{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/semi-supervised-learning-of-visual-features","title":"Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples","arxiv_id":"2104.13963","date":"2021-04-28","proceeding":"ICCV 2021 10","authors":["Mahmoud Assran","Mathilde Caron","Ishan Misra","Piotr Bojanowski","Armand Joulin","Nicolas Ballas","Michael Rabbat"],"abstract":"This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are assigned similar pseudo-labels. The pseudo-labels are generated non-parametrically, by comparing the representations of the image views to those of a set of randomly sampled labeled images. The distance between the view representations and labeled representations is used to provide a weighting over class labels, which we interpret as a soft pseudo-label. By non-parametrically incorporating labeled samples in this way, PAWS extends the distance-metric loss used in self-supervised methods such as BYOL and SwAV to the semi-supervised setting. Despite the simplicity of the approach, PAWS outperforms other semi-supervised methods across architectures, setting a new state-of-the-art for a ResNet-50 on ImageNet trained with either 10% or 1% of the labels, reaching 75.5% and 66.5% top-1 respectively. PAWS requires 4x to 12x less training than the previous best methods.","url_abs":"https://arxiv.org/abs/2104.13963v3","url_pdf":"https://arxiv.org/pdf/2104.13963v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"semi-supervised-learning-of-visual-features","repo_url":"https://github.com/facebookresearch/suncet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"semi-supervised-learning-of-visual-features","repo_url":"https://github.com/beresandras/semisupervised-classification-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"semi-supervised-learning-of-visual-features","repo_url":"https://github.com/facebookresearch/msn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"semi-supervised-learning-of-visual-features","repo_url":"https://github.com/sayakpaul/PAWS-TF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[{"method_slug":"byol","method_name":"BYOL"},{"method_slug":"lars","method_name":"LARS"},{"method_slug":"swav","method_name":"SwAV"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PAWS (ResNet-50, 10% labels)","rank_in_archive_order":946,"of":1060,"metrics":{"Top 1 Accuracy":"75.5%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"PAWS (ResNet-50, 1% labels)","rank_in_archive_order":1042,"of":1060,"metrics":{"Top 1 Accuracy":"66.5%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 4000 Labels","model":"PAWS-NN (WRN-28-2)","rank_in_archive_order":7,"of":49,"metrics":{"Percentage error":"4.0 ± 0.25"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"PAWS (ResNet-50 4x)","rank_in_archive_order":21,"of":65,"metrics":{"Top 1 Accuracy":"69.9%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"PAWS (ResNet-50 2x)","rank_in_archive_order":22,"of":65,"metrics":{"Top 1 Accuracy":"69.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"PAWS (ResNet-50)","rank_in_archive_order":29,"of":65,"metrics":{"Top 1 Accuracy":"66.5%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"PAWS (ResNet-50 4x)","rank_in_archive_order":14,"of":75,"metrics":{"Top 1 Accuracy":"79.0%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"PAWS (ResNet-50 2x)","rank_in_archive_order":19,"of":75,"metrics":{"Top 1 Accuracy":"77.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"PAWS (ResNet-50)","rank_in_archive_order":25,"of":75,"metrics":{"Top 1 Accuracy":"75.5%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.13963","atlas_url":"https://app.syntology.ai/?focus=2104.13963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.13963"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.13963"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2104.13963"},"call":"get_harvested_code_for_paper(arxiv_id=\"2104.13963\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2104.13963"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2104.13963\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2104.13963"},"call":"get_concepts_for_paper(arxiv_id=\"2104.13963\")"}],"by_repo":[{"repo":"facebookresearch/suncet","kind":"official","samples":2,"ran":2,"instrument":1,"unverified":0},{"repo":"beresandras/semisupervised-classification-keras","kind":"listed","samples":2,"ran":2,"instrument":0,"unverified":0},{"repo":"facebookresearch/msn","kind":"listed","samples":3,"ran":3,"instrument":2,"unverified":0},{"repo":"sayakpaul/PAWS-TF","kind":"listed","samples":14,"ran":12,"instrument":0,"unverified":2}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"212e3a049ee99420","source_kind":"harvested","method_name":"PAWS","realizes_method":"PAWS","graph_method":"PAWS","realizes_severed":false,"claim":"This function implements the PAWS method's consistency loss, which trains a model to minimize the difference in pseudo-label assignments for different views of the same unlabeled instance using support samples.","centrality":"contribution","entry":"init_msn_loss","entry_sha256":"8058e8c73e3a9d20","n_bricks":3,"bricks":[{"entry":"init_msn_loss","code_sha256":"8058e8c73e3a9d20","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"},{"entry":"AllReduce","code_sha256":"95ac5fe2166b117a","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"distributed_sinkhorn","code_sha256":"7478f8e64cee8964","role":"helper","order":2,"level":1,"status":"ran_fixture"}],"ran_individually":3,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_draft_wrong":1,"ran_fixture":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"f8b409416955","n_siblings":2,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"36abc99ce21fb515","source_kind":"harvested","method_name":"PAWS","realizes_method":"PAWS","graph_method":"PAWS","realizes_severed":false,"claim":"The code implements a consistency loss that ensures different views of the same unlabeled instance are assigned similar pseudo-labels, as proposed by PAWS.","centrality":"contribution","entry":"init_paws_loss","entry_sha256":"e4fcb778fbb424df","n_bricks":3,"bricks":[{"entry":"init_paws_loss","code_sha256":"e4fcb778fbb424df","role":"entry","order":0,"level":1,"status":"ran_draft_wrong"},{"entry":"AllGather","code_sha256":"f68fac75925a8996","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"AllReduce","code_sha256":"95ac5fe2166b117a","role":"helper","order":2,"level":1,"status":"ran"}],"ran_individually":3,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"f8b409416955","n_siblings":2,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"98e22d16a0df27e3","source_kind":"harvested","method_name":"PAWS","realizes_method":"PAWS","graph_method":"PAWS","realizes_severed":false,"claim":"The paper claims this code implements a method that trains a model to minimize a consistency loss by predicting view assignments with support samples, generating pseudo-labels for unlabeled data.","centrality":"contribution","entry":"PAWS","entry_sha256":"1bb1dee92e0a093b","n_bricks":2,"bricks":[{"entry":"PAWS","code_sha256":"1bb1dee92e0a093b","role":"entry","order":0,"level":1,"status":"ran"},{"entry":"SemisupervisedModel","code_sha256":"71e80bb6a7133768","role":"helper","order":1,"level":1,"status":"ran"}],"ran_individually":2,"ran_individually_constructed":2,"ran_individually_by_status":{"ran":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"f8b409416955","n_siblings":2,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"f8b409416955","realizes_method":"PAWS","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["212e3a049ee99420","36abc99ce21fb515","98e22d16a0df27e3"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"2104.13963"},"call":"assembly(arxiv_id=\"2104.13963\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2104.13963.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2104.13963.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/msn","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sayakpaul/PAWS-TF","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/beresandras/semisupervised-classification-keras","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/suncet","reach":null}],"summary":{"ran":16,"ran_fixture":1,"ran_draft_wrong":2,"unverified":2},"n_samples":21,"n_ran":19,"n_constructed":4,"n_ran_checked":16,"n_instrument":3,"n_unverified":2,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":2,"ran":2,"n_ran_checked":1,"n_instrument":1,"repositories":1},"listed":{"samples":19,"ran":17,"n_ran_checked":15,"n_instrument":2,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":19,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"f68fac75925a8996","code_sha256_prefix":"f68fac75925a8996","entry":"AllGather","repo":"facebookresearch/suncet","repo_kind":"official","path":"src/losses.py","file_url":"https://github.com/facebookresearch/suncet/blob/HEAD/src/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"AllGather","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/allgather","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f68fac75925a8996"}},{"code_sha256":"95ac5fe2166b117a","code_sha256_prefix":"95ac5fe2166b117a","entry":"AllReduce","repo":"facebookresearch/msn","repo_kind":"listed","path":"src/losses.py","file_url":"https://github.com/facebookresearch/msn/blob/HEAD/src/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"AllReduce","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, facebookresearch/msn (NOASSERTION)","mcp_get_code":{"code_sha256":"95ac5fe2166b117a"}},{"code_sha256":"1bb1dee92e0a093b","code_sha256_prefix":"1bb1dee92e0a093b","entry":"PAWS","repo":"beresandras/semisupervised-classification-keras","repo_kind":"listed","path":"algorithms.py","file_url":"https://github.com/beresandras/semisupervised-classification-keras/blob/HEAD/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"PAWS","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1bb1dee92e0a093b"}},{"code_sha256":"71e80bb6a7133768","code_sha256_prefix":"71e80bb6a7133768","entry":"SemisupervisedModel","repo":"beresandras/semisupervised-classification-keras","repo_kind":"listed","path":"algorithms.py","file_url":"https://github.com/beresandras/semisupervised-classification-keras/blob/HEAD/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"SemisupervisedModel","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"71e80bb6a7133768"}},{"code_sha256":"7478f8e64cee8964","code_sha256_prefix":"7478f8e64cee8964","entry":"distributed_sinkhorn","repo":"facebookresearch/msn","repo_kind":"listed","path":"src/losses.py","file_url":"https://github.com/facebookresearch/msn/blob/HEAD/src/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"signature":"Q:Tensor/2/float, num_itr:int/0/int, use_dist:bool/0/bool","fixture_out_type":"Tensor","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7478f8e64cee8964"},"code_page":"/code/distributed-sinkhorn","census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, facebookresearch/msn (NOASSERTION)","mcp_get_code":{"code_sha256":"7478f8e64cee8964"}},{"code_sha256":"0f0390c1cd8dff66","code_sha256_prefix":"0f0390c1cd8dff66","entry":"float_parameter","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"utils/multicrop_loader.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/utils/multicrop_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"level:int/0/int, maxval:int/0/int","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":"/code/float-parameter","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0f0390c1cd8dff66"}},{"code_sha256":"6a55065d9c679d3c","code_sha256_prefix":"6a55065d9c679d3c","entry":"get_paws_loss","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"utils/losses.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/utils/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"multicrop:int/0/int, tau:float/0/float, T:float/0/float, me_max:bool/0/bool","fixture_out_type":"function","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6a55065d9c679d3c"}},{"code_sha256":"8058e8c73e3a9d20","code_sha256_prefix":"8058e8c73e3a9d20","entry":"init_msn_loss","repo":"facebookresearch/msn","repo_kind":"listed","path":"src/losses.py","file_url":"https://github.com/facebookresearch/msn/blob/HEAD/src/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"num_views:int/0/int, tau:float/0/float, me_max:bool/0/bool, return_preds:bool/0/bool","fixture_out_type":"function","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, facebookresearch/msn (NOASSERTION)","mcp_get_code":{"code_sha256":"8058e8c73e3a9d20"}},{"code_sha256":"e4fcb778fbb424df","code_sha256_prefix":"e4fcb778fbb424df","entry":"init_paws_loss","repo":"facebookresearch/suncet","repo_kind":"official","path":"src/losses.py","file_url":"https://github.com/facebookresearch/suncet/blob/HEAD/src/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"multicrop:int/0/int, tau:float/0/float, T:float/0/float, me_max:bool/0/bool","fixture_out_type":"function","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e4fcb778fbb424df"}},{"code_sha256":"05d7d78714b9de1b","code_sha256_prefix":"05d7d78714b9de1b","entry":"layer","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"models/wide_resnet.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/models/wide_resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"block:callable/0/?, n_input_plane:int/0/int, n_output_plane:int/0/int, count:int/0/int, stride:tuple/1/int","fixture_out_type":"function","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":"/code/layer-2","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"05d7d78714b9de1b"}},{"code_sha256":"0756356a6dd842aa","code_sha256_prefix":"0756356a6dd842aa","entry":"learner","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"models/resnet20.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/models/resnet20.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:SymbolicTensor/4/float, n_blocks:int/0/int","fixture_out_type":"SymbolicTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0756356a6dd842aa"}},{"code_sha256":"fe3cc1bc7312b8a0","code_sha256_prefix":"fe3cc1bc7312b8a0","entry":"onehot_encode","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"utils/labeled_loader.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/utils/labeled_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"labels:EagerTensor/1/int, label_smoothing:float/0/float","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":"/code/onehot-encode","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fe3cc1bc7312b8a0"}},{"code_sha256":"cd82cca1cbf4ebbc","code_sha256_prefix":"cd82cca1cbf4ebbc","entry":"projection_head","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"models/wide_resnet.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/models/wide_resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:EagerTensor/2/float, hidden_dim:int/0/int","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"cd82cca1cbf4ebbc"}},{"code_sha256":"abadc575eb223999","code_sha256_prefix":"abadc575eb223999","entry":"residual_group","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"models/resnet20.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/models/resnet20.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"x:EagerTensor/4/float, n_filters:int/0/int, n_blocks:int/0/int, strides:tuple/1/int, n:int/0/int","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"abadc575eb223999"}},{"code_sha256":"08ad311e00fe4f97","code_sha256_prefix":"08ad311e00fe4f97","entry":"sample_level","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"utils/multicrop_loader.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/utils/multicrop_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"n:float/0/float","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":"/code/sample-level","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"08ad311e00fe4f97"}},{"code_sha256":"3d22afdeab459a13","code_sha256_prefix":"3d22afdeab459a13","entry":"snn","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"nn_eval.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/nn_eval.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"query:EagerTensor/2/float, h_train:EagerTensor/2/float, h_labs:EagerTensor/2/float, temp:float/0/float","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3d22afdeab459a13"}},{"code_sha256":"879172744bfa9ab1","code_sha256_prefix":"879172744bfa9ab1","entry":"solarize","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"utils/multicrop_loader.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/utils/multicrop_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:EagerTensor/3/float, level:int/0/int","fixture_out_type":"EagerTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":"/code/solarize","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"879172744bfa9ab1"}},{"code_sha256":"4771975a4479f016","code_sha256_prefix":"4771975a4479f016","entry":"stem","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"models/resnet20.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/models/resnet20.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"inputs:KerasTensor/4/float","fixture_out_type":"KerasTensor","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":"/code/stem","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4771975a4479f016"}},{"code_sha256":"40d8c0a153356fd9","code_sha256_prefix":"40d8c0a153356fd9","entry":"wide_basic","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"models/wide_resnet.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/models/wide_resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"n_input_plane:int/0/int, n_output_plane:int/0/int, stride:tuple/1/int","fixture_out_type":"function","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"40d8c0a153356fd9"}},{"code_sha256":"9c8af1a1234a70bb","code_sha256_prefix":"9c8af1a1234a70bb","entry":"dataset_for_class","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"utils/labeled_loader.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/utils/labeled_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9c8af1a1234a70bb"}},{"code_sha256":"c1d2ae4c09280e21","code_sha256_prefix":"c1d2ae4c09280e21","entry":"get_support_ds","repo":"sayakpaul/PAWS-TF","repo_kind":"listed","path":"utils/labeled_loader.py","file_url":"https://github.com/sayakpaul/PAWS-TF/blob/HEAD/utils/labeled_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c1d2ae4c09280e21"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c38cd0ceb85607bc374b2e888f484aa5bdda82ff36101362ed6768e08415c3ff","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}