguments — proposed ingredients (a,b,c) for human-like machines— “these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (b) ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn” | content_tags.quantities[0] |
| quantity | ~half error rate — Krizhevsky convnet cut the prior error rate— “nearly halved the error rate of the previous state-of-the-art” | content_tags.quantities[1] |
| quantity | late 1980s era — when HMMs became the leading speech approach— “been the leading approach since the late 1980s” | content_tags.quantities[2] |
| variable | causal models (proposed ingredient for understanding)— “Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems” | content_tags.variables[1] |
| variable | intuitive theories (knowledge grounding in physics and psychology)— “intuitive theories of physics and psychology” | content_tags.variables[2] |
| variable | compositionality (enables rapid generalization)— “harness compositionality and learning-to-learn” | content_tags.variables[3] |
| definition | deep learning— “Much of this progress has come from recent advances in “deep learning,” characterized by learning large neural-network-style” | content_tags.definitions[0] |
| definition | deep reinforcement learning— “(2015) combined ideas from deep learning and reinforcement learning to make a “deep reinforcement learning” algorithm that learns to play large classes of simple video games from just frames of pixels” | content_tags.definitions[1] |
| definition | convolutional neural network— “trained a deep convolutional neural network (convnets; LeCun et al., 1989)” | content_tags.definitions[2] |
| definition | learning-to-learn— “learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations” | content_tags.definitions[3] |
| key-terms | artificial intelligence, deep learning, neural networks, human intelligence, causal models, intuitive theories, compositionality, learning-to-learn, cognitive science, pattern recognition |
| concept | MNIST— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two important differences: people learn from fewer examples and they learn richer representations” | concepts[4] |
| concept | richer representations— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two important differences: people learn from fewer examples and they learn richer representations” | concepts[5] |
| concept | human-level performance— “The best results achieved using deep convolutional nets are very close to human-level performance at an error rate of 0.2% (Ciresan, Meier, & Schmidhuber, 2012). Similarly, recent results applying convolutional nets to the far more challenging ImageNet object recognition benchmark have shown that human-level performance is within reach on… | concepts[6] |
| concept | ImageNet— “The best results achieved using deep convolutional nets are very close to human-level performance at an error rate of 0.2% (Ciresan, Meier, & Schmidhuber, 2012). Similarly, recent results applying convolutional nets to the far more challenging ImageNet object recognition benchmark have shown that human-level performance is within reach on… | concepts[7] |
| concept | neural networks— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two important differences: people learn from fewer examples and they learn richer representations” | concepts[8] |
| concept | people— “While humans and neural networks may perform equally well on the MNIST digit recognition task and other large-scale image classification tasks, it does not mean that they learn and think in the same way. There are at least two… | concepts[9] |
| concept | deep learning — not defined in this paper's own words; the current name for work the paper says shares the representational commitments AND often the algorithms of 1980s PDP models; 'deep' names a property of the architecture, not a new commitment | concepts[10] |
| concept | PDP models — not defined in this paper's own words; the earlier name for the same programme - parallel distributed processing, named for the computation rather than for the depth | concepts[11] |
| concept | Intuitive psychology — not defined in this paper's own words; the early-emerging capacity to treat some things as agents; the record already carried 'intuitive physics' and not its sibling, so the paper's pair was recorded by halves | concepts[12] |
| Bayesian | content_tags.statistics[0] | |
| mean μ | as written: average of Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[1] |
| regression β | EVIDENCE CORRECTED (RE-GROUNDED) · as written: regression model Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[2] |
| retracted | regression — RE-GROUNDED. The old evidence was 'Automatic con- struction and natural-language description of nonparametric regression models.' - THE TITLE OF A PAPER BY SOMEBODY ELSE, sitting in this paper's bibliography. An internal tool cuts the reference list on purpose, for exactly this reason, so the row was invisible to every grounding check. lake2017 uses 'regression' once in its own prose and that sentence is now the evidence. | content_tags.statistics[2] |
| statistical-significance | as written: significantly Quotation withheld — this paper is not ours to reproduce, and the page has already quoted as much of it as the rights layer allows. The tag, its field and its confidence stand; the sentence is at the publisher. | content_tags.statistics[3] |
When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.
Tag layer © the Meta-Tagging Project, CC BY 4.0. The paper text is © its authors/publisher
and is linked, not reproduced. Excerpts shown are short quotations for identification and verification.
· back to index
· concepts · authors
· עברית
© 2026 Shir Sivroni · ORCID 0009-0000-2597-2824