{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NLXDZ2HYYPDJB75YWQQPTWBZGW","short_pith_number":"pith:NLXDZ2HY","canonical_record":{"source":{"id":"2104.08860","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-18T13:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"5d81713df70f57d44c30e68db74c43ce9bb54ceed0716ae54102e9f7c21051ac","abstract_canon_sha256":"2d2a046108fe4a90cab6ede7a26d5e5c0e7afd99e94ac16932d9efa2cdd8f4ce"},"schema_version":"1.0"},"canonical_sha256":"6aee3ce8f8c3c690ffb8b420f9d839359b9154f1b3bf91a88a4f9b8ed14b585c","source":{"kind":"arxiv","id":"2104.08860","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08860","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08860v2","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08860","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"NLXDZ2HYYPDJ","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"NLXDZ2HYYPDJB75Y","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"NLXDZ2HY","created_at":"2026-07-05T02:38:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NLXDZ2HYYPDJB75YWQQPTWBZGW","target":"record","payload":{"canonical_record":{"source":{"id":"2104.08860","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-18T13:59:50Z","cross_cats_sorted":[],"title_canon_sha256":"5d81713df70f57d44c30e68db74c43ce9bb54ceed0716ae54102e9f7c21051ac","abstract_canon_sha256":"2d2a046108fe4a90cab6ede7a26d5e5c0e7afd99e94ac16932d9efa2cdd8f4ce"},"schema_version":"1.0"},"canonical_sha256":"6aee3ce8f8c3c690ffb8b420f9d839359b9154f1b3bf91a88a4f9b8ed14b585c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:34.205785Z","signature_b64":"X7NC+3ot3cGrkYO3kRXcguYmC3U/yHbMXQaPlfRmG6PkEbMffgoTWprV7/B6nJN0vEt1oyjl2TStMldPbE2WBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aee3ce8f8c3c690ffb8b420f9d839359b9154f1b3bf91a88a4f9b8ed14b585c","last_reissued_at":"2026-07-05T02:38:34.205265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:34.205265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.08860","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":"2026-07-05T02:38:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N0ZHLiQpvfpLP6Xcqw6SgFs6FfqvlRGD93JlcljKYXvEANXMwizLXE10NjYfNEyDnIxZIlGys/uzASysE1A5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T12:06:25.325610Z"},"content_sha256":"79a205095d71ad711ca99e2e43baf1e7858585c986fb779474ff5b401d5aad7e","schema_version":"1.0","event_id":"sha256:79a205095d71ad711ca99e2e43baf1e7858585c986fb779474ff5b401d5aad7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NLXDZ2HYYPDJB75YWQQPTWBZGW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaishao Luo, Lei Ji, Ming Zhong, Nan Duan, Tianrui Li, Wen Lei, Yang Chen","submitted_at":"2021-04-18T13:59:50Z","abstract_excerpt":"Video-text retrieval plays an essential role in multi-modal research and has been widely used in many real-world web applications. The CLIP (Contrastive Language-Image Pre-training), an image-language pre-training model, has demonstrated the power of visual concepts learning from web collected image-text datasets. In this paper, we propose a CLIP4Clip model to transfer the knowledge of the CLIP model to video-language retrieval in an end-to-end manner. Several questions are investigated via empirical studies: 1) Whether image feature is enough for video-text retrieval? 2) How a post-pretrainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08860","kind":"arxiv","version":2},"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/2104.08860/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":"2026-07-05T02:38:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yDnEx0DBKibyF/75Lb+rleNe+uurxzddR30D6Go/4orwZ5CenGkTQgLgxkBYwIZLfr1VagLMi4YVo1JN5H8CCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T12:06:25.326026Z"},"content_sha256":"e6236fb01de8088da575fab42eac01157ead3c1a549fc23d75f798ccffb31d7f","schema_version":"1.0","event_id":"sha256:e6236fb01de8088da575fab42eac01157ead3c1a549fc23d75f798ccffb31d7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLXDZ2HYYPDJB75YWQQPTWBZGW/bundle.json","state_url":"https://pith.science/pith/NLXDZ2HYYPDJB75YWQQPTWBZGW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLXDZ2HYYPDJB75YWQQPTWBZGW/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":"2026-07-13T12:06:25Z","links":{"resolver":"https://pith.science/pith/NLXDZ2HYYPDJB75YWQQPTWBZGW","bundle":"https://pith.science/pith/NLXDZ2HYYPDJB75YWQQPTWBZGW/bundle.json","state":"https://pith.science/pith/NLXDZ2HYYPDJB75YWQQPTWBZGW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLXDZ2HYYPDJB75YWQQPTWBZGW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NLXDZ2HYYPDJB75YWQQPTWBZGW","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":"2d2a046108fe4a90cab6ede7a26d5e5c0e7afd99e94ac16932d9efa2cdd8f4ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-18T13:59:50Z","title_canon_sha256":"5d81713df70f57d44c30e68db74c43ce9bb54ceed0716ae54102e9f7c21051ac"},"schema_version":"1.0","source":{"id":"2104.08860","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08860","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08860v2","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08860","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"NLXDZ2HYYPDJ","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"NLXDZ2HYYPDJB75Y","created_at":"2026-07-05T02:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"NLXDZ2HY","created_at":"2026-07-05T02:38:34Z"}],"graph_snapshots":[{"event_id":"sha256:e6236fb01de8088da575fab42eac01157ead3c1a549fc23d75f798ccffb31d7f","target":"graph","created_at":"2026-07-05T02:38:34Z","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/2104.08860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-text retrieval plays an essential role in multi-modal research and has been widely used in many real-world web applications. The CLIP (Contrastive Language-Image Pre-training), an image-language pre-training model, has demonstrated the power of visual concepts learning from web collected image-text datasets. In this paper, we propose a CLIP4Clip model to transfer the knowledge of the CLIP model to video-language retrieval in an end-to-end manner. Several questions are investigated via empirical studies: 1) Whether image feature is enough for video-text retrieval? 2) How a post-pretrainin","authors_text":"Huaishao Luo, Lei Ji, Ming Zhong, Nan Duan, Tianrui Li, Wen Lei, Yang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-18T13:59:50Z","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08860","kind":"arxiv","version":2},"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":"sha256:79a205095d71ad711ca99e2e43baf1e7858585c986fb779474ff5b401d5aad7e","target":"record","created_at":"2026-07-05T02:38:34Z","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":"2d2a046108fe4a90cab6ede7a26d5e5c0e7afd99e94ac16932d9efa2cdd8f4ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-18T13:59:50Z","title_canon_sha256":"5d81713df70f57d44c30e68db74c43ce9bb54ceed0716ae54102e9f7c21051ac"},"schema_version":"1.0","source":{"id":"2104.08860","kind":"arxiv","version":2}},"canonical_sha256":"6aee3ce8f8c3c690ffb8b420f9d839359b9154f1b3bf91a88a4f9b8ed14b585c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6aee3ce8f8c3c690ffb8b420f9d839359b9154f1b3bf91a88a4f9b8ed14b585c","first_computed_at":"2026-07-05T02:38:34.205265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:34.205265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X7NC+3ot3cGrkYO3kRXcguYmC3U/yHbMXQaPlfRmG6PkEbMffgoTWprV7/B6nJN0vEt1oyjl2TStMldPbE2WBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:34.205785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08860","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79a205095d71ad711ca99e2e43baf1e7858585c986fb779474ff5b401d5aad7e","sha256:e6236fb01de8088da575fab42eac01157ead3c1a549fc23d75f798ccffb31d7f"],"state_sha256":"41a9800ebb7531000e76b4a244b47b4efcfacc8f212f3b971663b25d0ab0d4e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QEww1/T/KCH0NQlpoDBSgDLg6xopCNVLMAmf0OuI6kC8BsEsI4mMnzsF1LF8pxPTtlZLgvX1g3poxtK0TI5DAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T12:06:25.328201Z","bundle_sha256":"d70905b4656f28fdf2ece47c8c9c891569266fcc138a8d48d726ec53408bf79e"}}