{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:F5JIEQ5E74ZGB7KHCF3276ODFW","short_pith_number":"pith:F5JIEQ5E","canonical_record":{"source":{"id":"2210.05039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-10T22:48:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"441de28fd59225a33508fa40df2c1d141d0c541f3593db56f4ebef98e4c1034c","abstract_canon_sha256":"5d3952aae02a2ac9f3f2f9de7bc98a50802e2e8b34f9af6a80f020b345f28e20"},"schema_version":"1.0"},"canonical_sha256":"2f528243a4ff3260fd471177aff9c32da5d67b34f1fd3bd8a9020f2dc23ea468","source":{"kind":"arxiv","id":"2210.05039","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05039","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05039v1","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05039","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"F5JIEQ5E74ZG","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"F5JIEQ5E74ZGB7KH","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"F5JIEQ5E","created_at":"2026-07-05T05:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:F5JIEQ5E74ZGB7KHCF3276ODFW","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05039","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-10T22:48:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"441de28fd59225a33508fa40df2c1d141d0c541f3593db56f4ebef98e4c1034c","abstract_canon_sha256":"5d3952aae02a2ac9f3f2f9de7bc98a50802e2e8b34f9af6a80f020b345f28e20"},"schema_version":"1.0"},"canonical_sha256":"2f528243a4ff3260fd471177aff9c32da5d67b34f1fd3bd8a9020f2dc23ea468","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:12.128047Z","signature_b64":"tLIsOhNqpAdOs5ugq3TM4YMGvvyQvBRpBgD4ixJRSboUkSQDQ72tm4eMvisIfmEpGwIjF/JgaepagSjoHDSQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f528243a4ff3260fd471177aff9c32da5d67b34f1fd3bd8a9020f2dc23ea468","last_reissued_at":"2026-07-05T05:05:12.127628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:12.127628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05039","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":"2026-07-05T05:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5DtRrGNsQmARBeL+P9CRd3qoorHCjXzCC4LUc6phE/Wze74eAHdeOxZ1O8F8rOm8pjk7FSrtcIMZGsxfyK7YAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:25:07.911379Z"},"content_sha256":"51b1471dbc3765cd2d1c83bf605e4e012873f03aeb87431d4d6d8024074b96cc","schema_version":"1.0","event_id":"sha256:51b1471dbc3765cd2d1c83bf605e4e012873f03aeb87431d4d6d8024074b96cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:F5JIEQ5E74ZGB7KHCF3276ODFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Video-Language Learning with Fine-grained Frame Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Lin Ma, Lucia Specia, Yishu Miao, Yujie Zhong, Zixu Wang","submitted_at":"2022-10-10T22:48:08Z","abstract_excerpt":"Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level loss to predict whether a pair of video and text is aligned. However, even in paired video-text segments, only a subset of the frames are semantically relevant to the corresponding text, with the remainder representing noise; where the ratio of noisy frames is higher for longer videos. We propose FineCo (Fine-grained Contrastive Loss for Frame Sampling), an approach to better l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05039","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/2210.05039/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":"2026-07-05T05:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fp3BDK/ytJRgFOSljnyuVs2veVMsc6oxk6Xkckpz6NBf95fPGonw+J08iqU6XEl7y1W5LwD/5RLIJtMe5a6/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:25:07.912366Z"},"content_sha256":"e24b1dc1ec5e0c64586bc57fb9d694b444b7835c6ed70c37601e3b63684d9954","schema_version":"1.0","event_id":"sha256:e24b1dc1ec5e0c64586bc57fb9d694b444b7835c6ed70c37601e3b63684d9954"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5JIEQ5E74ZGB7KHCF3276ODFW/bundle.json","state_url":"https://pith.science/pith/F5JIEQ5E74ZGB7KHCF3276ODFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5JIEQ5E74ZGB7KHCF3276ODFW/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":"2026-08-18T16:25:07Z","links":{"resolver":"https://pith.science/pith/F5JIEQ5E74ZGB7KHCF3276ODFW","bundle":"https://pith.science/pith/F5JIEQ5E74ZGB7KHCF3276ODFW/bundle.json","state":"https://pith.science/pith/F5JIEQ5E74ZGB7KHCF3276ODFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5JIEQ5E74ZGB7KHCF3276ODFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F5JIEQ5E74ZGB7KHCF3276ODFW","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":"5d3952aae02a2ac9f3f2f9de7bc98a50802e2e8b34f9af6a80f020b345f28e20","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-10T22:48:08Z","title_canon_sha256":"441de28fd59225a33508fa40df2c1d141d0c541f3593db56f4ebef98e4c1034c"},"schema_version":"1.0","source":{"id":"2210.05039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05039","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05039v1","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05039","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"F5JIEQ5E74ZG","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"F5JIEQ5E74ZGB7KH","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"F5JIEQ5E","created_at":"2026-07-05T05:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:e24b1dc1ec5e0c64586bc57fb9d694b444b7835c6ed70c37601e3b63684d9954","target":"graph","created_at":"2026-07-05T05:05:12Z","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/2210.05039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent progress in video and language representation learning, the weak or sparse correspondence between the two modalities remains a bottleneck in the area. Most video-language models are trained via pair-level loss to predict whether a pair of video and text is aligned. However, even in paired video-text segments, only a subset of the frames are semantically relevant to the corresponding text, with the remainder representing noise; where the ratio of noisy frames is higher for longer videos. We propose FineCo (Fine-grained Contrastive Loss for Frame Sampling), an approach to better l","authors_text":"Lin Ma, Lucia Specia, Yishu Miao, Yujie Zhong, Zixu Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-10T22:48:08Z","title":"Contrastive Video-Language Learning with Fine-grained Frame Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05039","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":"sha256:51b1471dbc3765cd2d1c83bf605e4e012873f03aeb87431d4d6d8024074b96cc","target":"record","created_at":"2026-07-05T05:05:12Z","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":"5d3952aae02a2ac9f3f2f9de7bc98a50802e2e8b34f9af6a80f020b345f28e20","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-10T22:48:08Z","title_canon_sha256":"441de28fd59225a33508fa40df2c1d141d0c541f3593db56f4ebef98e4c1034c"},"schema_version":"1.0","source":{"id":"2210.05039","kind":"arxiv","version":1}},"canonical_sha256":"2f528243a4ff3260fd471177aff9c32da5d67b34f1fd3bd8a9020f2dc23ea468","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f528243a4ff3260fd471177aff9c32da5d67b34f1fd3bd8a9020f2dc23ea468","first_computed_at":"2026-07-05T05:05:12.127628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:12.127628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tLIsOhNqpAdOs5ugq3TM4YMGvvyQvBRpBgD4ixJRSboUkSQDQ72tm4eMvisIfmEpGwIjF/JgaepagSjoHDSQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:12.128047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51b1471dbc3765cd2d1c83bf605e4e012873f03aeb87431d4d6d8024074b96cc","sha256:e24b1dc1ec5e0c64586bc57fb9d694b444b7835c6ed70c37601e3b63684d9954"],"state_sha256":"9455a82ce4f8be833d326f7c7c06077241c85d093d375bb9337889d3d0d26d3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4RMWRhn8HDEa7YIs8qtazl2/z/BiQoWGQWTfD+WvPrWLKtbEDjXWUm8NGCbA70Bad7+YHJjeQn1J7+maY6lCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:25:07.919484Z","bundle_sha256":"123ef3b10d1b9f92c3744e3edc15ea7bc653ba5bf3ebeda31d8da115c4cc4121"}}