{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G2QH3NLBOPC2S64LSZRUDQAUVP","short_pith_number":"pith:G2QH3NLB","schema_version":"1.0","canonical_sha256":"36a07db56173c5a97b8b966341c014abd079385ce901fdf5e9fa2d2325fef799","source":{"kind":"arxiv","id":"2411.12951","version":2},"attestation_state":"computed","paper":{"title":"On the Consistency of Video Large Language Models in Temporal Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Byoung-Tak Zhang, Junbin Xiao, Minjoon Jung","submitted_at":"2024-11-20T00:47:17Z","abstract_excerpt":"Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding. After the model identifies an initial moment within the video content, we apply a series of probes to check if the model's responses align with this initial grounding as an indicator of reliable comprehension. Our results reveal that current Video-LLMs are sensitive to variations"},"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":"2411.12951","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T00:47:17Z","cross_cats_sorted":[],"title_canon_sha256":"b4943dd5a8dac48bb06757430dbc9fab2de7411a8398dc90da9be3ec4a3125df","abstract_canon_sha256":"f34458f060b64b414dcffb7ec68b3d06f8063b603c6be76769ee11a22759ac35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:34.088054Z","signature_b64":"L7XVZeWKAlWN6a/HLZpRJB5Jj8Gj5nxjQY4lx3duuq9FmDp1KPFOfziAN+XtpEWeM5ywkrlxuVTZxbo/RbpdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36a07db56173c5a97b8b966341c014abd079385ce901fdf5e9fa2d2325fef799","last_reissued_at":"2026-07-05T10:32:34.087526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:34.087526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Consistency of Video Large Language Models in Temporal Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angela Yao, Byoung-Tak Zhang, Junbin Xiao, Minjoon Jung","submitted_at":"2024-11-20T00:47:17Z","abstract_excerpt":"Video large language models (Video-LLMs) can temporally ground language queries and retrieve video moments. Yet, such temporal comprehension capabilities are neither well-studied nor understood. So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding. After the model identifies an initial moment within the video content, we apply a series of probes to check if the model's responses align with this initial grounding as an indicator of reliable comprehension. Our results reveal that current Video-LLMs are sensitive to variations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12951","kind":"arxiv","version":2},"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/2411.12951/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":"2411.12951","created_at":"2026-07-05T10:32:34.087601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12951v2","created_at":"2026-07-05T10:32:34.087601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12951","created_at":"2026-07-05T10:32:34.087601+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2QH3NLBOPC2","created_at":"2026-07-05T10:32:34.087601+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2QH3NLBOPC2S64L","created_at":"2026-07-05T10:32:34.087601+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2QH3NLB","created_at":"2026-07-05T10:32:34.087601+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/G2QH3NLBOPC2S64LSZRUDQAUVP","json":"https://pith.science/pith/G2QH3NLBOPC2S64LSZRUDQAUVP.json","graph_json":"https://pith.science/api/pith-number/G2QH3NLBOPC2S64LSZRUDQAUVP/graph.json","events_json":"https://pith.science/api/pith-number/G2QH3NLBOPC2S64LSZRUDQAUVP/events.json","paper":"https://pith.science/paper/G2QH3NLB"},"agent_actions":{"view_html":"https://pith.science/pith/G2QH3NLBOPC2S64LSZRUDQAUVP","download_json":"https://pith.science/pith/G2QH3NLBOPC2S64LSZRUDQAUVP.json","view_paper":"https://pith.science/paper/G2QH3NLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12951&json=true","fetch_graph":"https://pith.science/api/pith-number/G2QH3NLBOPC2S64LSZRUDQAUVP/graph.json","fetch_events":"https://pith.science/api/pith-number/G2QH3NLBOPC2S64LSZRUDQAUVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2QH3NLBOPC2S64LSZRUDQAUVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2QH3NLBOPC2S64LSZRUDQAUVP/action/storage_attestation","attest_author":"https://pith.science/pith/G2QH3NLBOPC2S64LSZRUDQAUVP/action/author_attestation","sign_citation":"https://pith.science/pith/G2QH3NLBOPC2S64LSZRUDQAUVP/action/citation_signature","submit_replication":"https://pith.science/pith/G2QH3NLBOPC2S64LSZRUDQAUVP/action/replication_record"}},"created_at":"2026-07-05T10:32:34.087601+00:00","updated_at":"2026-07-05T10:32:34.087601+00:00"}