{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TEAANA2DKBT22OCI4E5FEYHH6J","short_pith_number":"pith:TEAANA2D","schema_version":"1.0","canonical_sha256":"99000683435067ad3848e13a5260e7f24fb3cb72db728e86a30520786203f5b6","source":{"kind":"arxiv","id":"2506.08887","version":1},"attestation_state":"computed","paper":{"title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guiguang Ding, Guoqiang Gong, Jungong Han, Leqi Shen, Pengzhang Liu, Sicheng Zhao, Tao He, Tianxiang Hao, Yifeng Zhang","submitted_at":"2025-06-10T15:16:40Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.08887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T15:16:40Z","cross_cats_sorted":[],"title_canon_sha256":"e37169af9175ce3e0ae7648806787909b544280e7617d0b804d1fe8e7bfea99e","abstract_canon_sha256":"29da41982a93aed470b7532abeaf10cd7f2f0a1a5a00560a96d4fe641b91124e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:14.727707Z","signature_b64":"85H6GGmuRQ/x08108zg3DGj1ezLwaGGu0W3fANQScDOMixrVJJQMrV4bNZNKEMs/v/Z8Z2mbk65l115nEun2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99000683435067ad3848e13a5260e7f24fb3cb72db728e86a30520786203f5b6","last_reissued_at":"2026-07-05T11:19:14.727188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:14.727188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guiguang Ding, Guoqiang Gong, Jungong Han, Leqi Shen, Pengzhang Liu, Sicheng Zhao, Tao He, Tianxiang Hao, Yifeng Zhang","submitted_at":"2025-06-10T15:16:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08887","kind":"arxiv","version":1},"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/2506.08887/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.08887","created_at":"2026-07-05T11:19:14.727242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08887v1","created_at":"2026-07-05T11:19:14.727242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08887","created_at":"2026-07-05T11:19:14.727242+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEAANA2DKBT2","created_at":"2026-07-05T11:19:14.727242+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEAANA2DKBT22OCI","created_at":"2026-07-05T11:19:14.727242+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEAANA2D","created_at":"2026-07-05T11:19:14.727242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J","json":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J.json","graph_json":"https://pith.science/api/pith-number/TEAANA2DKBT22OCI4E5FEYHH6J/graph.json","events_json":"https://pith.science/api/pith-number/TEAANA2DKBT22OCI4E5FEYHH6J/events.json","paper":"https://pith.science/paper/TEAANA2D"},"agent_actions":{"view_html":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J","download_json":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J.json","view_paper":"https://pith.science/paper/TEAANA2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08887&json=true","fetch_graph":"https://pith.science/api/pith-number/TEAANA2DKBT22OCI4E5FEYHH6J/graph.json","fetch_events":"https://pith.science/api/pith-number/TEAANA2DKBT22OCI4E5FEYHH6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J/action/storage_attestation","attest_author":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J/action/author_attestation","sign_citation":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J/action/citation_signature","submit_replication":"https://pith.science/pith/TEAANA2DKBT22OCI4E5FEYHH6J/action/replication_record"}},"created_at":"2026-07-05T11:19:14.727242+00:00","updated_at":"2026-07-05T11:19:14.727242+00:00"}