{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5W7M3QST3JJKZZYA4H34IPVWZ6","short_pith_number":"pith:5W7M3QST","schema_version":"1.0","canonical_sha256":"edbecdc253da52ace700e1f7c43eb6cf8d1ba8eebd506c694d98792303e5de18","source":{"kind":"arxiv","id":"2607.16173","version":1},"attestation_state":"computed","paper":{"title":"Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ayushi Shakya, Dibyendu Ghosh","submitted_at":"2026-07-17T17:53:13Z","abstract_excerpt":"Open-vocabulary 3D maps let robots answer language queries about what and where, but they assume a static world and cannot answer queries about how scene elements behave. We introduce Vision-Language-Motion Maps (VLMM), an open-vocabulary, natural-language-queryable 3D map in which each element carries a fused motion attribute: a VLM/LLM semantic movability prior combined with geometrically observed cross-frame motion, together with a per-element uncertainty. Queries reduce to attribute filters that distinguish what has been seen to move, what could move but has not, and what stays still. On a"},"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":"2607.16173","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-17T17:53:13Z","cross_cats_sorted":[],"title_canon_sha256":"89625392b0e5a779252241cbfee429afb1ee7be1db11c96f8eed87f0018e94d1","abstract_canon_sha256":"9007185e4d895da138a4c7e0a86b8f79208e4c9c2ce7677c5d673b563874421d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T02:19:37.558243Z","signature_b64":"GpbiS9lZ/vJx1LiY6lhu/OzagphoiOOzZhj+9Qx0hhYi3OqX6vduanZ5Saelzh+dMihc/xf1R9Cnrji+oLaGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edbecdc253da52ace700e1f7c43eb6cf8d1ba8eebd506c694d98792303e5de18","last_reissued_at":"2026-07-20T02:19:37.557332Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T02:19:37.557332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ayushi Shakya, Dibyendu Ghosh","submitted_at":"2026-07-17T17:53:13Z","abstract_excerpt":"Open-vocabulary 3D maps let robots answer language queries about what and where, but they assume a static world and cannot answer queries about how scene elements behave. We introduce Vision-Language-Motion Maps (VLMM), an open-vocabulary, natural-language-queryable 3D map in which each element carries a fused motion attribute: a VLM/LLM semantic movability prior combined with geometrically observed cross-frame motion, together with a per-element uncertainty. Queries reduce to attribute filters that distinguish what has been seen to move, what could move but has not, and what stays still. On a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16173","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/2607.16173/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":"2607.16173","created_at":"2026-07-20T02:19:37.557771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16173v1","created_at":"2026-07-20T02:19:37.557771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16173","created_at":"2026-07-20T02:19:37.557771+00:00"},{"alias_kind":"pith_short_12","alias_value":"5W7M3QST3JJK","created_at":"2026-07-20T02:19:37.557771+00:00"},{"alias_kind":"pith_short_16","alias_value":"5W7M3QST3JJKZZYA","created_at":"2026-07-20T02:19:37.557771+00:00"},{"alias_kind":"pith_short_8","alias_value":"5W7M3QST","created_at":"2026-07-20T02:19:37.557771+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/5W7M3QST3JJKZZYA4H34IPVWZ6","json":"https://pith.science/pith/5W7M3QST3JJKZZYA4H34IPVWZ6.json","graph_json":"https://pith.science/api/pith-number/5W7M3QST3JJKZZYA4H34IPVWZ6/graph.json","events_json":"https://pith.science/api/pith-number/5W7M3QST3JJKZZYA4H34IPVWZ6/events.json","paper":"https://pith.science/paper/5W7M3QST"},"agent_actions":{"view_html":"https://pith.science/pith/5W7M3QST3JJKZZYA4H34IPVWZ6","download_json":"https://pith.science/pith/5W7M3QST3JJKZZYA4H34IPVWZ6.json","view_paper":"https://pith.science/paper/5W7M3QST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16173&json=true","fetch_graph":"https://pith.science/api/pith-number/5W7M3QST3JJKZZYA4H34IPVWZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/5W7M3QST3JJKZZYA4H34IPVWZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5W7M3QST3JJKZZYA4H34IPVWZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5W7M3QST3JJKZZYA4H34IPVWZ6/action/storage_attestation","attest_author":"https://pith.science/pith/5W7M3QST3JJKZZYA4H34IPVWZ6/action/author_attestation","sign_citation":"https://pith.science/pith/5W7M3QST3JJKZZYA4H34IPVWZ6/action/citation_signature","submit_replication":"https://pith.science/pith/5W7M3QST3JJKZZYA4H34IPVWZ6/action/replication_record"}},"created_at":"2026-07-20T02:19:37.557771+00:00","updated_at":"2026-07-20T02:19:37.557771+00:00"}