{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UZ62NATTLZXLCT7SELAKYD324C","short_pith_number":"pith:UZ62NATT","schema_version":"1.0","canonical_sha256":"a67da682735e6eb14ff222c0ac0f7ae0a8a4a3b854a126b94cc81cd6c605d797","source":{"kind":"arxiv","id":"2510.26113","version":2},"attestation_state":"computed","paper":{"title":"EgoExo-Con: Exploring View-Invariant Video Temporal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Byoung-Tak Zhang, Junbin Xiao, Junghyun Kim, Minjoon Jung","submitted_at":"2025-10-30T03:53:22Z","abstract_excerpt":"Do Video-LLMs have consistent temporal understanding when videos capture the same event from different viewpoints? To study this question, we introduce EgoExo-Con(sistency), a benchmark of synchronized egocentric and exocentric video pairs with human-refined queries that ensure all concepts are visible in both viewpoints. EgoExo-Con emphasizes two temporal understanding tasks: Temporal Verification and Temporal Grounding. It evaluates not only correctness but consistency across viewpoints. Our analysis reveals two critical limitations of existing Video-LLMs: (1) models often fail to maintain c"},"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":"2510.26113","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-30T03:53:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f2768a40f2f1cb227e4233c2c7eae7a874735b9aedf9358cd1601858cc56ace","abstract_canon_sha256":"c7e1664a42713f60a55a1971a1d377b7d33c7ed83c78ec69b3da9da648803bf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:11:58.456993Z","signature_b64":"bVr7LbZ7IU2eM8W/QuoVG52IjV3ChRn2IenXZANtKl02bWHpVvi/iiHkjt6k9ymu4vmKFSY9/iMlDdcMEfSSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a67da682735e6eb14ff222c0ac0f7ae0a8a4a3b854a126b94cc81cd6c605d797","last_reissued_at":"2026-06-23T01:11:58.456446Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:11:58.456446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoExo-Con: Exploring View-Invariant Video Temporal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Angela Yao, Byoung-Tak Zhang, Junbin Xiao, Junghyun Kim, Minjoon Jung","submitted_at":"2025-10-30T03:53:22Z","abstract_excerpt":"Do Video-LLMs have consistent temporal understanding when videos capture the same event from different viewpoints? To study this question, we introduce EgoExo-Con(sistency), a benchmark of synchronized egocentric and exocentric video pairs with human-refined queries that ensure all concepts are visible in both viewpoints. EgoExo-Con emphasizes two temporal understanding tasks: Temporal Verification and Temporal Grounding. It evaluates not only correctness but consistency across viewpoints. Our analysis reveals two critical limitations of existing Video-LLMs: (1) models often fail to maintain c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.26113","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/2510.26113/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":"2510.26113","created_at":"2026-06-23T01:11:58.456513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.26113v2","created_at":"2026-06-23T01:11:58.456513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.26113","created_at":"2026-06-23T01:11:58.456513+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZ62NATTLZXL","created_at":"2026-06-23T01:11:58.456513+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZ62NATTLZXLCT7S","created_at":"2026-06-23T01:11:58.456513+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZ62NATT","created_at":"2026-06-23T01:11:58.456513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.18734","citing_title":"EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18431","citing_title":"Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13803","citing_title":"EvoGround: Self-Evolving Video Agents for Video Temporal Grounding","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C","json":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C.json","graph_json":"https://pith.science/api/pith-number/UZ62NATTLZXLCT7SELAKYD324C/graph.json","events_json":"https://pith.science/api/pith-number/UZ62NATTLZXLCT7SELAKYD324C/events.json","paper":"https://pith.science/paper/UZ62NATT"},"agent_actions":{"view_html":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C","download_json":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C.json","view_paper":"https://pith.science/paper/UZ62NATT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.26113&json=true","fetch_graph":"https://pith.science/api/pith-number/UZ62NATTLZXLCT7SELAKYD324C/graph.json","fetch_events":"https://pith.science/api/pith-number/UZ62NATTLZXLCT7SELAKYD324C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C/action/storage_attestation","attest_author":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C/action/author_attestation","sign_citation":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C/action/citation_signature","submit_replication":"https://pith.science/pith/UZ62NATTLZXLCT7SELAKYD324C/action/replication_record"}},"created_at":"2026-06-23T01:11:58.456513+00:00","updated_at":"2026-06-23T01:11:58.456513+00:00"}