{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DAQBVJJAA52X6UZXF2RUTLFIOQ","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":"be2d01577eec47b7ce6cae70dca5a808ce73237be03d0c8a7d84449b5acaba98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T12:45:44Z","title_canon_sha256":"9b049c70e89cf97bf03ed8602a16492958bd268d4c6c17a885a805803571774b"},"schema_version":"1.0","source":{"id":"2401.17797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17797","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17797v1","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17797","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_12","alias_value":"DAQBVJJAA52X","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_16","alias_value":"DAQBVJJAA52X6UZX","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_8","alias_value":"DAQBVJJA","created_at":"2026-07-05T07:39:42Z"}],"graph_snapshots":[{"event_id":"sha256:8b4f1629c02ab6e9e847fa18f2eb822697fb9697e8c8093dbc22b44c40cd625b","target":"graph","created_at":"2026-07-05T07:39:42Z","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/2401.17797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards effective and efficient zero-shot video-text retrieval, dubbed M2-RAAP. Upon popular image-text models like CLIP, most current adaptation-based video-text pre-training methods are confronted by three major issues, i.e., noisy data corpus, time-consuming pre-training, and limited performance gain. Towards this end, we conduct a comprehensive study including four critical steps in video-text pre-training. Specifically, we investigate 1) data filtering and refinement, 2) video input type selection, 3) temporal mod","authors_text":"Chunluan Zhou, Ming Yang, Qingpei Guo, Xingning Dong, Xuzheng Yu, Zipeng Feng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T12:45:44Z","title":"M2-RAAP: A Multi-Modal Recipe for Advancing Adaptation-based Pre-training towards Effective and Efficient Zero-shot Video-text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17797","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":"sha256:8cb221e03da035770563785ea9d777562d3dab541b6e81a59c5e50a1aee46ccd","target":"record","created_at":"2026-07-05T07:39:42Z","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":"be2d01577eec47b7ce6cae70dca5a808ce73237be03d0c8a7d84449b5acaba98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T12:45:44Z","title_canon_sha256":"9b049c70e89cf97bf03ed8602a16492958bd268d4c6c17a885a805803571774b"},"schema_version":"1.0","source":{"id":"2401.17797","kind":"arxiv","version":1}},"canonical_sha256":"18201aa52007757f53372ea349aca8740857f108b47ba9ec1e44030ec72bbcba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18201aa52007757f53372ea349aca8740857f108b47ba9ec1e44030ec72bbcba","first_computed_at":"2026-07-05T07:39:42.593891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:42.593891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"shcxPCqRQUslnlpZh5EC9uJSQ6RZHBOirqqaV/OZI4DJgdu7VQM2pXIHHBptFbGcBHMmTgZ/U4IGZ0OUV3KSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:42.594247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.17797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cb221e03da035770563785ea9d777562d3dab541b6e81a59c5e50a1aee46ccd","sha256:8b4f1629c02ab6e9e847fa18f2eb822697fb9697e8c8093dbc22b44c40cd625b"],"state_sha256":"e4d0440fd4f91105084198cd0d33e2193facdb9e28a42b06a999dd6bc6b6c30f"}