{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:D3C4YGCU3KLZ44ITEVVKHQY4H2","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":"b136eba413297afcfcad8b4b283b79dce62d1f8b692b8d7c6098d7023579f30a","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-20T08:43:51Z","title_canon_sha256":"bbb58d08d7550afb64c4d38e89a8dfa062cfb245baa8593e8016757c83edb50f"},"schema_version":"1.0","source":{"id":"2305.12140","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12140","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12140v2","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12140","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_12","alias_value":"D3C4YGCU3KLZ","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_16","alias_value":"D3C4YGCU3KLZ44IT","created_at":"2026-07-05T06:24:50Z"},{"alias_kind":"pith_short_8","alias_value":"D3C4YGCU","created_at":"2026-07-05T06:24:50Z"}],"graph_snapshots":[{"event_id":"sha256:a38363284d8179719f3eb35d71a8ac2ad1e935fcf4b4cc8c47ffc1565e090d9e","target":"graph","created_at":"2026-07-05T06:24:50Z","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/2305.12140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To help the visually impaired enjoy movies, automatic movie narrating systems are expected to narrate accurate, coherent, and role-aware plots when there are no speaking lines of actors. Existing works benchmark this challenge as a normal video captioning task via some simplifications, such as removing role names and evaluating narrations with ngram-based metrics, which makes it difficult for automatic systems to meet the needs of real application scenarios. To narrow this gap, we construct a large-scale Chinese movie benchmark, named Movie101. Closer to real scenarios, the Movie Clip Narratin","authors_text":"Anwen Hu, Liang Zhang, Qin Jin, Qi Zhang, Zihao Yue, Ziheng Wang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-20T08:43:51Z","title":"Movie101: A New Movie Understanding Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12140","kind":"arxiv","version":2},"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:c959ee815ac32a941793b7d85c7a8e582b41016d5a8e5863a960090ada8cc6c3","target":"record","created_at":"2026-07-05T06:24:50Z","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":"b136eba413297afcfcad8b4b283b79dce62d1f8b692b8d7c6098d7023579f30a","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-20T08:43:51Z","title_canon_sha256":"bbb58d08d7550afb64c4d38e89a8dfa062cfb245baa8593e8016757c83edb50f"},"schema_version":"1.0","source":{"id":"2305.12140","kind":"arxiv","version":2}},"canonical_sha256":"1ec5cc1854da979e7113256aa3c31c3eb8f6df571054b1ace3b73e8375cfdda5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ec5cc1854da979e7113256aa3c31c3eb8f6df571054b1ace3b73e8375cfdda5","first_computed_at":"2026-07-05T06:24:50.140845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:50.140845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CC3EDnKSeiuKrCT7rCRs9Q0pVFaACLXzY22EAcgg4D8nIPwmpVH/Xl1HEHrBy0D9ZR9I5888PW9Um2WAHjDkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:50.141216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12140","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c959ee815ac32a941793b7d85c7a8e582b41016d5a8e5863a960090ada8cc6c3","sha256:a38363284d8179719f3eb35d71a8ac2ad1e935fcf4b4cc8c47ffc1565e090d9e"],"state_sha256":"5dc3f65e48e9f5698b1e4ea98f2a15d2aacff59e5639ddf99c1835e805b87ffa"}