{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RCM3HA6FM2IIZTJTMVNX3DXQLE","short_pith_number":"pith:RCM3HA6F","schema_version":"1.0","canonical_sha256":"8899b383c566908ccd33655b7d8ef059265e8696dcbfc4138480081a5254d539","source":{"kind":"arxiv","id":"2406.10923","version":1},"attestation_state":"computed","paper":{"title":"Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun-Tong Chao, Hung-Ting Su, Hung-yi Lee, Winston H. Hsu, Xudong Lin, Ya-Ching Hsu, Yulei Niu","submitted_at":"2024-06-16T12:58:31Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated effectiveness not only in language tasks but also in video reasoning. This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet previously overlooked video reasoning skills: (1) Abstract Perception: understanding and tokenizing abstract concepts in videos, and (2) Long-range Compositional Reasoning: planning and integrating intermediate reasoning steps for understanding long-range videos with numerous frames. Utilizing tropes from movie storytelling, TiM evaluates the reasoning capabilities"},"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":"2406.10923","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-16T12:58:31Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"849b46c017565554371b319073604b3bee8ba1616500704b038f1fe5ce70a84c","abstract_canon_sha256":"ebe7b52b9d6ea8094fe3c455135f6877951791372f5db52efa33c2da2575f7bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:46.459899Z","signature_b64":"vYOiwTmh5alQLpi16g1651bjfxhfGZ8lVrUYBssBKo/jTL5Z4EsvAK/hlUgIbNqDR8Siof8aPSCzoqiqhmDrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8899b383c566908ccd33655b7d8ef059265e8696dcbfc4138480081a5254d539","last_reissued_at":"2026-07-05T08:32:46.459467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:46.459467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chun-Tong Chao, Hung-Ting Su, Hung-yi Lee, Winston H. Hsu, Xudong Lin, Ya-Ching Hsu, Yulei Niu","submitted_at":"2024-06-16T12:58:31Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated effectiveness not only in language tasks but also in video reasoning. This paper introduces a novel dataset, Tropes in Movies (TiM), designed as a testbed for exploring two critical yet previously overlooked video reasoning skills: (1) Abstract Perception: understanding and tokenizing abstract concepts in videos, and (2) Long-range Compositional Reasoning: planning and integrating intermediate reasoning steps for understanding long-range videos with numerous frames. Utilizing tropes from movie storytelling, TiM evaluates the reasoning capabilities"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10923","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/2406.10923/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":"2406.10923","created_at":"2026-07-05T08:32:46.459523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10923v1","created_at":"2026-07-05T08:32:46.459523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10923","created_at":"2026-07-05T08:32:46.459523+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCM3HA6FM2II","created_at":"2026-07-05T08:32:46.459523+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCM3HA6FM2IIZTJT","created_at":"2026-07-05T08:32:46.459523+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCM3HA6F","created_at":"2026-07-05T08:32:46.459523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19499","citing_title":"Narrative Structure in Tropes: A Computational Analysis of `Friends'","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE","json":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE.json","graph_json":"https://pith.science/api/pith-number/RCM3HA6FM2IIZTJTMVNX3DXQLE/graph.json","events_json":"https://pith.science/api/pith-number/RCM3HA6FM2IIZTJTMVNX3DXQLE/events.json","paper":"https://pith.science/paper/RCM3HA6F"},"agent_actions":{"view_html":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE","download_json":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE.json","view_paper":"https://pith.science/paper/RCM3HA6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10923&json=true","fetch_graph":"https://pith.science/api/pith-number/RCM3HA6FM2IIZTJTMVNX3DXQLE/graph.json","fetch_events":"https://pith.science/api/pith-number/RCM3HA6FM2IIZTJTMVNX3DXQLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE/action/storage_attestation","attest_author":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE/action/author_attestation","sign_citation":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE/action/citation_signature","submit_replication":"https://pith.science/pith/RCM3HA6FM2IIZTJTMVNX3DXQLE/action/replication_record"}},"created_at":"2026-07-05T08:32:46.459523+00:00","updated_at":"2026-07-05T08:32:46.459523+00:00"}