{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4KXYZZYOAL6CTQOAHW6BLN3YHB","short_pith_number":"pith:4KXYZZYO","canonical_record":{"source":{"id":"2605.02116","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T00:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"e31927de8b7349f6052390c6f4c1970324cac524aeb4393aaf41facb000fe3f1","abstract_canon_sha256":"9800b4b057f16bb7270417674de90b5c0c839a1d45f18e8ce12d401ee95a77fc"},"schema_version":"1.0"},"canonical_sha256":"e2af8ce70e02fc29c1c03dbc15b7783859a0af203aa9e0e93f02205a031e5777","source":{"kind":"arxiv","id":"2605.02116","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02116","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02116v2","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02116","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"4KXYZZYOAL6C","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"4KXYZZYOAL6CTQOA","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"4KXYZZYO","created_at":"2026-05-21T01:04:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4KXYZZYOAL6CTQOAHW6BLN3YHB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.02116","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T00:38:29Z","cross_cats_sorted":[],"title_canon_sha256":"e31927de8b7349f6052390c6f4c1970324cac524aeb4393aaf41facb000fe3f1","abstract_canon_sha256":"9800b4b057f16bb7270417674de90b5c0c839a1d45f18e8ce12d401ee95a77fc"},"schema_version":"1.0"},"canonical_sha256":"e2af8ce70e02fc29c1c03dbc15b7783859a0af203aa9e0e93f02205a031e5777","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:26.658208Z","signature_b64":"2YVuQFp+kkaZtl11C3sIXwG4aNHPt8Rtp9hl+AhiF4ocqdSdMEUuDTKAPP2rz3w4bVRIgO6qEARG/3HKthFTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2af8ce70e02fc29c1c03dbc15b7783859a0af203aa9e0e93f02205a031e5777","last_reissued_at":"2026-05-21T01:04:26.657450Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:26.657450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.02116","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ljpxcGHGFrrXKK6ATHW0rUw7HJ2bflUIkyOoRooHY3HlwJowc58XgXWyTg9AYNB3UIC9vm4Z1OtQ5jVVSMMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:46:32.417330Z"},"content_sha256":"1f01107d84a96006f1f06e1229b1077e792e210415146137c04e2aafebecf053","schema_version":"1.0","event_id":"sha256:1f01107d84a96006f1f06e1229b1077e792e210415146137c04e2aafebecf053"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4KXYZZYOAL6CTQOAHW6BLN3YHB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistical Consistency and Generalization of Contrastive Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Contrastive loss is statistically consistent with optimal ranking in retrieval tasks","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tianbao Yang, Xiyuan Wei, Yiming Ying, Yuanfan Li","submitted_at":"2026-05-04T00:38:29Z","abstract_excerpt":"Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood; (ii) available generalization bounds deteriorate as the number of negative samples increases, contradicting the empirical benefits of large negative sets; and (iii) the retrieval performance of CRL has received limited theoretical attention. In this paper, we develop a unified statistical learning theory for CRL. For downstream tasks, we evaluate retrieval "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that the contrastive loss is statistically consistent with optimal ranking and derive generalization bounds of order O(1/m + 1/sqrt(n)) and O(1/sqrt(m) + 1/sqrt(n)) for supervised and self-supervised CRL respectively.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The paper does not state the weakest assumption explicitly in the abstract; the bounds and consistency results are likely to rest on standard statistical-learning assumptions such as i.i.d. sampling, bounded loss functions, and appropriate regularity conditions on the data distribution that are not detailed here.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Contrastive representation learning is statistically consistent for optimal retrieval and admits generalization bounds of order O(1/m + 1/sqrt(n)) supervised and O(1/sqrt(m) + 1/sqrt(n)) self-supervised that benefit from large negative-sample counts m.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Contrastive loss is statistically consistent with optimal ranking in retrieval tasks","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5ba978c8ed98c321c22678001f012980c211e13824edf06855ec4830aefe9c32"},"source":{"id":"2605.02116","kind":"arxiv","version":2},"verdict":{"id":"0264c3e4-f5dc-4e19-b5d2-3e99d21d7892","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T16:52:33.174189Z","strongest_claim":"We show that the contrastive loss is statistically consistent with optimal ranking and derive generalization bounds of order O(1/m + 1/sqrt(n)) and O(1/sqrt(m) + 1/sqrt(n)) for supervised and self-supervised CRL respectively.","one_line_summary":"Contrastive representation learning is statistically consistent for optimal retrieval and admits generalization bounds of order O(1/m + 1/sqrt(n)) supervised and O(1/sqrt(m) + 1/sqrt(n)) self-supervised that benefit from large negative-sample counts m.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The paper does not state the weakest assumption explicitly in the abstract; the bounds and consistency results are likely to rest on standard statistical-learning assumptions such as i.i.d. sampling, bounded loss functions, and appropriate regularity conditions on the data distribution that are not detailed here.","pith_extraction_headline":"Contrastive loss is statistically consistent with optimal ranking in retrieval tasks"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02116/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T16:37:40.598294Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T04:01:22.646763Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:39:39.227981Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7e055980203754714e3434be3efad1e3797fd7a368fa4093da582dcb5f288c56"},"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"},"verdict_id":"0264c3e4-f5dc-4e19-b5d2-3e99d21d7892"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQeaJDNN0q7cu42gyv10QqISHbm6jqrlRfC+JJGKSnCk5csSo2/BqM4aH7h+IXPYZk22J01RJ58bAnJdJb1sDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:46:32.418344Z"},"content_sha256":"965f0567907b1d019f53c0dc52acc1f55d0940a6bb7b13f79ac6a1f2301b5c64","schema_version":"1.0","event_id":"sha256:965f0567907b1d019f53c0dc52acc1f55d0940a6bb7b13f79ac6a1f2301b5c64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KXYZZYOAL6CTQOAHW6BLN3YHB/bundle.json","state_url":"https://pith.science/pith/4KXYZZYOAL6CTQOAHW6BLN3YHB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KXYZZYOAL6CTQOAHW6BLN3YHB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-29T20:46:32Z","links":{"resolver":"https://pith.science/pith/4KXYZZYOAL6CTQOAHW6BLN3YHB","bundle":"https://pith.science/pith/4KXYZZYOAL6CTQOAHW6BLN3YHB/bundle.json","state":"https://pith.science/pith/4KXYZZYOAL6CTQOAHW6BLN3YHB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KXYZZYOAL6CTQOAHW6BLN3YHB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4KXYZZYOAL6CTQOAHW6BLN3YHB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9800b4b057f16bb7270417674de90b5c0c839a1d45f18e8ce12d401ee95a77fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T00:38:29Z","title_canon_sha256":"e31927de8b7349f6052390c6f4c1970324cac524aeb4393aaf41facb000fe3f1"},"schema_version":"1.0","source":{"id":"2605.02116","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.02116","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.02116v2","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02116","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_12","alias_value":"4KXYZZYOAL6C","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_16","alias_value":"4KXYZZYOAL6CTQOA","created_at":"2026-05-21T01:04:26Z"},{"alias_kind":"pith_short_8","alias_value":"4KXYZZYO","created_at":"2026-05-21T01:04:26Z"}],"graph_snapshots":[{"event_id":"sha256:965f0567907b1d019f53c0dc52acc1f55d0940a6bb7b13f79ac6a1f2301b5c64","target":"graph","created_at":"2026-05-21T01:04:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We show that the contrastive loss is statistically consistent with optimal ranking and derive generalization bounds of order O(1/m + 1/sqrt(n)) and O(1/sqrt(m) + 1/sqrt(n)) for supervised and self-supervised CRL respectively."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The paper does not state the weakest assumption explicitly in the abstract; the bounds and consistency results are likely to rest on standard statistical-learning assumptions such as i.i.d. sampling, bounded loss functions, and appropriate regularity conditions on the data distribution that are not detailed here."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Contrastive representation learning is statistically consistent for optimal retrieval and admits generalization bounds of order O(1/m + 1/sqrt(n)) supervised and O(1/sqrt(m) + 1/sqrt(n)) self-supervised that benefit from large negative-sample counts m."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Contrastive loss is statistically consistent with optimal ranking in retrieval tasks"}],"snapshot_sha256":"5ba978c8ed98c321c22678001f012980c211e13824edf06855ec4830aefe9c32"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T16:37:40.598294Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T04:01:22.646763Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:39:39.227981Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.02116/integrity.json","findings":[],"snapshot_sha256":"7e055980203754714e3434be3efad1e3797fd7a368fa4093da582dcb5f288c56","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive representation learning (CRL) underpins many modern foundation models. Despite recent theoretical progress, existing analyses suffer from several key limitations: (i) the statistical consistency of CRL remains poorly understood; (ii) available generalization bounds deteriorate as the number of negative samples increases, contradicting the empirical benefits of large negative sets; and (iii) the retrieval performance of CRL has received limited theoretical attention. In this paper, we develop a unified statistical learning theory for CRL. For downstream tasks, we evaluate retrieval ","authors_text":"Tianbao Yang, Xiyuan Wei, Yiming Ying, Yuanfan Li","cross_cats":[],"headline":"Contrastive loss is statistically consistent with optimal ranking in retrieval tasks","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T00:38:29Z","title":"Statistical Consistency and Generalization of Contrastive Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.02116","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T16:52:33.174189Z","id":"0264c3e4-f5dc-4e19-b5d2-3e99d21d7892","model_set":{"reader":"grok-4.3"},"one_line_summary":"Contrastive representation learning is statistically consistent for optimal retrieval and admits generalization bounds of order O(1/m + 1/sqrt(n)) supervised and O(1/sqrt(m) + 1/sqrt(n)) self-supervised that benefit from large negative-sample counts m.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Contrastive loss is statistically consistent with optimal ranking in retrieval tasks","strongest_claim":"We show that the contrastive loss is statistically consistent with optimal ranking and derive generalization bounds of order O(1/m + 1/sqrt(n)) and O(1/sqrt(m) + 1/sqrt(n)) for supervised and self-supervised CRL respectively.","weakest_assumption":"The paper does not state the weakest assumption explicitly in the abstract; the bounds and consistency results are likely to rest on standard statistical-learning assumptions such as i.i.d. sampling, bounded loss functions, and appropriate regularity conditions on the data distribution that are not detailed here."}},"verdict_id":"0264c3e4-f5dc-4e19-b5d2-3e99d21d7892"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1f01107d84a96006f1f06e1229b1077e792e210415146137c04e2aafebecf053","target":"record","created_at":"2026-05-21T01:04:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9800b4b057f16bb7270417674de90b5c0c839a1d45f18e8ce12d401ee95a77fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T00:38:29Z","title_canon_sha256":"e31927de8b7349f6052390c6f4c1970324cac524aeb4393aaf41facb000fe3f1"},"schema_version":"1.0","source":{"id":"2605.02116","kind":"arxiv","version":2}},"canonical_sha256":"e2af8ce70e02fc29c1c03dbc15b7783859a0af203aa9e0e93f02205a031e5777","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2af8ce70e02fc29c1c03dbc15b7783859a0af203aa9e0e93f02205a031e5777","first_computed_at":"2026-05-21T01:04:26.657450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:26.657450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2YVuQFp+kkaZtl11C3sIXwG4aNHPt8Rtp9hl+AhiF4ocqdSdMEUuDTKAPP2rz3w4bVRIgO6qEARG/3HKthFTCQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:26.658208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.02116","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f01107d84a96006f1f06e1229b1077e792e210415146137c04e2aafebecf053","sha256:965f0567907b1d019f53c0dc52acc1f55d0940a6bb7b13f79ac6a1f2301b5c64"],"state_sha256":"471c1a4961a6e0b3c27488741d9963627165302f34abdce1c6d4e39a90990689"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gH4siKKBGL3prXE/yqADwD4uL9sdwim25xV3XQYd3Hd8kq9hLKpqCR2OXyBp1X7U94gOJhc8SkW45tNVwn9nCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T20:46:32.424440Z","bundle_sha256":"6ce23678c6deaec5137a487e3f57af798be186188d22e4160f08cbca291181a4"}}