{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YE2BS2SM6ZM2FOJPYMMDD4EIV4","short_pith_number":"pith:YE2BS2SM","schema_version":"1.0","canonical_sha256":"c134196a4cf659a2b92fc31831f088af2d63fc0867e546690b568f20bb7dc18f","source":{"kind":"arxiv","id":"2505.22196","version":1},"attestation_state":"computed","paper":{"title":"An Augmentation-Aware Theory for Self-Supervised Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongwei Wen, Jingyi Cui, Yisen Wang","submitted_at":"2025-05-28T10:18:20Z","abstract_excerpt":"Self-supervised contrastive learning has emerged as a powerful tool in machine learning and computer vision to learn meaningful representations from unlabeled data. Meanwhile, its empirical success has encouraged many theoretical studies to reveal the learning mechanisms. However, in the existing theoretical research, the role of data augmentation is still under-exploited, especially the effects of specific augmentation types. To fill in the blank, we for the first time propose an augmentation-aware error bound for self-supervised contrastive learning, showing that the supervised risk is bound"},"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":"2505.22196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T10:18:20Z","cross_cats_sorted":[],"title_canon_sha256":"89d495d61517183cd9a407fe052db60e155eafdf15c251d63063dc7046f41d9d","abstract_canon_sha256":"3089021d6f0166464c7b74a4f7371dc1b74d5c2f3a141aa8cb54caedee1d8d3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:11.287877Z","signature_b64":"s0WXP5s6NKiwytOehjvPvSbYC8EQuiWbSoe1VJ+8q3N7XDqcdgL4zSEveOrUayJEttco7N/HK2IpPQ+IUaZ0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c134196a4cf659a2b92fc31831f088af2d63fc0867e546690b568f20bb7dc18f","last_reissued_at":"2026-07-05T11:11:11.287385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:11.287385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Augmentation-Aware Theory for Self-Supervised Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongwei Wen, Jingyi Cui, Yisen Wang","submitted_at":"2025-05-28T10:18:20Z","abstract_excerpt":"Self-supervised contrastive learning has emerged as a powerful tool in machine learning and computer vision to learn meaningful representations from unlabeled data. Meanwhile, its empirical success has encouraged many theoretical studies to reveal the learning mechanisms. However, in the existing theoretical research, the role of data augmentation is still under-exploited, especially the effects of specific augmentation types. To fill in the blank, we for the first time propose an augmentation-aware error bound for self-supervised contrastive learning, showing that the supervised risk is bound"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22196","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/2505.22196/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":"2505.22196","created_at":"2026-07-05T11:11:11.287443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22196v1","created_at":"2026-07-05T11:11:11.287443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22196","created_at":"2026-07-05T11:11:11.287443+00:00"},{"alias_kind":"pith_short_12","alias_value":"YE2BS2SM6ZM2","created_at":"2026-07-05T11:11:11.287443+00:00"},{"alias_kind":"pith_short_16","alias_value":"YE2BS2SM6ZM2FOJP","created_at":"2026-07-05T11:11:11.287443+00:00"},{"alias_kind":"pith_short_8","alias_value":"YE2BS2SM","created_at":"2026-07-05T11:11:11.287443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4","json":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4.json","graph_json":"https://pith.science/api/pith-number/YE2BS2SM6ZM2FOJPYMMDD4EIV4/graph.json","events_json":"https://pith.science/api/pith-number/YE2BS2SM6ZM2FOJPYMMDD4EIV4/events.json","paper":"https://pith.science/paper/YE2BS2SM"},"agent_actions":{"view_html":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4","download_json":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4.json","view_paper":"https://pith.science/paper/YE2BS2SM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22196&json=true","fetch_graph":"https://pith.science/api/pith-number/YE2BS2SM6ZM2FOJPYMMDD4EIV4/graph.json","fetch_events":"https://pith.science/api/pith-number/YE2BS2SM6ZM2FOJPYMMDD4EIV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4/action/storage_attestation","attest_author":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4/action/author_attestation","sign_citation":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4/action/citation_signature","submit_replication":"https://pith.science/pith/YE2BS2SM6ZM2FOJPYMMDD4EIV4/action/replication_record"}},"created_at":"2026-07-05T11:11:11.287443+00:00","updated_at":"2026-07-05T11:11:11.287443+00:00"}