{"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":"/code/featurizer","entry":"Featurizer","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":11,"n_papers_ran":4,"n_papers_ran_no_instrument_failure":3,"n_papers_ran_instrument_only":1,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":10,"n_samples_ran":4,"n_samples_constructed":1,"n_samples_ran_checked":3,"n_samples_instrument":1,"n_samples_unverified":6,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":4,"n_places_pointer_only_link_open":0,"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_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":3,"unverified":6},"key_notes":{"n_samples_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_samples_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)"},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.16372","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-16372","title":"SWORDBENCH: Evaluating Orthogonality of Steering Image Representations","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Weixin-Liang/MetaShift","path":"experiments/distribution_shift/networks.py","file_url":"https://github.com/Weixin-Liang/MetaShift/blob/HEAD/experiments/distribution_shift/networks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"35b902a4c075efc3","code_sha256_prefix":"35b902a4c075efc3","mcp_get_code":{"code_sha256":"35b902a4c075efc3"}},{"arxiv_id":"2603.25839","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-25839","title":"A Compression Perspective on Simplicity Bias","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"3rdCore/complicity","path":"source/networks.py","file_url":"https://github.com/3rdCore/complicity/blob/HEAD/source/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"ec18af6058c44a7b","code_sha256_prefix":"ec18af6058c44a7b","mcp_get_code":{"code_sha256":"ec18af6058c44a7b"}},{"arxiv_id":"2601.21999","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-21999","title":"Negatives-Dominant Contrastive Learning for Generalization in Imbalanced Domains","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Alrash/NDCL","path":"src/algorithms.py","file_url":"https://github.com/Alrash/NDCL/blob/HEAD/src/algorithms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"5586e626465a1519","code_sha256_prefix":"5586e626465a1519","mcp_get_code":{"code_sha256":"5586e626465a1519"}},{"arxiv_id":"2502.04242","arxiv_id_is_arxiv":true,"paper":"/paper/a-theoretical-framework-for-data-efficient","title":"A Theoretical Framework for Data Efficient Multi-Source Transfer Learning Based on Cramér-Rao Bound","date":"2025-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zqy0126/OTQMS","path":"algorithms.py","file_url":"https://github.com/zqy0126/OTQMS/blob/HEAD/algorithms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zqy0126/OTQMS when it was checked","code_sha256":"df389b17a2896c02","code_sha256_prefix":"df389b17a2896c02","mcp_get_code":{"code_sha256":"df389b17a2896c02"}},{"arxiv_id":"2307.12502","arxiv_id_is_arxiv":true,"paper":"/paper/cross-contrastive-feature-perturbation-for","title":"Cross Contrasting Feature Perturbation for Domain Generalization","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization","path":"algorithms.py","file_url":"https://github.com/hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization/blob/HEAD/algorithms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, hackmebroo/cross-contrasting-feature-perturbation-for-domain-generalization when it was checked","code_sha256":"9e043048978eb855","code_sha256_prefix":"9e043048978eb855","mcp_get_code":{"code_sha256":"9e043048978eb855"}},{"arxiv_id":"2306.08328","arxiv_id_is_arxiv":true,"paper":"/paper/distribution-shift-inversion-for-out-of-1","title":"Distribution Shift Inversion for Out-of-Distribution Prediction","date":"2023-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yu-rp/distribution-shift-iverson","path":"DSI/Predictor/domainbed_part/networks.py","file_url":"https://github.com/yu-rp/distribution-shift-iverson/blob/HEAD/DSI/Predictor/domainbed_part/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"387b3ed83dbf9591","code_sha256_prefix":"387b3ed83dbf9591","mcp_get_code":{"code_sha256":"387b3ed83dbf9591"}},{"arxiv_id":"2303.10353","arxiv_id_is_arxiv":true,"paper":"/paper/sharpness-aware-gradient-matching-for-domain","title":"Sharpness-Aware Gradient Matching for Domain Generalization","date":"2023-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wang-pengfei/sagm","path":"domainbed/algorithms/algorithms.py","file_url":"https://github.com/wang-pengfei/sagm/blob/HEAD/domainbed/algorithms/algorithms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"467b3583a59f952e","code_sha256_prefix":"467b3583a59f952e","mcp_get_code":{"code_sha256":"467b3583a59f952e"}},{"arxiv_id":"2301.12067","arxiv_id_is_arxiv":true,"paper":"/paper/learning-optimal-features-via-partial","title":"Learning Optimal Features via Partial Invariance","date":"2023-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IbtihalFerwana/pirm","path":"metashift/experiments/distribution_shift/algorithms.py","file_url":"https://github.com/IbtihalFerwana/pirm/blob/HEAD/metashift/experiments/distribution_shift/algorithms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"35b902a4c075efc3","code_sha256_prefix":"35b902a4c075efc3","mcp_get_code":{"code_sha256":"35b902a4c075efc3"}},{"arxiv_id":"2210.03115","arxiv_id_is_arxiv":true,"paper":"/paper/simper-simple-self-supervised-learning-of","title":"SimPer: Simple Self-Supervised Learning of Periodic Targets","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yyzharry/simper","path":"src/simper.py","file_url":"https://github.com/yyzharry/simper/blob/HEAD/src/simper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, yyzharry/simper (NOASSERTION)","code_sha256":"4ac0d2e193eab8a6","code_sha256_prefix":"4ac0d2e193eab8a6","mcp_get_code":{"code_sha256":"4ac0d2e193eab8a6"}},{"arxiv_id":"2205.14546","arxiv_id_is_arxiv":true,"paper":"/paper/the-missing-invariance-principle-found-the","title":"The Missing Invariance Principle Found -- the Reciprocal Twin of Invariant Risk Minimization","date":"2022-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/mri","path":"custom_algorithms.py","file_url":"https://github.com/ibm/mri/blob/HEAD/custom_algorithms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"28f76c5b44ed54e5","code_sha256_prefix":"28f76c5b44ed54e5","mcp_get_code":{"code_sha256":"28f76c5b44ed54e5"}},{"arxiv_id":"2201.11259","arxiv_id_is_arxiv":true,"paper":"/paper/controlling-directions-orthogonal-to-a-1","title":"Controlling Directions Orthogonal to a Classifier","date":"2022-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"newbeeer/orthogonal_classifier","path":"style_transfer/algorithms.py","file_url":"https://github.com/newbeeer/orthogonal_classifier/blob/HEAD/style_transfer/algorithms.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, newbeeer/orthogonal_classifier when it was checked","code_sha256":"20eba8a32c4f4158","code_sha256_prefix":"20eba8a32c4f4158","mcp_get_code":{"code_sha256":"20eba8a32c4f4158"}}],"record_sha256":"4a0521687731d82c074b297bc359afffdf5ea076630ea9cfbdcb2f6be494bdf8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}