{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2BYWDPHL6V32GQHR6EZQC4IMIT","short_pith_number":"pith:2BYWDPHL","schema_version":"1.0","canonical_sha256":"d07161bcebf577a340f1f13301710c44fb5032e535d2795b5d62b466393d7814","source":{"kind":"arxiv","id":"2508.14812","version":1},"attestation_state":"computed","paper":{"title":"Repeating Words for Video-Language Retrieval with Coarse-to-Fine Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Haoyu Zhao, Jiaxi Gu, Shicong Wang, Xing Zhang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2025-08-20T16:03:56Z","abstract_excerpt":"The explosive growth of video streaming presents challenges in achieving high accuracy and low training costs for video-language retrieval. However, existing methods rely on large-scale pre-training to improve video retrieval performance, resulting in significant computational demands. Additionally, the fine-grained information in videos and texts remains underexplored. To alleviate these problems, we propose a novel framework to learn fine-grained features for better alignment and introduce an inference pipeline to improve performance without additional training. Specifically, we employ coars"},"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":"2508.14812","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-20T16:03:56Z","cross_cats_sorted":[],"title_canon_sha256":"21e3b1d99a8170bd6a70726dad9d19e016c514684095ff1637c313862ea175a8","abstract_canon_sha256":"792d577044ab29ea15b456271a6629a8daa2e4a2b2df3b79fb88bcc1dee0c9b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:44.916691Z","signature_b64":"+NUB2Ve5S81djxyxDPDwWGjG1vrwV+ru89Kzic+L2d3+r6de746unJaRfp3+Mn2YNa3U7twwI9Eufe6gfq7LCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d07161bcebf577a340f1f13301710c44fb5032e535d2795b5d62b466393d7814","last_reissued_at":"2026-07-05T11:56:44.916057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:44.916057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repeating Words for Video-Language Retrieval with Coarse-to-Fine Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Haoyu Zhao, Jiaxi Gu, Shicong Wang, Xing Zhang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2025-08-20T16:03:56Z","abstract_excerpt":"The explosive growth of video streaming presents challenges in achieving high accuracy and low training costs for video-language retrieval. However, existing methods rely on large-scale pre-training to improve video retrieval performance, resulting in significant computational demands. Additionally, the fine-grained information in videos and texts remains underexplored. To alleviate these problems, we propose a novel framework to learn fine-grained features for better alignment and introduce an inference pipeline to improve performance without additional training. Specifically, we employ coars"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14812","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/2508.14812/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":"2508.14812","created_at":"2026-07-05T11:56:44.916137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14812v1","created_at":"2026-07-05T11:56:44.916137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14812","created_at":"2026-07-05T11:56:44.916137+00:00"},{"alias_kind":"pith_short_12","alias_value":"2BYWDPHL6V32","created_at":"2026-07-05T11:56:44.916137+00:00"},{"alias_kind":"pith_short_16","alias_value":"2BYWDPHL6V32GQHR","created_at":"2026-07-05T11:56:44.916137+00:00"},{"alias_kind":"pith_short_8","alias_value":"2BYWDPHL","created_at":"2026-07-05T11:56:44.916137+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/2BYWDPHL6V32GQHR6EZQC4IMIT","json":"https://pith.science/pith/2BYWDPHL6V32GQHR6EZQC4IMIT.json","graph_json":"https://pith.science/api/pith-number/2BYWDPHL6V32GQHR6EZQC4IMIT/graph.json","events_json":"https://pith.science/api/pith-number/2BYWDPHL6V32GQHR6EZQC4IMIT/events.json","paper":"https://pith.science/paper/2BYWDPHL"},"agent_actions":{"view_html":"https://pith.science/pith/2BYWDPHL6V32GQHR6EZQC4IMIT","download_json":"https://pith.science/pith/2BYWDPHL6V32GQHR6EZQC4IMIT.json","view_paper":"https://pith.science/paper/2BYWDPHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14812&json=true","fetch_graph":"https://pith.science/api/pith-number/2BYWDPHL6V32GQHR6EZQC4IMIT/graph.json","fetch_events":"https://pith.science/api/pith-number/2BYWDPHL6V32GQHR6EZQC4IMIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2BYWDPHL6V32GQHR6EZQC4IMIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2BYWDPHL6V32GQHR6EZQC4IMIT/action/storage_attestation","attest_author":"https://pith.science/pith/2BYWDPHL6V32GQHR6EZQC4IMIT/action/author_attestation","sign_citation":"https://pith.science/pith/2BYWDPHL6V32GQHR6EZQC4IMIT/action/citation_signature","submit_replication":"https://pith.science/pith/2BYWDPHL6V32GQHR6EZQC4IMIT/action/replication_record"}},"created_at":"2026-07-05T11:56:44.916137+00:00","updated_at":"2026-07-05T11:56:44.916137+00:00"}