{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2OZKSOBF2HJRVHHUR4LBBSFMTU","short_pith_number":"pith:2OZKSOBF","schema_version":"1.0","canonical_sha256":"d3b2a93825d1d31a9cf48f1610c8ac9d04589edce7c88e5c9c93a6eed67f3b07","source":{"kind":"arxiv","id":"2606.24636","version":1},"attestation_state":"computed","paper":{"title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Max Meng, Meng Wang, Pengfei Wan, Wenyu Qin, Xiaohan Xing, Xiaokun Liu, Xin Tao, Xinyu Mao, Yuhui Zeng","submitted_at":"2026-06-23T14:29:40Z","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"},"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":"2606.24636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T14:29:40Z","cross_cats_sorted":[],"title_canon_sha256":"d62c6fbdbc3e017968783c08f8f30d67799ced963986a1226aaae13672936439","abstract_canon_sha256":"39ced5d3c6bb3f605848f86ec971d12307a7f2478c29298226b3c1009db143fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:37.775545Z","signature_b64":"wVOY0nSFVmBs2SrpdTRyaysfGqRAfHa35nz2DTixpkdDgrK+r2tWKADbr+bu+pjjwBf1KhBxe+p4cciz16keBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3b2a93825d1d31a9cf48f1610c8ac9d04589edce7c88e5c9c93a6eed67f3b07","last_reissued_at":"2026-06-24T01:15:37.775170Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:37.775170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Max Meng, Meng Wang, Pengfei Wan, Wenyu Qin, Xiaohan Xing, Xiaokun Liu, Xin Tao, Xinyu Mao, Yuhui Zeng","submitted_at":"2026-06-23T14:29:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24636","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/2606.24636/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":"2606.24636","created_at":"2026-06-24T01:15:37.775231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24636v1","created_at":"2026-06-24T01:15:37.775231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24636","created_at":"2026-06-24T01:15:37.775231+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OZKSOBF2HJR","created_at":"2026-06-24T01:15:37.775231+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OZKSOBF2HJRVHHU","created_at":"2026-06-24T01:15:37.775231+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OZKSOBF","created_at":"2026-06-24T01:15:37.775231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU","json":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU.json","graph_json":"https://pith.science/api/pith-number/2OZKSOBF2HJRVHHUR4LBBSFMTU/graph.json","events_json":"https://pith.science/api/pith-number/2OZKSOBF2HJRVHHUR4LBBSFMTU/events.json","paper":"https://pith.science/paper/2OZKSOBF"},"agent_actions":{"view_html":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU","download_json":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU.json","view_paper":"https://pith.science/paper/2OZKSOBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24636&json=true","fetch_graph":"https://pith.science/api/pith-number/2OZKSOBF2HJRVHHUR4LBBSFMTU/graph.json","fetch_events":"https://pith.science/api/pith-number/2OZKSOBF2HJRVHHUR4LBBSFMTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU/action/storage_attestation","attest_author":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU/action/author_attestation","sign_citation":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU/action/citation_signature","submit_replication":"https://pith.science/pith/2OZKSOBF2HJRVHHUR4LBBSFMTU/action/replication_record"}},"created_at":"2026-06-24T01:15:37.775231+00:00","updated_at":"2026-06-24T01:15:37.775231+00:00"}