{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2OZKSOBF2HJRVHHUR4LBBSFMTU","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":"39ced5d3c6bb3f605848f86ec971d12307a7f2478c29298226b3c1009db143fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T14:29:40Z","title_canon_sha256":"d62c6fbdbc3e017968783c08f8f30d67799ced963986a1226aaae13672936439"},"schema_version":"1.0","source":{"id":"2606.24636","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24636","created_at":"2026-06-24T01:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24636v1","created_at":"2026-06-24T01:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24636","created_at":"2026-06-24T01:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"2OZKSOBF2HJR","created_at":"2026-06-24T01:15:37Z"},{"alias_kind":"pith_short_16","alias_value":"2OZKSOBF2HJRVHHU","created_at":"2026-06-24T01:15:37Z"},{"alias_kind":"pith_short_8","alias_value":"2OZKSOBF","created_at":"2026-06-24T01:15:37Z"}],"graph_snapshots":[{"event_id":"sha256:ceb4b9066e7ca85dbd9a1a7a5c1382c29f4c5116e025030b0ee18609402c5c99","target":"graph","created_at":"2026-06-24T01:15:37Z","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/2606.24636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cinematographic captioning aims to describe how a video is filmed using professional film-language concepts such as camera movement, shot size, depth of field, composition, and shooting angle. This capability is important for fine-grained video understanding and controllable movie-quality video generation, yet remains underexplored in existing multimodal large language models. Unlike question-answering-based evaluation of cinematic understanding, cinematographic captioning requires a unified open-form description over multiple cinematographic dimensions. This task is challenging for two main r","authors_text":"Max Meng, Meng Wang, Pengfei Wan, Wenyu Qin, Xiaohan Xing, Xiaokun Liu, Xin Tao, Xinyu Mao, Yuhui Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T14:29:40Z","title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24636","kind":"arxiv","version":1},"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:c94410727befa8a68bad026feab7abc6e6dbdca9cd725769eb8a7c74cd6311a6","target":"record","created_at":"2026-06-24T01:15:37Z","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":"39ced5d3c6bb3f605848f86ec971d12307a7f2478c29298226b3c1009db143fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T14:29:40Z","title_canon_sha256":"d62c6fbdbc3e017968783c08f8f30d67799ced963986a1226aaae13672936439"},"schema_version":"1.0","source":{"id":"2606.24636","kind":"arxiv","version":1}},"canonical_sha256":"d3b2a93825d1d31a9cf48f1610c8ac9d04589edce7c88e5c9c93a6eed67f3b07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3b2a93825d1d31a9cf48f1610c8ac9d04589edce7c88e5c9c93a6eed67f3b07","first_computed_at":"2026-06-24T01:15:37.775170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:37.775170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wVOY0nSFVmBs2SrpdTRyaysfGqRAfHa35nz2DTixpkdDgrK+r2tWKADbr+bu+pjjwBf1KhBxe+p4cciz16keBQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:37.775545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24636","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c94410727befa8a68bad026feab7abc6e6dbdca9cd725769eb8a7c74cd6311a6","sha256:ceb4b9066e7ca85dbd9a1a7a5c1382c29f4c5116e025030b0ee18609402c5c99"],"state_sha256":"0912c49522d6a7cc0496647dfa0d20e77de01d30c1779b2db75183bd6e1c9cd5"}