{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2LRBGEVLNIRF7LW5ONZZLHSI35","short_pith_number":"pith:2LRBGEVL","schema_version":"1.0","canonical_sha256":"d2e21312ab6a225faedd7373959e48df48f9e2bffcf5e74e150a377fe685432a","source":{"kind":"arxiv","id":"2501.07214","version":1},"attestation_state":"computed","paper":{"title":"TimeLogic: A Temporal Logic Benchmark for Video QA","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hilde Kuehne, Mubarak Shah, Sirnam Swetha","submitted_at":"2025-01-13T11:12:59Z","abstract_excerpt":"Temporal logical understanding, a core facet of human cognition, plays a pivotal role in capturing complex sequential events and their temporal relationships within videos. This capability is particularly crucial in tasks like Video Question Answering (VideoQA), where the goal is to process visual data over time together with textual data to provide coherent answers. However, current VideoQA benchmarks devote little focus to evaluating this critical skill due to the challenge of annotating temporal logic. Despite the advancement of vision-language models, assessing their temporal logical reaso"},"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":"2501.07214","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-13T11:12:59Z","cross_cats_sorted":[],"title_canon_sha256":"8d52985a4f5bf692953862d3679540d9a94ed20c0cd9cb51ca667e022f945959","abstract_canon_sha256":"906c8ac3f432f6de5e3fb807fb92a71f6198f96effc7c7220505c6efcd2b5bf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:17.356775Z","signature_b64":"+NKCmAvZtMHK7bF9pz7RclnthIsLZ9fiO4laHsr8VNsPtKjawjWgW167g2a6NidBYbIEFELflu5mAn6k1cqLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2e21312ab6a225faedd7373959e48df48f9e2bffcf5e74e150a377fe685432a","last_reissued_at":"2026-07-05T10:00:17.356363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:17.356363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TimeLogic: A Temporal Logic Benchmark for Video QA","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hilde Kuehne, Mubarak Shah, Sirnam Swetha","submitted_at":"2025-01-13T11:12:59Z","abstract_excerpt":"Temporal logical understanding, a core facet of human cognition, plays a pivotal role in capturing complex sequential events and their temporal relationships within videos. This capability is particularly crucial in tasks like Video Question Answering (VideoQA), where the goal is to process visual data over time together with textual data to provide coherent answers. However, current VideoQA benchmarks devote little focus to evaluating this critical skill due to the challenge of annotating temporal logic. Despite the advancement of vision-language models, assessing their temporal logical reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07214","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/2501.07214/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":"2501.07214","created_at":"2026-07-05T10:00:17.356423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.07214v1","created_at":"2026-07-05T10:00:17.356423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07214","created_at":"2026-07-05T10:00:17.356423+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LRBGEVLNIRF","created_at":"2026-07-05T10:00:17.356423+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LRBGEVLNIRF7LW5","created_at":"2026-07-05T10:00:17.356423+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LRBGEVL","created_at":"2026-07-05T10:00:17.356423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01591","citing_title":"TLG: Temporal-Logic Grounding for Video Question Answering via Source-Annotation Reconstruction and Category-Targeted Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01106","citing_title":"Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35","json":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35.json","graph_json":"https://pith.science/api/pith-number/2LRBGEVLNIRF7LW5ONZZLHSI35/graph.json","events_json":"https://pith.science/api/pith-number/2LRBGEVLNIRF7LW5ONZZLHSI35/events.json","paper":"https://pith.science/paper/2LRBGEVL"},"agent_actions":{"view_html":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35","download_json":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35.json","view_paper":"https://pith.science/paper/2LRBGEVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.07214&json=true","fetch_graph":"https://pith.science/api/pith-number/2LRBGEVLNIRF7LW5ONZZLHSI35/graph.json","fetch_events":"https://pith.science/api/pith-number/2LRBGEVLNIRF7LW5ONZZLHSI35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35/action/storage_attestation","attest_author":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35/action/author_attestation","sign_citation":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35/action/citation_signature","submit_replication":"https://pith.science/pith/2LRBGEVLNIRF7LW5ONZZLHSI35/action/replication_record"}},"created_at":"2026-07-05T10:00:17.356423+00:00","updated_at":"2026-07-05T10:00:17.356423+00:00"}