{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4SBNUUQ5UQRSOVL3TQVIMLBT2Q","short_pith_number":"pith:4SBNUUQ5","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"},"canonical_sha256":"e482da521da42327557b9c2a862c33d427757ac3d128631aefe4d465afc29c8a","source":{"kind":"arxiv","id":"2505.24257","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24257","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24257v1","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24257","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"pith_short_12","alias_value":"4SBNUUQ5UQRS","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"pith_short_16","alias_value":"4SBNUUQ5UQRSOVL3","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"pith_short_8","alias_value":"4SBNUUQ5","created_at":"2026-07-05T11:12:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4SBNUUQ5UQRSOVL3TQVIMLBT2Q","target":"record","payload":{"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"},"canonical_sha256":"e482da521da42327557b9c2a862c33d427757ac3d128631aefe4d465afc29c8a","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"},"source_kind":"arxiv","source_id":"2505.24257","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IqkIz8+j8nj7gRaQ+8AxdikyzngxpW5YZCmOR6/slB7nGMmC+fG9Pqw62LOalem75m/ktbdkA+IgCfFWgPubDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:12:33.590379Z"},"content_sha256":"d4b2b9de59d91dbfafacbafa45b376e1ba4ff519814154d56e5a5d763dcd8459","schema_version":"1.0","event_id":"sha256:d4b2b9de59d91dbfafacbafa45b376e1ba4ff519814154d56e5a5d763dcd8459"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4SBNUUQ5UQRSOVL3TQVIMLBT2Q","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pEMGPu9pY5HCL/xi1kqaRSYoW4boxW+7bAiLo/f69n2j98UQtRgF6O2IeM7XL6SkdMyRhevU6qWU0EaqS78+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T05:12:33.590955Z"},"content_sha256":"0cfb977fefa2bf83c595317bbab7b44d093839b7f18487ae779a518c95cf8f15","schema_version":"1.0","event_id":"sha256:0cfb977fefa2bf83c595317bbab7b44d093839b7f18487ae779a518c95cf8f15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/bundle.json","state_url":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T05:12:33Z","links":{"resolver":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q","bundle":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/bundle.json","state":"https://pith.science/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4SBNUUQ5UQRSOVL3TQVIMLBT2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4SBNUUQ5UQRSOVL3TQVIMLBT2Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"34b4caf705358c183a71d58a7112b81ff2538b1704e035ec69ad72ec24493cd8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T06:32:26Z","title_canon_sha256":"abe0f082f57b5016740c94e07366e2e77c00823002e9cdd54ed5c8ae32833253"},"schema_version":"1.0","source":{"id":"2505.24257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24257","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24257v1","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24257","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"pith_short_12","alias_value":"4SBNUUQ5UQRS","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"pith_short_16","alias_value":"4SBNUUQ5UQRSOVL3","created_at":"2026-07-05T11:12:45Z"},{"alias_kind":"pith_short_8","alias_value":"4SBNUUQ5","created_at":"2026-07-05T11:12:45Z"}],"graph_snapshots":[{"event_id":"sha256:0cfb977fefa2bf83c595317bbab7b44d093839b7f18487ae779a518c95cf8f15","target":"graph","created_at":"2026-07-05T11:12:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.24257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Andrew D. Wilson, Balasaravanan Thoravi Kumaravel, Gabriel Sarch, Sahithya Ravi, Vibhav Vineet","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T06:32:26Z","title":"Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24257","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d4b2b9de59d91dbfafacbafa45b376e1ba4ff519814154d56e5a5d763dcd8459","target":"record","created_at":"2026-07-05T11:12:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"34b4caf705358c183a71d58a7112b81ff2538b1704e035ec69ad72ec24493cd8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-30T06:32:26Z","title_canon_sha256":"abe0f082f57b5016740c94e07366e2e77c00823002e9cdd54ed5c8ae32833253"},"schema_version":"1.0","source":{"id":"2505.24257","kind":"arxiv","version":1}},"canonical_sha256":"e482da521da42327557b9c2a862c33d427757ac3d128631aefe4d465afc29c8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e482da521da42327557b9c2a862c33d427757ac3d128631aefe4d465afc29c8a","first_computed_at":"2026-07-05T11:12:45.325529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:45.325529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ULT/Z6Aflf44yXf7Zr22XL94XhNzddRljYQIJnRZ8aIVqT1dYh6KZ3NopIHlYvy9gZsVse+/OWU6zHjZCTFJAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:45.326011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4b2b9de59d91dbfafacbafa45b376e1ba4ff519814154d56e5a5d763dcd8459","sha256:0cfb977fefa2bf83c595317bbab7b44d093839b7f18487ae779a518c95cf8f15"],"state_sha256":"85ae9672d12515b1dc19c8b2b264d31509bddb8605abc4880d2631bf43560c0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IClI2z0z3lHRYpjT+34m+7svqT/olvEBSdqBorYH8YvfIctvnqNCdScyTZxrEVncoXaScpaMaoAkufepCOfnAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T05:12:33.613963Z","bundle_sha256":"977258eca4fabdc7e48a9a248bd7ac56db3e418e64d8c857f276dbfe1613a26b"}}