{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IVTUGNSHZ5OUORWT7PYHWCJD43","short_pith_number":"pith:IVTUGNSH","schema_version":"1.0","canonical_sha256":"4567433647cf5d4746d3fbf07b0923e6d41dfec66e78d73ddb56016a8ee3d87d","source":{"kind":"arxiv","id":"2605.31196","version":1},"attestation_state":"computed","paper":{"title":"Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jun Wang, Xiaohao Xu, Xiaonan Huang","submitted_at":"2026-05-29T12:04:38Z","abstract_excerpt":"Safe human--robot collaboration requires more than visual description: a monitor must determine whether the robot body is safely separated, already colliding with the scene or a person, or about to collide. We call this capability collision grounding: binding visual observations to robot body geometry, camera viewpoint, scene layout, human proximity, and temporal motion in order to infer present and imminent contact. We introduce TouchSafeBench, a physics-grounded benchmark for evaluating collision grounding in vision-language models (VLMs). Built in Habitat~3.0, TouchSafeBench contains 2,940 "},"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":"2605.31196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T12:04:38Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"7a755c29393fe3380e823e49bdbef29acc4a85df2a06348e5f1a593aeb0e1274","abstract_canon_sha256":"5cf05d31d0437024ac00b147b046306cf2a5a2252f2c6440df3ec62f15163343"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:03.383685Z","signature_b64":"9605/rHivAVxlM6IiInlqdNSbajE/9KuZT2iD9o8Y34wqI/YWdlh3XbhLQzUeVE1JE/h32J2PeDDXskHJPPDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4567433647cf5d4746d3fbf07b0923e6d41dfec66e78d73ddb56016a8ee3d87d","last_reissued_at":"2026-06-01T01:04:03.383112Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:03.383112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.CV","authors_text":"Jun Wang, Xiaohao Xu, Xiaonan Huang","submitted_at":"2026-05-29T12:04:38Z","abstract_excerpt":"Safe human--robot collaboration requires more than visual description: a monitor must determine whether the robot body is safely separated, already colliding with the scene or a person, or about to collide. We call this capability collision grounding: binding visual observations to robot body geometry, camera viewpoint, scene layout, human proximity, and temporal motion in order to infer present and imminent contact. We introduce TouchSafeBench, a physics-grounded benchmark for evaluating collision grounding in vision-language models (VLMs). Built in Habitat~3.0, TouchSafeBench contains 2,940 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31196","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/2605.31196/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":"2605.31196","created_at":"2026-06-01T01:04:03.383186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31196v1","created_at":"2026-06-01T01:04:03.383186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31196","created_at":"2026-06-01T01:04:03.383186+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVTUGNSHZ5OU","created_at":"2026-06-01T01:04:03.383186+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVTUGNSHZ5OUORWT","created_at":"2026-06-01T01:04:03.383186+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVTUGNSH","created_at":"2026-06-01T01:04:03.383186+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/IVTUGNSHZ5OUORWT7PYHWCJD43","json":"https://pith.science/pith/IVTUGNSHZ5OUORWT7PYHWCJD43.json","graph_json":"https://pith.science/api/pith-number/IVTUGNSHZ5OUORWT7PYHWCJD43/graph.json","events_json":"https://pith.science/api/pith-number/IVTUGNSHZ5OUORWT7PYHWCJD43/events.json","paper":"https://pith.science/paper/IVTUGNSH"},"agent_actions":{"view_html":"https://pith.science/pith/IVTUGNSHZ5OUORWT7PYHWCJD43","download_json":"https://pith.science/pith/IVTUGNSHZ5OUORWT7PYHWCJD43.json","view_paper":"https://pith.science/paper/IVTUGNSH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31196&json=true","fetch_graph":"https://pith.science/api/pith-number/IVTUGNSHZ5OUORWT7PYHWCJD43/graph.json","fetch_events":"https://pith.science/api/pith-number/IVTUGNSHZ5OUORWT7PYHWCJD43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVTUGNSHZ5OUORWT7PYHWCJD43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVTUGNSHZ5OUORWT7PYHWCJD43/action/storage_attestation","attest_author":"https://pith.science/pith/IVTUGNSHZ5OUORWT7PYHWCJD43/action/author_attestation","sign_citation":"https://pith.science/pith/IVTUGNSHZ5OUORWT7PYHWCJD43/action/citation_signature","submit_replication":"https://pith.science/pith/IVTUGNSHZ5OUORWT7PYHWCJD43/action/replication_record"}},"created_at":"2026-06-01T01:04:03.383186+00:00","updated_at":"2026-06-01T01:04:03.383186+00:00"}