{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VEHIZFEASXJNJL3TGDRWC6NWAH","short_pith_number":"pith:VEHIZFEA","schema_version":"1.0","canonical_sha256":"a90e8c948095d2d4af7330e36179b601d46bd7bf8ca664d2e8adcbe32d4dc5df","source":{"kind":"arxiv","id":"2605.29793","version":1},"attestation_state":"computed","paper":{"title":"Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daizong Liu, Junyang Chen, Pan Zhou, Renfu Li, Wanlong Fang, Wenzheng Xu, Xiang Fang, Zichuan Xu","submitted_at":"2026-05-28T11:42:28Z","abstract_excerpt":"Given an untrimmed video and a sentence query, video moment retrieval using language (VMR) aims to locate a target query-relevant moment. Since the untrimmed video is overlong, almost all existing VMR methods first sparsely down-sample each untrimmed video into multiple fixed-length video clips and then conduct multi-modal interactions with the query feature and expensive clip features for reasoning, which is infeasible for long real-world videos that span hours. Since the video is downsampled into fixed-length clips, some query-related frames may be filtered out, which will blur the specific "},"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":"2605.29793","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T11:42:28Z","cross_cats_sorted":[],"title_canon_sha256":"2ffb2c61ba0030fd6995143e592d9bb83ac779f1e66c3b31d152da6654fe65c7","abstract_canon_sha256":"f459992c128137d0d503ddc8f01802aef3746c08b173cb14e5acf0697eed24e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:52.643110Z","signature_b64":"BqaPVg8Ma553LdPWxQixHwoYHxYVirgF4Qba7xbGAqDQVc39V7tWITYhbAdensT20Y0f+5OC3cQtk4fHvE3LBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a90e8c948095d2d4af7330e36179b601d46bd7bf8ca664d2e8adcbe32d4dc5df","last_reissued_at":"2026-05-29T02:05:52.642029Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:52.642029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daizong Liu, Junyang Chen, Pan Zhou, Renfu Li, Wanlong Fang, Wenzheng Xu, Xiang Fang, Zichuan Xu","submitted_at":"2026-05-28T11:42:28Z","abstract_excerpt":"Given an untrimmed video and a sentence query, video moment retrieval using language (VMR) aims to locate a target query-relevant moment. Since the untrimmed video is overlong, almost all existing VMR methods first sparsely down-sample each untrimmed video into multiple fixed-length video clips and then conduct multi-modal interactions with the query feature and expensive clip features for reasoning, which is infeasible for long real-world videos that span hours. Since the video is downsampled into fixed-length clips, some query-related frames may be filtered out, which will blur the specific "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29793","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/2605.29793/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":"2605.29793","created_at":"2026-05-29T02:05:52.642153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29793v1","created_at":"2026-05-29T02:05:52.642153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29793","created_at":"2026-05-29T02:05:52.642153+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEHIZFEASXJN","created_at":"2026-05-29T02:05:52.642153+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEHIZFEASXJNJL3T","created_at":"2026-05-29T02:05:52.642153+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEHIZFEA","created_at":"2026-05-29T02:05:52.642153+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/VEHIZFEASXJNJL3TGDRWC6NWAH","json":"https://pith.science/pith/VEHIZFEASXJNJL3TGDRWC6NWAH.json","graph_json":"https://pith.science/api/pith-number/VEHIZFEASXJNJL3TGDRWC6NWAH/graph.json","events_json":"https://pith.science/api/pith-number/VEHIZFEASXJNJL3TGDRWC6NWAH/events.json","paper":"https://pith.science/paper/VEHIZFEA"},"agent_actions":{"view_html":"https://pith.science/pith/VEHIZFEASXJNJL3TGDRWC6NWAH","download_json":"https://pith.science/pith/VEHIZFEASXJNJL3TGDRWC6NWAH.json","view_paper":"https://pith.science/paper/VEHIZFEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29793&json=true","fetch_graph":"https://pith.science/api/pith-number/VEHIZFEASXJNJL3TGDRWC6NWAH/graph.json","fetch_events":"https://pith.science/api/pith-number/VEHIZFEASXJNJL3TGDRWC6NWAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEHIZFEASXJNJL3TGDRWC6NWAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEHIZFEASXJNJL3TGDRWC6NWAH/action/storage_attestation","attest_author":"https://pith.science/pith/VEHIZFEASXJNJL3TGDRWC6NWAH/action/author_attestation","sign_citation":"https://pith.science/pith/VEHIZFEASXJNJL3TGDRWC6NWAH/action/citation_signature","submit_replication":"https://pith.science/pith/VEHIZFEASXJNJL3TGDRWC6NWAH/action/replication_record"}},"created_at":"2026-05-29T02:05:52.642153+00:00","updated_at":"2026-05-29T02:05:52.642153+00:00"}