{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QWDOHCJHU2JTNLX7YYUALVUAZY","short_pith_number":"pith:QWDOHCJH","schema_version":"1.0","canonical_sha256":"8586e38927a69336aeffc62805d680ce1c88cafa812278249683a49f41fe6ff5","source":{"kind":"arxiv","id":"2412.17170","version":1},"attestation_state":"computed","paper":{"title":"Where Did Your Model Learn That? Label-free Influence for Self-supervised Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amit Kiran Rege, Claire Monteleoni, Maziar Raissi, Nidhin Harilal, Reza Akbarian Bafghi","submitted_at":"2024-12-22T21:43:56Z","abstract_excerpt":"Self-supervised learning (SSL) has revolutionized learning from large-scale unlabeled datasets, yet the intrinsic relationship between pretraining data and the learned representations remains poorly understood. Traditional supervised learning benefits from gradient-based data attribution tools like influence functions that measure the contribution of an individual data point to model predictions. However, existing definitions of influence rely on labels, making them unsuitable for SSL settings. We address this gap by introducing Influence-SSL, a novel and label-free approach for defining influ"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.17170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-22T21:43:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5ddf8edd429162f21cf8b707a9bb5e8cf7705239d0f777dff78dc081acf83b40","abstract_canon_sha256":"817cc571f95e699adedec85b8079062ff12640bfec2f22f6611fadc5d6bad3f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:18.366546Z","signature_b64":"0U0EwAvjzTT7y3L9yUVjBB1oXT7dPZC8lhitcvBvf3Kfq9sks9GacYCTZCHFa3wvDZls8aiCQHvYmrjmAygeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8586e38927a69336aeffc62805d680ce1c88cafa812278249683a49f41fe6ff5","last_reissued_at":"2026-07-05T09:53:18.366091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:18.366091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where Did Your Model Learn That? Label-free Influence for Self-supervised Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Amit Kiran Rege, Claire Monteleoni, Maziar Raissi, Nidhin Harilal, Reza Akbarian Bafghi","submitted_at":"2024-12-22T21:43:56Z","abstract_excerpt":"Self-supervised learning (SSL) has revolutionized learning from large-scale unlabeled datasets, yet the intrinsic relationship between pretraining data and the learned representations remains poorly understood. Traditional supervised learning benefits from gradient-based data attribution tools like influence functions that measure the contribution of an individual data point to model predictions. However, existing definitions of influence rely on labels, making them unsuitable for SSL settings. We address this gap by introducing Influence-SSL, a novel and label-free approach for defining influ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17170","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.17170/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.17170","created_at":"2026-07-05T09:53:18.366155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17170v1","created_at":"2026-07-05T09:53:18.366155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17170","created_at":"2026-07-05T09:53:18.366155+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWDOHCJHU2JT","created_at":"2026-07-05T09:53:18.366155+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWDOHCJHU2JTNLX7","created_at":"2026-07-05T09:53:18.366155+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWDOHCJH","created_at":"2026-07-05T09:53:18.366155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY","json":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY.json","graph_json":"https://pith.science/api/pith-number/QWDOHCJHU2JTNLX7YYUALVUAZY/graph.json","events_json":"https://pith.science/api/pith-number/QWDOHCJHU2JTNLX7YYUALVUAZY/events.json","paper":"https://pith.science/paper/QWDOHCJH"},"agent_actions":{"view_html":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY","download_json":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY.json","view_paper":"https://pith.science/paper/QWDOHCJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17170&json=true","fetch_graph":"https://pith.science/api/pith-number/QWDOHCJHU2JTNLX7YYUALVUAZY/graph.json","fetch_events":"https://pith.science/api/pith-number/QWDOHCJHU2JTNLX7YYUALVUAZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY/action/storage_attestation","attest_author":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY/action/author_attestation","sign_citation":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY/action/citation_signature","submit_replication":"https://pith.science/pith/QWDOHCJHU2JTNLX7YYUALVUAZY/action/replication_record"}},"created_at":"2026-07-05T09:53:18.366155+00:00","updated_at":"2026-07-05T09:53:18.366155+00:00"}