{"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"}