{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J3CN44B5LHPEPPVCHQNEOTLTHW","short_pith_number":"pith:J3CN44B5","schema_version":"1.0","canonical_sha256":"4ec4de703d59de47bea23c1a474d733d9edef9aefefccda93b96071c64820be4","source":{"kind":"arxiv","id":"2402.19467","version":4},"attestation_state":"computed","paper":{"title":"TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Kate Sanders, Nathaniel Weir","submitted_at":"2024-02-29T18:57:01Z","abstract_excerpt":"It is challenging for models to understand complex, multimodal content such as television clips, and this is in part because video-language models often rely on single-modality reasoning and lack interpretability. To combat these issues we propose TV-TREES, the first multimodal entailment tree generator. TV-TREES serves as an approach to video understanding that promotes interpretable joint-modality reasoning by searching for trees of entailment relationships between simple text-video evidence and higher-level conclusions that prove question-answer pairs. We also introduce the task of multimod"},"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":"2402.19467","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-29T18:57:01Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"3de3e71d43eae45b226eb2466eb56b24c36d29672c82e10675f876ae502c273e","abstract_canon_sha256":"5d9e9fd7b93e9008efad4e70719e244f299074bed2b61d426e210b7100737573"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:23.590918Z","signature_b64":"tBKDBZ6Py3xAnWWUFYQu53kZrS/R9ywsc8lt1LoKhVjjoh+K0iku81A1ilCF03sYR3PKGkC28y74ytwmXaGnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ec4de703d59de47bea23c1a474d733d9edef9aefefccda93b96071c64820be4","last_reissued_at":"2026-07-05T09:18:23.590434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:23.590434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Benjamin Van Durme, Kate Sanders, Nathaniel Weir","submitted_at":"2024-02-29T18:57:01Z","abstract_excerpt":"It is challenging for models to understand complex, multimodal content such as television clips, and this is in part because video-language models often rely on single-modality reasoning and lack interpretability. To combat these issues we propose TV-TREES, the first multimodal entailment tree generator. TV-TREES serves as an approach to video understanding that promotes interpretable joint-modality reasoning by searching for trees of entailment relationships between simple text-video evidence and higher-level conclusions that prove question-answer pairs. We also introduce the task of multimod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19467","kind":"arxiv","version":4},"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/2402.19467/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":"2402.19467","created_at":"2026-07-05T09:18:23.590486+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.19467v4","created_at":"2026-07-05T09:18:23.590486+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19467","created_at":"2026-07-05T09:18:23.590486+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3CN44B5LHPE","created_at":"2026-07-05T09:18:23.590486+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3CN44B5LHPEPPVC","created_at":"2026-07-05T09:18:23.590486+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3CN44B5","created_at":"2026-07-05T09:18:23.590486+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03039","citing_title":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW","json":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW.json","graph_json":"https://pith.science/api/pith-number/J3CN44B5LHPEPPVCHQNEOTLTHW/graph.json","events_json":"https://pith.science/api/pith-number/J3CN44B5LHPEPPVCHQNEOTLTHW/events.json","paper":"https://pith.science/paper/J3CN44B5"},"agent_actions":{"view_html":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW","download_json":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW.json","view_paper":"https://pith.science/paper/J3CN44B5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.19467&json=true","fetch_graph":"https://pith.science/api/pith-number/J3CN44B5LHPEPPVCHQNEOTLTHW/graph.json","fetch_events":"https://pith.science/api/pith-number/J3CN44B5LHPEPPVCHQNEOTLTHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW/action/storage_attestation","attest_author":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW/action/author_attestation","sign_citation":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW/action/citation_signature","submit_replication":"https://pith.science/pith/J3CN44B5LHPEPPVCHQNEOTLTHW/action/replication_record"}},"created_at":"2026-07-05T09:18:23.590486+00:00","updated_at":"2026-07-05T09:18:23.590486+00:00"}