{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5UXZDKHMGAJQAYIHYMADEF2XE","short_pith_number":"pith:F5UXZDKH","schema_version":"1.0","canonical_sha256":"2f697c8d4761809803083e180190bab9371c103f1e9d560390f768eb6e023cb5","source":{"kind":"arxiv","id":"2606.08666","version":1},"attestation_state":"computed","paper":{"title":"Language as a Sensor: Calibrated Spatial Belief Estimation in 3D Scenes from Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andreea Bobu, Aryan Naveen, Jason Xinyu Liu, Luca Carlone","submitted_at":"2026-06-07T15:17:25Z","abstract_excerpt":"Robots deployed in human-centric environments routinely receive natural-language descriptions of spatial information (\"I left my backpack on the table\") that reference parts of the world beyond their perceptual field of view. Traditional metric-semantic mapping ignores this signal, while off-the-shelf multimodal models remain limited in 3D spatial reasoning and are not directly amenable to fusion with other sensor modalities. To convert language observations into a calibrated spatial distribution, we train a Language Sensor Model (LSM) that maps each utterance and its scene-graph context to 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":"2606.08666","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-07T15:17:25Z","cross_cats_sorted":[],"title_canon_sha256":"71a5b32751f9b9ff1bafa30a209d86f8c546aad8149be7bf976bd6e8724fc135","abstract_canon_sha256":"ab36b026e3e1b79bfbd0ce583a84dc76ac5c8b1552f7d307636cb459ad41d647"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:43.177000Z","signature_b64":"Jp7W/Swcb2M7LYxJ3I8H2d9kvRyPPcd0YJZ2syaHKGXBcR/mizc5E9S3wrfmTChL+rKjri9+XqXYJqAObLqpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f697c8d4761809803083e180190bab9371c103f1e9d560390f768eb6e023cb5","last_reissued_at":"2026-06-09T01:05:43.176587Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:43.176587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language as a Sensor: Calibrated Spatial Belief Estimation in 3D Scenes from Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andreea Bobu, Aryan Naveen, Jason Xinyu Liu, Luca Carlone","submitted_at":"2026-06-07T15:17:25Z","abstract_excerpt":"Robots deployed in human-centric environments routinely receive natural-language descriptions of spatial information (\"I left my backpack on the table\") that reference parts of the world beyond their perceptual field of view. Traditional metric-semantic mapping ignores this signal, while off-the-shelf multimodal models remain limited in 3D spatial reasoning and are not directly amenable to fusion with other sensor modalities. To convert language observations into a calibrated spatial distribution, we train a Language Sensor Model (LSM) that maps each utterance and its scene-graph context to a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08666","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/2606.08666/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":"2606.08666","created_at":"2026-06-09T01:05:43.176651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08666v1","created_at":"2026-06-09T01:05:43.176651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08666","created_at":"2026-06-09T01:05:43.176651+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5UXZDKHMGAJ","created_at":"2026-06-09T01:05:43.176651+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5UXZDKHMGAJQAYI","created_at":"2026-06-09T01:05:43.176651+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5UXZDKH","created_at":"2026-06-09T01:05:43.176651+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/F5UXZDKHMGAJQAYIHYMADEF2XE","json":"https://pith.science/pith/F5UXZDKHMGAJQAYIHYMADEF2XE.json","graph_json":"https://pith.science/api/pith-number/F5UXZDKHMGAJQAYIHYMADEF2XE/graph.json","events_json":"https://pith.science/api/pith-number/F5UXZDKHMGAJQAYIHYMADEF2XE/events.json","paper":"https://pith.science/paper/F5UXZDKH"},"agent_actions":{"view_html":"https://pith.science/pith/F5UXZDKHMGAJQAYIHYMADEF2XE","download_json":"https://pith.science/pith/F5UXZDKHMGAJQAYIHYMADEF2XE.json","view_paper":"https://pith.science/paper/F5UXZDKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08666&json=true","fetch_graph":"https://pith.science/api/pith-number/F5UXZDKHMGAJQAYIHYMADEF2XE/graph.json","fetch_events":"https://pith.science/api/pith-number/F5UXZDKHMGAJQAYIHYMADEF2XE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5UXZDKHMGAJQAYIHYMADEF2XE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5UXZDKHMGAJQAYIHYMADEF2XE/action/storage_attestation","attest_author":"https://pith.science/pith/F5UXZDKHMGAJQAYIHYMADEF2XE/action/author_attestation","sign_citation":"https://pith.science/pith/F5UXZDKHMGAJQAYIHYMADEF2XE/action/citation_signature","submit_replication":"https://pith.science/pith/F5UXZDKHMGAJQAYIHYMADEF2XE/action/replication_record"}},"created_at":"2026-06-09T01:05:43.176651+00:00","updated_at":"2026-06-09T01:05:43.176651+00:00"}