{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NXJX3DTNFGVCLPP2ZJOVJBTT3M","short_pith_number":"pith:NXJX3DTN","schema_version":"1.0","canonical_sha256":"6dd37d8e6d29aa25bdfaca5d548673db37e4b44cd6d80d1801ef1214993d8e3b","source":{"kind":"arxiv","id":"2501.18086","version":1},"attestation_state":"computed","paper":{"title":"DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Seung-Woo Seo, Se-Wook Yoo","submitted_at":"2025-01-30T01:56:07Z","abstract_excerpt":"Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent challenge. Recent research highlights the potential of leveraging pre-acquired task-agnostic knowledge to enhance both safety and sample efficiency in related tasks. Building on this insight, we propose a novel method to learn shared constraint distributions across multiple tasks. Our approach identifies the shared constraints through imitation learning and "},"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":"2501.18086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T01:56:07Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"7eec8bedbe091568a25dfc135dfa4e7b7ee1f7e1db1c2f693f6bc29176ef964f","abstract_canon_sha256":"a5ff4eec7b68d2355156df513bcc166c8dc7750c6486aa5a0df94aaf88536735"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:06.803427Z","signature_b64":"pBzA92GQpKOHPAURfJDKWKCAAzIICoM0Xv2ggEwfexlQTSWHK0HH08QEJx+HPMphw5ZSE9J050yGxKdnpmH8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dd37d8e6d29aa25bdfaca5d548673db37e4b44cd6d80d1801ef1214993d8e3b","last_reissued_at":"2026-07-05T10:07:06.802993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:06.802993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIAL: Distribution-Informed Adaptive Learning of Multi-Task Constraints for Safety-Critical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Seung-Woo Seo, Se-Wook Yoo","submitted_at":"2025-01-30T01:56:07Z","abstract_excerpt":"Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent challenge. Recent research highlights the potential of leveraging pre-acquired task-agnostic knowledge to enhance both safety and sample efficiency in related tasks. Building on this insight, we propose a novel method to learn shared constraint distributions across multiple tasks. Our approach identifies the shared constraints through imitation learning and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18086","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/2501.18086/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":"2501.18086","created_at":"2026-07-05T10:07:06.803050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18086v1","created_at":"2026-07-05T10:07:06.803050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18086","created_at":"2026-07-05T10:07:06.803050+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXJX3DTNFGVC","created_at":"2026-07-05T10:07:06.803050+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXJX3DTNFGVCLPP2","created_at":"2026-07-05T10:07:06.803050+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXJX3DTN","created_at":"2026-07-05T10:07:06.803050+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/NXJX3DTNFGVCLPP2ZJOVJBTT3M","json":"https://pith.science/pith/NXJX3DTNFGVCLPP2ZJOVJBTT3M.json","graph_json":"https://pith.science/api/pith-number/NXJX3DTNFGVCLPP2ZJOVJBTT3M/graph.json","events_json":"https://pith.science/api/pith-number/NXJX3DTNFGVCLPP2ZJOVJBTT3M/events.json","paper":"https://pith.science/paper/NXJX3DTN"},"agent_actions":{"view_html":"https://pith.science/pith/NXJX3DTNFGVCLPP2ZJOVJBTT3M","download_json":"https://pith.science/pith/NXJX3DTNFGVCLPP2ZJOVJBTT3M.json","view_paper":"https://pith.science/paper/NXJX3DTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18086&json=true","fetch_graph":"https://pith.science/api/pith-number/NXJX3DTNFGVCLPP2ZJOVJBTT3M/graph.json","fetch_events":"https://pith.science/api/pith-number/NXJX3DTNFGVCLPP2ZJOVJBTT3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXJX3DTNFGVCLPP2ZJOVJBTT3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXJX3DTNFGVCLPP2ZJOVJBTT3M/action/storage_attestation","attest_author":"https://pith.science/pith/NXJX3DTNFGVCLPP2ZJOVJBTT3M/action/author_attestation","sign_citation":"https://pith.science/pith/NXJX3DTNFGVCLPP2ZJOVJBTT3M/action/citation_signature","submit_replication":"https://pith.science/pith/NXJX3DTNFGVCLPP2ZJOVJBTT3M/action/replication_record"}},"created_at":"2026-07-05T10:07:06.803050+00:00","updated_at":"2026-07-05T10:07:06.803050+00:00"}