{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EEA4VGTISJI5MZRLUF77ZD6QUS","short_pith_number":"pith:EEA4VGTI","schema_version":"1.0","canonical_sha256":"2101ca9a689251d6662ba17ffc8fd0a488e4418b0b6df003aa35cfaae01d75ed","source":{"kind":"arxiv","id":"2510.01483","version":3},"attestation_state":"computed","paper":{"title":"Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Arthur Nigmatzyanov, Dmitrii Nalberskii, Gonzalo Ferrer, Mohamad Al Mdfaa, Sergey Zagoruyko, Svetlana Lukina, Timur Akhtyamov","submitted_at":"2025-10-01T21:53:44Z","abstract_excerpt":"Vision-language models (VLMs) demonstrate strong image-level scene understanding, but reasoning over long egocentric video remains costly: because VLMs maintain no persistent memory or explicit spatial representation, all sampled frames must be re-processed for every new query. We present VL-KnG, a training-free framework that constructs spatiotemporal knowledge graphs from monocular egocentric video, bridging fine-grained scene graphs and global topological graphs without 3D reconstruction. VL-KnG processes video in chunks, maintains persistent object identities via large language model (LLM)"},"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":"2510.01483","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-10-01T21:53:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28016595ea8a49a8928e9e54ce52980df1c68caf100a8e4d9fd7c0cd0c5ab072","abstract_canon_sha256":"1c4c6d5303c149213a6134d6cce18b3d045f7c9180e497f577376942410ead85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:21:22.304598Z","signature_b64":"Cqf8Q6hAFWtUj3abZboyqopLJbZVPI/SXe+88jQVV5tPp/khAEjwoJLPaw+p2QHMZm/THvKId2q26WaY9MZ3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2101ca9a689251d6662ba17ffc8fd0a488e4418b0b6df003aa35cfaae01d75ed","last_reissued_at":"2026-07-21T02:21:22.303618Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:21:22.303618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatiotemporal Knowledge Graphs as Persistent Scene Memory for Embodied Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Arthur Nigmatzyanov, Dmitrii Nalberskii, Gonzalo Ferrer, Mohamad Al Mdfaa, Sergey Zagoruyko, Svetlana Lukina, Timur Akhtyamov","submitted_at":"2025-10-01T21:53:44Z","abstract_excerpt":"Vision-language models (VLMs) demonstrate strong image-level scene understanding, but reasoning over long egocentric video remains costly: because VLMs maintain no persistent memory or explicit spatial representation, all sampled frames must be re-processed for every new query. We present VL-KnG, a training-free framework that constructs spatiotemporal knowledge graphs from monocular egocentric video, bridging fine-grained scene graphs and global topological graphs without 3D reconstruction. VL-KnG processes video in chunks, maintains persistent object identities via large language model (LLM)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01483","kind":"arxiv","version":3},"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/2510.01483/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":"2510.01483","created_at":"2026-07-21T02:21:22.304043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.01483v3","created_at":"2026-07-21T02:21:22.304043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01483","created_at":"2026-07-21T02:21:22.304043+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEA4VGTISJI5","created_at":"2026-07-21T02:21:22.304043+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEA4VGTISJI5MZRL","created_at":"2026-07-21T02:21:22.304043+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEA4VGTI","created_at":"2026-07-21T02:21:22.304043+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/EEA4VGTISJI5MZRLUF77ZD6QUS","json":"https://pith.science/pith/EEA4VGTISJI5MZRLUF77ZD6QUS.json","graph_json":"https://pith.science/api/pith-number/EEA4VGTISJI5MZRLUF77ZD6QUS/graph.json","events_json":"https://pith.science/api/pith-number/EEA4VGTISJI5MZRLUF77ZD6QUS/events.json","paper":"https://pith.science/paper/EEA4VGTI"},"agent_actions":{"view_html":"https://pith.science/pith/EEA4VGTISJI5MZRLUF77ZD6QUS","download_json":"https://pith.science/pith/EEA4VGTISJI5MZRLUF77ZD6QUS.json","view_paper":"https://pith.science/paper/EEA4VGTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.01483&json=true","fetch_graph":"https://pith.science/api/pith-number/EEA4VGTISJI5MZRLUF77ZD6QUS/graph.json","fetch_events":"https://pith.science/api/pith-number/EEA4VGTISJI5MZRLUF77ZD6QUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEA4VGTISJI5MZRLUF77ZD6QUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEA4VGTISJI5MZRLUF77ZD6QUS/action/storage_attestation","attest_author":"https://pith.science/pith/EEA4VGTISJI5MZRLUF77ZD6QUS/action/author_attestation","sign_citation":"https://pith.science/pith/EEA4VGTISJI5MZRLUF77ZD6QUS/action/citation_signature","submit_replication":"https://pith.science/pith/EEA4VGTISJI5MZRLUF77ZD6QUS/action/replication_record"}},"created_at":"2026-07-21T02:21:22.304043+00:00","updated_at":"2026-07-21T02:21:22.304043+00:00"}