{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H2XJOWSCZF62O7RSMAPB4VSDDM","short_pith_number":"pith:H2XJOWSC","schema_version":"1.0","canonical_sha256":"3eae975a42c97da77e32601e1e56431b113dd6a840964d5317df1bc36ea3dc98","source":{"kind":"arxiv","id":"2412.09989","version":1},"attestation_state":"computed","paper":{"title":"One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Albert Lin, Shuang Peng, Somil Bansal","submitted_at":"2024-12-13T09:21:02Z","abstract_excerpt":"As learning-based methods for legged robots rapidly grow in popularity, it is important that we can provide safety assurances efficiently across different controllers and environments. Existing works either rely on a priori knowledge of the environment and safety constraints to ensure system safety or provide assurances for a specific locomotion policy. To address these limitations, we propose an observation-conditioned reachability-based (OCR) safety-filter framework. Our key idea is to use an OCR value network (OCR-VN) that predicts the optimal control-theoretic safety value function for new"},"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":"2412.09989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-13T09:21:02Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"28568c2e7d2fb9bde3a5c85270bf8184a21ce6583d49ab46c0c180b2fb966fee","abstract_canon_sha256":"de607859716cfb0fadf49b97325f036e25f9b15e90e07ef7ecada4baf1ac8444"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:45.037464Z","signature_b64":"uwhqwC80cBK8NPd6cHPt2I2k/dS8StFt3PTpwZwV/f4n0oVUjp1EQlMQ7nXSc7r6xPYE5hSe9t28RvltZ8P3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eae975a42c97da77e32601e1e56431b113dd6a840964d5317df1bc36ea3dc98","last_reissued_at":"2026-07-05T09:48:45.036969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:45.036969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Albert Lin, Shuang Peng, Somil Bansal","submitted_at":"2024-12-13T09:21:02Z","abstract_excerpt":"As learning-based methods for legged robots rapidly grow in popularity, it is important that we can provide safety assurances efficiently across different controllers and environments. Existing works either rely on a priori knowledge of the environment and safety constraints to ensure system safety or provide assurances for a specific locomotion policy. To address these limitations, we propose an observation-conditioned reachability-based (OCR) safety-filter framework. Our key idea is to use an OCR value network (OCR-VN) that predicts the optimal control-theoretic safety value function for new"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09989","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/2412.09989/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":"2412.09989","created_at":"2026-07-05T09:48:45.037028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09989v1","created_at":"2026-07-05T09:48:45.037028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09989","created_at":"2026-07-05T09:48:45.037028+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2XJOWSCZF62","created_at":"2026-07-05T09:48:45.037028+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2XJOWSCZF62O7RS","created_at":"2026-07-05T09:48:45.037028+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2XJOWSC","created_at":"2026-07-05T09:48:45.037028+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.13727","citing_title":"From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18482","citing_title":"Safe Control using Learned Safety Filters and Adaptive Conformal Inference","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM","json":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM.json","graph_json":"https://pith.science/api/pith-number/H2XJOWSCZF62O7RSMAPB4VSDDM/graph.json","events_json":"https://pith.science/api/pith-number/H2XJOWSCZF62O7RSMAPB4VSDDM/events.json","paper":"https://pith.science/paper/H2XJOWSC"},"agent_actions":{"view_html":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM","download_json":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM.json","view_paper":"https://pith.science/paper/H2XJOWSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09989&json=true","fetch_graph":"https://pith.science/api/pith-number/H2XJOWSCZF62O7RSMAPB4VSDDM/graph.json","fetch_events":"https://pith.science/api/pith-number/H2XJOWSCZF62O7RSMAPB4VSDDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM/action/storage_attestation","attest_author":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM/action/author_attestation","sign_citation":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM/action/citation_signature","submit_replication":"https://pith.science/pith/H2XJOWSCZF62O7RSMAPB4VSDDM/action/replication_record"}},"created_at":"2026-07-05T09:48:45.037028+00:00","updated_at":"2026-07-05T09:48:45.037028+00:00"}