{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MGAOBBNQL2WR23ZF6R4G7DWAW5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6776afb888be1358a3fd25c5cf839429b9824613c25cb1a0af3b5e99b0b3766b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T03:17:30Z","title_canon_sha256":"0cd116de3e9c6509aa11595606af86525d5e22ff2190bb8f939b689960654943"},"schema_version":"1.0","source":{"id":"2312.10300","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10300","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10300v3","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10300","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"MGAOBBNQL2WR","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"MGAOBBNQL2WR23ZF","created_at":"2026-07-05T10:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"MGAOBBNQ","created_at":"2026-07-05T10:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:a0643b0144528e10c99fd34d1d89e5e6a5412602fd680c3473584fbae9c112e0","target":"graph","created_at":"2026-07-05T10:09:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.10300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Heng Wang, Lina Yao, Linjie Yang, Mingfei Han, Xiaojun Chang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T03:17:30Z","title":"Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10300","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6badea4734d1d0574bc990ddd100d06d73e5aa1bca2223c038dbb5277cf66358","target":"record","created_at":"2026-07-05T10:09:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6776afb888be1358a3fd25c5cf839429b9824613c25cb1a0af3b5e99b0b3766b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T03:17:30Z","title_canon_sha256":"0cd116de3e9c6509aa11595606af86525d5e22ff2190bb8f939b689960654943"},"schema_version":"1.0","source":{"id":"2312.10300","kind":"arxiv","version":3}},"canonical_sha256":"6180e085b05ead1d6f25f4786f8ec0b77614431554ae949ea49b866da4172bac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6180e085b05ead1d6f25f4786f8ec0b77614431554ae949ea49b866da4172bac","first_computed_at":"2026-07-05T10:09:41.616901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:41.616901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iNkSiRKazo7992+m72ZJNJJpBhqt2RuzjejoDDekgQm0dkkUBtV1V4w1UYVYru3AYOVUOsIO9sYR6QV/Bzw9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:41.617382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10300","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6badea4734d1d0574bc990ddd100d06d73e5aa1bca2223c038dbb5277cf66358","sha256:a0643b0144528e10c99fd34d1d89e5e6a5412602fd680c3473584fbae9c112e0"],"state_sha256":"3213c12c2593421e468e27dade6c5ad3b337b5f565893565bd7b6e9db91c65e7"}