{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4SBNUUQ5UQRSOVL3TQVIMLBT2Q","short_pith_number":"pith:4SBNUUQ5","schema_version":"1.0","canonical_sha256":"e482da521da42327557b9c2a862c33d427757ac3d128631aefe4d465afc29c8a","source":{"kind":"arxiv","id":"2505.24257","version":1},"attestation_state":"computed","paper":{"title":"Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew D. Wilson, Balasaravanan Thoravi Kumaravel, Gabriel Sarch, Sahithya Ravi, Vibhav Vineet","submitted_at":"2025-05-30T06:32:26Z","abstract_excerpt":"An embodied AI assistant operating on egocentric video must integrate spatial cues across time - for instance, determining where an object A, glimpsed a few moments ago lies relative to an object B encountered later. We introduce Disjoint-3DQA , a generative QA benchmark that evaluates this ability of VLMs by posing questions about object pairs that are not co-visible in the same frame. We evaluated seven state-of-the-art VLMs and found that models lag behind human performance by 28%, with steeper declines in accuracy (60% to 30 %) as the temporal gap widens. Our analysis further reveals that "},"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":"2505.24257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T06:32:26Z","cross_cats_sorted":[],"title_canon_sha256":"abe0f082f57b5016740c94e07366e2e77c00823002e9cdd54ed5c8ae32833253","abstract_canon_sha256":"34b4caf705358c183a71d58a7112b81ff2538b1704e035ec69ad72ec24493cd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:45.326011Z","signature_b64":"ULT/Z6Aflf44yXf7Zr22XL94XhNzddRljYQIJnRZ8aIVqT1dYh6KZ3NopIHlYvy9gZsVse+/OWU6zHjZCTFJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e482da521da42327557b9c2a862c33d427757ac3d128631aefe4d465afc29c8a","last_reissued_at":"2026-07-05T11:12:45.325529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:45.325529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew D. Wilson, Balasaravanan Thoravi Kumaravel, Gabriel Sarch, Sahithya Ravi, Vibhav Vineet","submitted_at":"2025-05-30T06:32:26Z","abstract_excerpt":"An embodied AI assistant operating on egocentric video must integrate spatial cues across time - for instance, determining where an object A, glimpsed a few moments ago lies relative to an object B encountered later. We introduce Disjoint-3DQA , a generative QA benchmark that evaluates this ability of VLMs by posing questions about object pairs that are not co-visible in the same frame. We evaluated seven state-of-the-art VLMs and found that models lag behind human performance by 28%, with steeper declines in accuracy (60% to 30 %) as the temporal gap widens. Our analysis further reveals that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24257","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/2505.24257/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":"2505.24257","created_at":"2026-07-05T11:12:45.325587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24257v1","created_at":"2026-07-05T11:12:45.325587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24257","created_at":"2026-07-05T11:12:45.325587+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SBNUUQ5UQRS","created_at":"2026-07-05T11:12:45.325587+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SBNUUQ5UQRSOVL3","created_at":"2026-07-05T11:12:45.325587+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SBNUUQ5","created_at":"2026-07-05T11:12:45.325587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22409","citing_title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22409","citing_title":"SpaMEM: Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q","json":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q.json","graph_json":"https://pith.science/api/pith-number/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/graph.json","events_json":"https://pith.science/api/pith-number/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/events.json","paper":"https://pith.science/paper/4SBNUUQ5"},"agent_actions":{"view_html":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q","download_json":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q.json","view_paper":"https://pith.science/paper/4SBNUUQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24257&json=true","fetch_graph":"https://pith.science/api/pith-number/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/action/storage_attestation","attest_author":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/action/author_attestation","sign_citation":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/action/citation_signature","submit_replication":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/action/replication_record"}},"created_at":"2026-07-05T11:12:45.325587+00:00","updated_at":"2026-07-05T11:12:45.325587+00:00"}