{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:74OPJVVZWNT2BQZN4OGEUO7EWL","short_pith_number":"pith:74OPJVVZ","schema_version":"1.0","canonical_sha256":"ff1cf4d6b9b367a0c32de38c4a3be4b2fd2bc1439e8f694c043d04ab6cf74e4b","source":{"kind":"arxiv","id":"2412.09276","version":1},"attestation_state":"computed","paper":{"title":"Text-Video Multi-Grained Integration for Video Moment Montage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Peng Jiang, Quan Chen, Xipeng Cao, Ye Ma, Zhihui Yin","submitted_at":"2024-12-12T13:40:59Z","abstract_excerpt":"The proliferation of online short video platforms has driven a surge in user demand for short video editing. However, manually selecting, cropping, and assembling raw footage into a coherent, high-quality video remains laborious and time-consuming. To accelerate this process, we focus on a user-friendly new task called Video Moment Montage (VMM), which aims to accurately locate the corresponding video segments based on a pre-provided narration text and then arrange these video clips to create a complete video that aligns with the corresponding descriptions. The challenge lies in extracting pre"},"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":"2412.09276","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T13:40:59Z","cross_cats_sorted":[],"title_canon_sha256":"d1cf5538640d189922c1a00e32d5f8183f63efa6dfd82cd5a5351d457e9ead51","abstract_canon_sha256":"586bdc4d03d735c32626eff209be161d8dedcb0a741717441a791261f0a1c612"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:22.437767Z","signature_b64":"Dbqc05P0BTSRI19djpaeL91B7D6VgYtkUdKaO+NERur/6pERFUKrM8MjXKIItTIPJNTZtbA2tFBpFT/jzcOyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff1cf4d6b9b367a0c32de38c4a3be4b2fd2bc1439e8f694c043d04ab6cf74e4b","last_reissued_at":"2026-07-05T09:48:22.437280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:22.437280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-Video Multi-Grained Integration for Video Moment Montage","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Wang, Peng Jiang, Quan Chen, Xipeng Cao, Ye Ma, Zhihui Yin","submitted_at":"2024-12-12T13:40:59Z","abstract_excerpt":"The proliferation of online short video platforms has driven a surge in user demand for short video editing. However, manually selecting, cropping, and assembling raw footage into a coherent, high-quality video remains laborious and time-consuming. To accelerate this process, we focus on a user-friendly new task called Video Moment Montage (VMM), which aims to accurately locate the corresponding video segments based on a pre-provided narration text and then arrange these video clips to create a complete video that aligns with the corresponding descriptions. The challenge lies in extracting pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09276","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/2412.09276/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":"2412.09276","created_at":"2026-07-05T09:48:22.437340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09276v1","created_at":"2026-07-05T09:48:22.437340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09276","created_at":"2026-07-05T09:48:22.437340+00:00"},{"alias_kind":"pith_short_12","alias_value":"74OPJVVZWNT2","created_at":"2026-07-05T09:48:22.437340+00:00"},{"alias_kind":"pith_short_16","alias_value":"74OPJVVZWNT2BQZN","created_at":"2026-07-05T09:48:22.437340+00:00"},{"alias_kind":"pith_short_8","alias_value":"74OPJVVZ","created_at":"2026-07-05T09:48:22.437340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04098","citing_title":"When Seeing Is Not Believing -- A Benchmark for Search-Grounded Video Misinformation Detection","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL","json":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL.json","graph_json":"https://pith.science/api/pith-number/74OPJVVZWNT2BQZN4OGEUO7EWL/graph.json","events_json":"https://pith.science/api/pith-number/74OPJVVZWNT2BQZN4OGEUO7EWL/events.json","paper":"https://pith.science/paper/74OPJVVZ"},"agent_actions":{"view_html":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL","download_json":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL.json","view_paper":"https://pith.science/paper/74OPJVVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09276&json=true","fetch_graph":"https://pith.science/api/pith-number/74OPJVVZWNT2BQZN4OGEUO7EWL/graph.json","fetch_events":"https://pith.science/api/pith-number/74OPJVVZWNT2BQZN4OGEUO7EWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL/action/storage_attestation","attest_author":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL/action/author_attestation","sign_citation":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL/action/citation_signature","submit_replication":"https://pith.science/pith/74OPJVVZWNT2BQZN4OGEUO7EWL/action/replication_record"}},"created_at":"2026-07-05T09:48:22.437340+00:00","updated_at":"2026-07-05T09:48:22.437340+00:00"}