{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TEAANA2DKBT22OCI4E5FEYHH6J","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":"29da41982a93aed470b7532abeaf10cd7f2f0a1a5a00560a96d4fe641b91124e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T15:16:40Z","title_canon_sha256":"e37169af9175ce3e0ae7648806787909b544280e7617d0b804d1fe8e7bfea99e"},"schema_version":"1.0","source":{"id":"2506.08887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08887","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08887v1","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08887","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_12","alias_value":"TEAANA2DKBT2","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_16","alias_value":"TEAANA2DKBT22OCI","created_at":"2026-07-05T11:19:14Z"},{"alias_kind":"pith_short_8","alias_value":"TEAANA2D","created_at":"2026-07-05T11:19:14Z"}],"graph_snapshots":[{"event_id":"sha256:298452ddffefc7e608b231605e0551e9c243e05b6d5bec312a53489e1325e7bc","target":"graph","created_at":"2026-07-05T11:19:14Z","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/2506.08887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The parameter-efficient adaptation of the image-text pretraining model CLIP for video-text retrieval is a prominent area of research. While CLIP is focused on image-level vision-language matching, video-text retrieval demands comprehensive understanding at the video level. Three key discrepancies emerge in the transfer from image-level to video-level: vision, language, and alignment. However, existing methods mainly focus on vision while neglecting language and alignment. In this paper, we propose Discrepancy Reduction in Vision, Language, and Alignment (DiscoVLA), which simultaneously mitigat","authors_text":"Guiguang Ding, Guoqiang Gong, Jungong Han, Leqi Shen, Pengzhang Liu, Sicheng Zhao, Tao He, Tianxiang Hao, Yifeng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T15:16:40Z","title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08887","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":"sha256:91d3fe28cb5bcd400ddf708822fcb57e509c912c6154f1f4fbee274a86218f7a","target":"record","created_at":"2026-07-05T11:19:14Z","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":"29da41982a93aed470b7532abeaf10cd7f2f0a1a5a00560a96d4fe641b91124e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T15:16:40Z","title_canon_sha256":"e37169af9175ce3e0ae7648806787909b544280e7617d0b804d1fe8e7bfea99e"},"schema_version":"1.0","source":{"id":"2506.08887","kind":"arxiv","version":1}},"canonical_sha256":"99000683435067ad3848e13a5260e7f24fb3cb72db728e86a30520786203f5b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99000683435067ad3848e13a5260e7f24fb3cb72db728e86a30520786203f5b6","first_computed_at":"2026-07-05T11:19:14.727188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:14.727188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"85H6GGmuRQ/x08108zg3DGj1ezLwaGGu0W3fANQScDOMixrVJJQMrV4bNZNKEMs/v/Z8Z2mbk65l115nEun2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:14.727707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91d3fe28cb5bcd400ddf708822fcb57e509c912c6154f1f4fbee274a86218f7a","sha256:298452ddffefc7e608b231605e0551e9c243e05b6d5bec312a53489e1325e7bc"],"state_sha256":"be7c7087bd6cd8bfdcff8dafb4debe403bb5e48d4252e97e0397486684647f22"}