{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:K3QLGRWC75CYAIXEDAYAE7CDKB","short_pith_number":"pith:K3QLGRWC","canonical_record":{"source":{"id":"2209.06430","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T05:47:02Z","cross_cats_sorted":[],"title_canon_sha256":"928664b4d66dca04730b0e3d42ef229772f5ef68d9808105184efbf830311846","abstract_canon_sha256":"afeeb423b79716bf6f62f1605369b8a243f897d1b39e979bc82eae875c886e50"},"schema_version":"1.0"},"canonical_sha256":"56e0b346c2ff458022e41830027c435061668e3fafab88a07f6da7b79ec64353","source":{"kind":"arxiv","id":"2209.06430","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06430","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06430v4","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06430","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"pith_short_12","alias_value":"K3QLGRWC75CY","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"pith_short_16","alias_value":"K3QLGRWC75CYAIXE","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"pith_short_8","alias_value":"K3QLGRWC","created_at":"2026-07-05T05:47:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:K3QLGRWC75CYAIXEDAYAE7CDKB","target":"record","payload":{"canonical_record":{"source":{"id":"2209.06430","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T05:47:02Z","cross_cats_sorted":[],"title_canon_sha256":"928664b4d66dca04730b0e3d42ef229772f5ef68d9808105184efbf830311846","abstract_canon_sha256":"afeeb423b79716bf6f62f1605369b8a243f897d1b39e979bc82eae875c886e50"},"schema_version":"1.0"},"canonical_sha256":"56e0b346c2ff458022e41830027c435061668e3fafab88a07f6da7b79ec64353","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:17.452570Z","signature_b64":"XJ1/4jMdseNTfWO0XoM41ASv6yP9hjUqWpKvRXwhSnDZFEb+prauYmvCP31joLf0GQ9feTPtNyxIClG1hYYrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56e0b346c2ff458022e41830027c435061668e3fafab88a07f6da7b79ec64353","last_reissued_at":"2026-07-05T05:47:17.452105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:17.452105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.06430","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:47:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHvgMkzeo8JqDC9DOdlN7VGeKrWdX3GYcW/Oexeyh7K49+W1BefliavhNZxNrbI1KNeQ8Tmz6C+Fbu2aefxkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:35:59.620828Z"},"content_sha256":"be1e7b89d06ed0baf77a36388ff36928a9254eaea6b986376f14063eaa11ea41","schema_version":"1.0","event_id":"sha256:be1e7b89d06ed0baf77a36388ff36928a9254eaea6b986376f14063eaa11ea41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:K3QLGRWC75CYAIXEDAYAE7CDKB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Liu, Hongwei Xue, Houqiang Li, Jianlong Fu, Jiebo Luo, Ruihua Song, Yuchong Sun","submitted_at":"2022-09-14T05:47:02Z","abstract_excerpt":"The pre-trained image-text models, like CLIP, have demonstrated the strong power of vision-language representation learned from a large scale of web-collected image-text data. In light of the well-learned visual features, some existing works transfer image representation to video domain and achieve good results. However, how to utilize image-language pre-trained model (e.g., CLIP) for video-language pre-training (post-pretraining) is still under explored. In this paper, we investigate two questions: 1) what are the factors hindering post-pretraining CLIP to further improve the performance on v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06430","kind":"arxiv","version":4},"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/2209.06430/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":"2026-07-05T05:47:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k51rh5VJfCK16ZETtFgyS43SpZKyepR2K9iK7z4xYlPJb4RneS0EDCV68jetGolfIWJ0AnV4AxzTAooVq8Q4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:35:59.621449Z"},"content_sha256":"65be9b92a8d4648ba2366a867fd7ebf223b8c78c34c18978cc7f9cb83a282a84","schema_version":"1.0","event_id":"sha256:65be9b92a8d4648ba2366a867fd7ebf223b8c78c34c18978cc7f9cb83a282a84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/bundle.json","state_url":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/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":"2026-08-04T06:35:59Z","links":{"resolver":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB","bundle":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/bundle.json","state":"https://pith.science/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K3QLGRWC75CYAIXEDAYAE7CDKB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:K3QLGRWC75CYAIXEDAYAE7CDKB","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":"afeeb423b79716bf6f62f1605369b8a243f897d1b39e979bc82eae875c886e50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T05:47:02Z","title_canon_sha256":"928664b4d66dca04730b0e3d42ef229772f5ef68d9808105184efbf830311846"},"schema_version":"1.0","source":{"id":"2209.06430","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06430","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06430v4","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06430","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"pith_short_12","alias_value":"K3QLGRWC75CY","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"pith_short_16","alias_value":"K3QLGRWC75CYAIXE","created_at":"2026-07-05T05:47:17Z"},{"alias_kind":"pith_short_8","alias_value":"K3QLGRWC","created_at":"2026-07-05T05:47:17Z"}],"graph_snapshots":[{"event_id":"sha256:65be9b92a8d4648ba2366a867fd7ebf223b8c78c34c18978cc7f9cb83a282a84","target":"graph","created_at":"2026-07-05T05:47:17Z","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/2209.06430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pre-trained image-text models, like CLIP, have demonstrated the strong power of vision-language representation learned from a large scale of web-collected image-text data. In light of the well-learned visual features, some existing works transfer image representation to video domain and achieve good results. However, how to utilize image-language pre-trained model (e.g., CLIP) for video-language pre-training (post-pretraining) is still under explored. In this paper, we investigate two questions: 1) what are the factors hindering post-pretraining CLIP to further improve the performance on v","authors_text":"Bei Liu, Hongwei Xue, Houqiang Li, Jianlong Fu, Jiebo Luo, Ruihua Song, Yuchong Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T05:47:02Z","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06430","kind":"arxiv","version":4},"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:be1e7b89d06ed0baf77a36388ff36928a9254eaea6b986376f14063eaa11ea41","target":"record","created_at":"2026-07-05T05:47:17Z","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":"afeeb423b79716bf6f62f1605369b8a243f897d1b39e979bc82eae875c886e50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-14T05:47:02Z","title_canon_sha256":"928664b4d66dca04730b0e3d42ef229772f5ef68d9808105184efbf830311846"},"schema_version":"1.0","source":{"id":"2209.06430","kind":"arxiv","version":4}},"canonical_sha256":"56e0b346c2ff458022e41830027c435061668e3fafab88a07f6da7b79ec64353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56e0b346c2ff458022e41830027c435061668e3fafab88a07f6da7b79ec64353","first_computed_at":"2026-07-05T05:47:17.452105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:17.452105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJ1/4jMdseNTfWO0XoM41ASv6yP9hjUqWpKvRXwhSnDZFEb+prauYmvCP31joLf0GQ9feTPtNyxIClG1hYYrDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:17.452570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.06430","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be1e7b89d06ed0baf77a36388ff36928a9254eaea6b986376f14063eaa11ea41","sha256:65be9b92a8d4648ba2366a867fd7ebf223b8c78c34c18978cc7f9cb83a282a84"],"state_sha256":"1e9348e0b98c10f16c7daf33a439efc06d8c4f83adac65661def6e66c8105f38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fHoMmCcoKk/Lwt9SHTxLfpv6we/DIDou8JhFu/RN/39LwlpLEU1ypHj+ZmTFnkHveB9cyqAipSy9q95LIgJjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:35:59.627080Z","bundle_sha256":"cd491ad471db72da387b636ee64076fabf37c30f23773dc5d7de608f7feefb4e"}}