{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:56GWHSSX22L4FBE6S7D3WLCK2W","short_pith_number":"pith:56GWHSSX","schema_version":"1.0","canonical_sha256":"ef8d63ca57d697c2849e97c7bb2c4ad5be7da783abc59f60446a80065f37b7c0","source":{"kind":"arxiv","id":"2605.12386","version":2},"attestation_state":"computed","paper":{"title":"SafeManip: A Property-Driven Benchmark for Temporal Safety Evaluation in Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new benchmark shows that robotic manipulation policies often violate temporal safety rules even on tasks they complete successfully.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chengyue Huang, Khang Vo Huynh, Lu Feng, Sebastian Elbaum, Zsolt Kira","submitted_at":"2026-05-12T16:49:28Z","abstract_excerpt":"Robotic manipulation is typically evaluated by task success, but successful completion does not guarantee safe execution. Many safety failures are temporal: a robot may touch a clean surface after contamination or release an object before it is fully inside an enclosure. We introduce SafeManip, a property-driven benchmark to explicitly evaluate temporal safety properties in robotic manipulation, moving beyond prior evaluations that largely focus on task completion or per-state constraint violations. SafeManip defines reusable safety templates over finite executions using Linear Temporal Logic "},"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":true},"canonical_record":{"source":{"id":"2605.12386","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-12T16:49:28Z","cross_cats_sorted":[],"title_canon_sha256":"c33e6927696d000caf790804a5cdb6c955cff6d8f248b7bd48ea53f3c7078a90","abstract_canon_sha256":"e48b1d6e7014fefe724fb74a1bce032a262a5f70c8fb634c1c9da864a8b24a10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T02:09:30.757517Z","signature_b64":"gFhOLu1lIB7IicOmvjuHaI6erPoe1sM8xlPQKefx9FmgsUUWzI0Wzw6duR9vF6M9mcXkhyBImMTkO/CqwkyYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef8d63ca57d697c2849e97c7bb2c4ad5be7da783abc59f60446a80065f37b7c0","last_reissued_at":"2026-06-11T02:09:30.756267Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T02:09:30.756267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafeManip: A Property-Driven Benchmark for Temporal Safety Evaluation in Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new benchmark shows that robotic manipulation policies often violate temporal safety rules even on tasks they complete successfully.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chengyue Huang, Khang Vo Huynh, Lu Feng, Sebastian Elbaum, Zsolt Kira","submitted_at":"2026-05-12T16:49:28Z","abstract_excerpt":"Robotic manipulation is typically evaluated by task success, but successful completion does not guarantee safe execution. Many safety failures are temporal: a robot may touch a clean surface after contamination or release an object before it is fully inside an enclosure. We introduce SafeManip, a property-driven benchmark to explicitly evaluate temporal safety properties in robotic manipulation, moving beyond prior evaluations that largely focus on task completion or per-state constraint violations. SafeManip defines reusable safety templates over finite executions using Linear Temporal Logic "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Results show that even strong models often behave unsafely. Task-success gains do not reliably translate into safer execution: many successful rollouts remain unsafe, while longer-horizon or more complex tasks expose more violations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The LTLf safety templates and the mapping from observed rollouts to symbolic predicate traces accurately capture all relevant temporal safety properties without introducing false positives or missing critical real-world constraints.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SafeManip is a new benchmark that applies LTLf monitors to assess temporal safety properties across eight categories in robotic manipulation, demonstrating that task success frequently fails to ensure safe execution in vision-language-action policies.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new benchmark shows that robotic manipulation policies often violate temporal safety rules even on tasks they complete successfully.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0a1876392ab6438af818d0cf487a218824735b37fcc5b8a4363a41c00fd095a0"},"source":{"id":"2605.12386","kind":"arxiv","version":2},"verdict":{"id":"850d389d-b100-40ee-8ba1-39779118c924","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T03:36:05.803212Z","strongest_claim":"Results show that even strong models often behave unsafely. Task-success gains do not reliably translate into safer execution: many successful rollouts remain unsafe, while longer-horizon or more complex tasks expose more violations.","one_line_summary":"SafeManip is a new benchmark that applies LTLf monitors to assess temporal safety properties across eight categories in robotic manipulation, demonstrating that task success frequently fails to ensure safe execution in vision-language-action policies.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The LTLf safety templates and the mapping from observed rollouts to symbolic predicate traces accurately capture all relevant temporal safety properties without introducing false positives or missing critical real-world constraints.","pith_extraction_headline":"A new benchmark shows that robotic manipulation policies often violate temporal safety rules even on tasks they complete successfully."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.12386/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-26T14:40:19.643466Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T13:31:25.053122Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T09:46:22.567775Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:41:58.221082Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5887839b98fc958103d3559f742d458d8d827d2aa36504639bc88d0cb4f5c9e2"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"224f6469a73e6cb72e5afe6c57d5a00029b466606582210e56e7e21df4e900bc"},"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":"2605.12386","created_at":"2026-06-11T02:09:30.756445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12386v2","created_at":"2026-06-11T02:09:30.756445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12386","created_at":"2026-06-11T02:09:30.756445+00:00"},{"alias_kind":"pith_short_12","alias_value":"56GWHSSX22L4","created_at":"2026-06-11T02:09:30.756445+00:00"},{"alias_kind":"pith_short_16","alias_value":"56GWHSSX22L4FBE6","created_at":"2026-06-11T02:09:30.756445+00:00"},{"alias_kind":"pith_short_8","alias_value":"56GWHSSX","created_at":"2026-06-11T02:09:30.756445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W","json":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W.json","graph_json":"https://pith.science/api/pith-number/56GWHSSX22L4FBE6S7D3WLCK2W/graph.json","events_json":"https://pith.science/api/pith-number/56GWHSSX22L4FBE6S7D3WLCK2W/events.json","paper":"https://pith.science/paper/56GWHSSX"},"agent_actions":{"view_html":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W","download_json":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W.json","view_paper":"https://pith.science/paper/56GWHSSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12386&json=true","fetch_graph":"https://pith.science/api/pith-number/56GWHSSX22L4FBE6S7D3WLCK2W/graph.json","fetch_events":"https://pith.science/api/pith-number/56GWHSSX22L4FBE6S7D3WLCK2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W/action/storage_attestation","attest_author":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W/action/author_attestation","sign_citation":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W/action/citation_signature","submit_replication":"https://pith.science/pith/56GWHSSX22L4FBE6S7D3WLCK2W/action/replication_record"}},"created_at":"2026-06-11T02:09:30.756445+00:00","updated_at":"2026-06-11T02:09:30.756445+00:00"}