{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2URLOLOPNJWRJEVWU77DDGA65K","short_pith_number":"pith:2URLOLOP","schema_version":"1.0","canonical_sha256":"d522b72dcf6a6d1492b6a7fe31981eeab16c0fdf879b6f4e0484e24a8d7cd78b","source":{"kind":"arxiv","id":"2607.19027","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheol-Ho Cho, Jae-Pil Heo, Jihyun Lee, Woojin Jeong, Woojin Jun","submitted_at":"2026-07-21T12:16:29Z","abstract_excerpt":"Zero-shot video moment retrieval aims to overcome the limitations of traditional approaches that require large-scale datasets annotated with text and its relevant temporal spans. Despite advances in pre-trained vision-language models and multimodal large language models, existing ZMR methods still heavily depend on query-to-video content similarity, making them vulnerable to modality and language-style gaps. These gaps lead to unreliable span proposals and unstable moment retrieval results. To address this issue, we propose Self-Similarity-based Moment Proposal and Scoring that instead exploit"},"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":"2607.19027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T12:16:29Z","cross_cats_sorted":[],"title_canon_sha256":"dbd4c7910d20d0980a899d64d4790a7ab17b03fe753d26513e3a488db4363ec4","abstract_canon_sha256":"14f7d6fbaadd4d9b2eee505998101684fa962dad1f54ba30c87f4b5c04d894c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:24:04.945851Z","signature_b64":"NeFu0a6OwLnq2a6HJuw7W8iKcIJZKxUcVaf/Ymrtq7UHfyVn46RHc6IstlaNBc8O/W82WdQM81CKW2mLssglAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d522b72dcf6a6d1492b6a7fe31981eeab16c0fdf879b6f4e0484e24a8d7cd78b","last_reissued_at":"2026-07-22T01:24:04.945045Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:24:04.945045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheol-Ho Cho, Jae-Pil Heo, Jihyun Lee, Woojin Jeong, Woojin Jun","submitted_at":"2026-07-21T12:16:29Z","abstract_excerpt":"Zero-shot video moment retrieval aims to overcome the limitations of traditional approaches that require large-scale datasets annotated with text and its relevant temporal spans. Despite advances in pre-trained vision-language models and multimodal large language models, existing ZMR methods still heavily depend on query-to-video content similarity, making them vulnerable to modality and language-style gaps. These gaps lead to unreliable span proposals and unstable moment retrieval results. To address this issue, we propose Self-Similarity-based Moment Proposal and Scoring that instead exploit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19027","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/2607.19027/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":"2607.19027","created_at":"2026-07-22T01:24:04.945465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19027v1","created_at":"2026-07-22T01:24:04.945465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19027","created_at":"2026-07-22T01:24:04.945465+00:00"},{"alias_kind":"pith_short_12","alias_value":"2URLOLOPNJWR","created_at":"2026-07-22T01:24:04.945465+00:00"},{"alias_kind":"pith_short_16","alias_value":"2URLOLOPNJWRJEVW","created_at":"2026-07-22T01:24:04.945465+00:00"},{"alias_kind":"pith_short_8","alias_value":"2URLOLOP","created_at":"2026-07-22T01:24:04.945465+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/2URLOLOPNJWRJEVWU77DDGA65K","json":"https://pith.science/pith/2URLOLOPNJWRJEVWU77DDGA65K.json","graph_json":"https://pith.science/api/pith-number/2URLOLOPNJWRJEVWU77DDGA65K/graph.json","events_json":"https://pith.science/api/pith-number/2URLOLOPNJWRJEVWU77DDGA65K/events.json","paper":"https://pith.science/paper/2URLOLOP"},"agent_actions":{"view_html":"https://pith.science/pith/2URLOLOPNJWRJEVWU77DDGA65K","download_json":"https://pith.science/pith/2URLOLOPNJWRJEVWU77DDGA65K.json","view_paper":"https://pith.science/paper/2URLOLOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19027&json=true","fetch_graph":"https://pith.science/api/pith-number/2URLOLOPNJWRJEVWU77DDGA65K/graph.json","fetch_events":"https://pith.science/api/pith-number/2URLOLOPNJWRJEVWU77DDGA65K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2URLOLOPNJWRJEVWU77DDGA65K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2URLOLOPNJWRJEVWU77DDGA65K/action/storage_attestation","attest_author":"https://pith.science/pith/2URLOLOPNJWRJEVWU77DDGA65K/action/author_attestation","sign_citation":"https://pith.science/pith/2URLOLOPNJWRJEVWU77DDGA65K/action/citation_signature","submit_replication":"https://pith.science/pith/2URLOLOPNJWRJEVWU77DDGA65K/action/replication_record"}},"created_at":"2026-07-22T01:24:04.945465+00:00","updated_at":"2026-07-22T01:24:04.945465+00:00"}