{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:F3SOW6EHJP7LPP7SNVGIQEMXRD","short_pith_number":"pith:F3SOW6EH","canonical_record":{"source":{"id":"2212.11790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-30T19:20:29Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d969f1b7fa49cc26c04a39b44bbaec059da8bca50b2d72fdefb52a5658c5d5d9","abstract_canon_sha256":"f6a91e879d931402f5351a4a76cde6dbf47f1494388788604d542ab0e5192b7f"},"schema_version":"1.0"},"canonical_sha256":"2ee4eb78874bfeb7bff26d4c88119788ee081ea26392fa12aa88ad03aeeb5d67","source":{"kind":"arxiv","id":"2212.11790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.11790","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"2212.11790v1","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11790","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"F3SOW6EHJP7L","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"F3SOW6EHJP7LPP7S","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"F3SOW6EH","created_at":"2026-07-05T05:27:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:F3SOW6EHJP7LPP7SNVGIQEMXRD","target":"record","payload":{"canonical_record":{"source":{"id":"2212.11790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-30T19:20:29Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"d969f1b7fa49cc26c04a39b44bbaec059da8bca50b2d72fdefb52a5658c5d5d9","abstract_canon_sha256":"f6a91e879d931402f5351a4a76cde6dbf47f1494388788604d542ab0e5192b7f"},"schema_version":"1.0"},"canonical_sha256":"2ee4eb78874bfeb7bff26d4c88119788ee081ea26392fa12aa88ad03aeeb5d67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:43.134546Z","signature_b64":"qJBICU3jHB4pFhjmFS0CZJL7z5yArkvSnLAvpF9puxUd8TyricvWy5+wjIT8sqWPX0WO+z/7hunzgHhPovdcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ee4eb78874bfeb7bff26d4c88119788ee081ea26392fa12aa88ad03aeeb5d67","last_reissued_at":"2026-07-05T05:27:43.134066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:43.134066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.11790","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:27:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obdzSZGkNr8eyWs6xuxLpkpW1RxeutCNH3zdnKkCJ0260VJXi4bg+QL81bCUpQicTaA3kCnHkue9jP54xsbNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:09:43.584342Z"},"content_sha256":"2b308cc5fb75781ffd68a51b585bde38b25f7529ad501ad304feaeb73083d24f","schema_version":"1.0","event_id":"sha256:2b308cc5fb75781ffd68a51b585bde38b25f7529ad501ad304feaeb73083d24f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:F3SOW6EHJP7LPP7SNVGIQEMXRD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Normalized Contrastive Learning for Text-Video Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bo Xiong, Florian Metze, Gourab Kundu, Kirmani Ahmed, Mahmoud Azab, Seungwhan Moon, Yookoon Park","submitted_at":"2022-11-30T19:20:29Z","abstract_excerpt":"Cross-modal contrastive learning has led the recent advances in multimodal retrieval with its simplicity and effectiveness. In this work, however, we reveal that cross-modal contrastive learning suffers from incorrect normalization of the sum retrieval probabilities of each text or video instance. Specifically, we show that many test instances are either over- or under-represented during retrieval, significantly hurting the retrieval performance. To address this problem, we propose Normalized Contrastive Learning (NCL) which utilizes the Sinkhorn-Knopp algorithm to compute the instance-wise bi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11790","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/2212.11790/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:27:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bgR8oIoWsJ7Q0jpT1BwcqifDX6pS9XIeqwuSgJlMhG6DkcB7NwnfZq3rdoQMEVpDJ++FrexdoDWI6iuBOG1sAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:09:43.585475Z"},"content_sha256":"343eac277be98d7f70ba9311a57fa13c94c339cf14921b72ebb7ee47078a3f5f","schema_version":"1.0","event_id":"sha256:343eac277be98d7f70ba9311a57fa13c94c339cf14921b72ebb7ee47078a3f5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3SOW6EHJP7LPP7SNVGIQEMXRD/bundle.json","state_url":"https://pith.science/pith/F3SOW6EHJP7LPP7SNVGIQEMXRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3SOW6EHJP7LPP7SNVGIQEMXRD/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":"2026-08-10T21:09:43Z","links":{"resolver":"https://pith.science/pith/F3SOW6EHJP7LPP7SNVGIQEMXRD","bundle":"https://pith.science/pith/F3SOW6EHJP7LPP7SNVGIQEMXRD/bundle.json","state":"https://pith.science/pith/F3SOW6EHJP7LPP7SNVGIQEMXRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3SOW6EHJP7LPP7SNVGIQEMXRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F3SOW6EHJP7LPP7SNVGIQEMXRD","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":"f6a91e879d931402f5351a4a76cde6dbf47f1494388788604d542ab0e5192b7f","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-30T19:20:29Z","title_canon_sha256":"d969f1b7fa49cc26c04a39b44bbaec059da8bca50b2d72fdefb52a5658c5d5d9"},"schema_version":"1.0","source":{"id":"2212.11790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.11790","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"2212.11790v1","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.11790","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"F3SOW6EHJP7L","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"F3SOW6EHJP7LPP7S","created_at":"2026-07-05T05:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"F3SOW6EH","created_at":"2026-07-05T05:27:43Z"}],"graph_snapshots":[{"event_id":"sha256:343eac277be98d7f70ba9311a57fa13c94c339cf14921b72ebb7ee47078a3f5f","target":"graph","created_at":"2026-07-05T05:27:43Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2212.11790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal contrastive learning has led the recent advances in multimodal retrieval with its simplicity and effectiveness. In this work, however, we reveal that cross-modal contrastive learning suffers from incorrect normalization of the sum retrieval probabilities of each text or video instance. Specifically, we show that many test instances are either over- or under-represented during retrieval, significantly hurting the retrieval performance. To address this problem, we propose Normalized Contrastive Learning (NCL) which utilizes the Sinkhorn-Knopp algorithm to compute the instance-wise bi","authors_text":"Bo Xiong, Florian Metze, Gourab Kundu, Kirmani Ahmed, Mahmoud Azab, Seungwhan Moon, Yookoon Park","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-30T19:20:29Z","title":"Normalized Contrastive Learning for Text-Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.11790","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2b308cc5fb75781ffd68a51b585bde38b25f7529ad501ad304feaeb73083d24f","target":"record","created_at":"2026-07-05T05:27:43Z","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":"f6a91e879d931402f5351a4a76cde6dbf47f1494388788604d542ab0e5192b7f","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-11-30T19:20:29Z","title_canon_sha256":"d969f1b7fa49cc26c04a39b44bbaec059da8bca50b2d72fdefb52a5658c5d5d9"},"schema_version":"1.0","source":{"id":"2212.11790","kind":"arxiv","version":1}},"canonical_sha256":"2ee4eb78874bfeb7bff26d4c88119788ee081ea26392fa12aa88ad03aeeb5d67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ee4eb78874bfeb7bff26d4c88119788ee081ea26392fa12aa88ad03aeeb5d67","first_computed_at":"2026-07-05T05:27:43.134066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:43.134066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qJBICU3jHB4pFhjmFS0CZJL7z5yArkvSnLAvpF9puxUd8TyricvWy5+wjIT8sqWPX0WO+z/7hunzgHhPovdcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:43.134546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.11790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b308cc5fb75781ffd68a51b585bde38b25f7529ad501ad304feaeb73083d24f","sha256:343eac277be98d7f70ba9311a57fa13c94c339cf14921b72ebb7ee47078a3f5f"],"state_sha256":"e494056db91a8232ba873d97d3102fd11e2c58271230aee6e407df270c94b038"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lHw1bxq6Y38VZVF9npxWENu2jKkDVKGd86jo0ckbi7O7Vvv3cbQyKuYdaiin4vYA/5tEskjZZZx4CvsbIG3zDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:09:43.593175Z","bundle_sha256":"db47f34699e6b28dc1597a1fbaac279554d8db587f7a6a5f3cc3cb57c3d72271"}}