{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MGAOBBNQL2WR23ZF6R4G7DWAW5","short_pith_number":"pith:MGAOBBNQ","schema_version":"1.0","canonical_sha256":"6180e085b05ead1d6f25f4786f8ec0b77614431554ae949ea49b866da4172bac","source":{"kind":"arxiv","id":"2312.10300","version":3},"attestation_state":"computed","paper":{"title":"Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Wang, Lina Yao, Linjie Yang, Mingfei Han, Xiaojun Chang","submitted_at":"2023-12-16T03:17:30Z","abstract_excerpt":"A short clip of video may contain progression of multiple events and an interesting story line. A human need to capture both the event in every shot and associate them together to understand the story behind it. In this work, we present a new multi-shot video understanding benchmark Shot2Story with detailed shot-level captions, comprehensive video summaries and question-answering pairs. To facilitate better semantic understanding of videos, we provide captions for both visual signals and human narrations. We design several distinct tasks including single-shot video captioning, multi-shot video"},"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":"2312.10300","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T03:17:30Z","cross_cats_sorted":[],"title_canon_sha256":"0cd116de3e9c6509aa11595606af86525d5e22ff2190bb8f939b689960654943","abstract_canon_sha256":"6776afb888be1358a3fd25c5cf839429b9824613c25cb1a0af3b5e99b0b3766b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:41.617382Z","signature_b64":"iNkSiRKazo7992+m72ZJNJJpBhqt2RuzjejoDDekgQm0dkkUBtV1V4w1UYVYru3AYOVUOsIO9sYR6QV/Bzw9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6180e085b05ead1d6f25f4786f8ec0b77614431554ae949ea49b866da4172bac","last_reissued_at":"2026-07-05T10:09:41.616901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:41.616901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Wang, Lina Yao, Linjie Yang, Mingfei Han, Xiaojun Chang","submitted_at":"2023-12-16T03:17:30Z","abstract_excerpt":"A short clip of video may contain progression of multiple events and an interesting story line. A human need to capture both the event in every shot and associate them together to understand the story behind it. In this work, we present a new multi-shot video understanding benchmark Shot2Story with detailed shot-level captions, comprehensive video summaries and question-answering pairs. To facilitate better semantic understanding of videos, we provide captions for both visual signals and human narrations. We design several distinct tasks including single-shot video captioning, multi-shot video"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10300","kind":"arxiv","version":3},"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/2312.10300/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":"2312.10300","created_at":"2026-07-05T10:09:41.616959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10300v3","created_at":"2026-07-05T10:09:41.616959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10300","created_at":"2026-07-05T10:09:41.616959+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGAOBBNQL2WR","created_at":"2026-07-05T10:09:41.616959+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGAOBBNQL2WR23ZF","created_at":"2026-07-05T10:09:41.616959+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGAOBBNQ","created_at":"2026-07-05T10:09:41.616959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17798","citing_title":"LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08615","citing_title":"Harnessing Streaming Video in the Wild","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21334","citing_title":"Streaming Video Instruction Tuning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23789","citing_title":"MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23789","citing_title":"MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15127","citing_title":"MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5","json":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5.json","graph_json":"https://pith.science/api/pith-number/MGAOBBNQL2WR23ZF6R4G7DWAW5/graph.json","events_json":"https://pith.science/api/pith-number/MGAOBBNQL2WR23ZF6R4G7DWAW5/events.json","paper":"https://pith.science/paper/MGAOBBNQ"},"agent_actions":{"view_html":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5","download_json":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5.json","view_paper":"https://pith.science/paper/MGAOBBNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10300&json=true","fetch_graph":"https://pith.science/api/pith-number/MGAOBBNQL2WR23ZF6R4G7DWAW5/graph.json","fetch_events":"https://pith.science/api/pith-number/MGAOBBNQL2WR23ZF6R4G7DWAW5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5/action/storage_attestation","attest_author":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5/action/author_attestation","sign_citation":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5/action/citation_signature","submit_replication":"https://pith.science/pith/MGAOBBNQL2WR23ZF6R4G7DWAW5/action/replication_record"}},"created_at":"2026-07-05T10:09:41.616959+00:00","updated_at":"2026-07-05T10:09:41.616959+00:00"}