{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XYGTZ5DKY3SE7FKAPGONLXXJNK","short_pith_number":"pith:XYGTZ5DK","schema_version":"1.0","canonical_sha256":"be0d3cf46ac6e44f9540799cd5dee96a98dfccf18761546548a2e1e56c466c6d","source":{"kind":"arxiv","id":"2602.23280","version":2},"attestation_state":"computed","paper":{"title":"Mollified Value Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Aniket Bera, Damon Conover, Hrishikesh Viswanath, Juanwu Lu, Mihir Chauhan, S. Talha Bukhari, Ziran Wang","submitted_at":"2026-02-26T17:53:46Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static datasets, but accurate value estimation remains challenging under limited state-action coverage. Existing physics-informed approaches address this by imposing pointwise distance-like geometric constraints derived from Hamilton--Jacobi--Bellman (HJB) optimality principles, often through first-order partial differential equations such as the Eikonal equation. However, enforcing local consistency through explicit differential structure can become unstable in complex, high-dimensional environments. Ou"},"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":"2602.23280","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-26T17:53:46Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"d037061d616cd9c70d7afdec658b5cd4eae59decc380ee86ef37f8976e19be43","abstract_canon_sha256":"a8d40ccfe4f06137e75520d0c9f0322aad10cdd57b0c671099623b8d1696d370"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:35.892208Z","signature_b64":"Em+lezTCFjHE3AnN8oF9CiJXgKlYwBT6J14mm10xGBn52mKz2ukinjnWegfMca5NNFvQ6gN50YHP60bqX88RAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be0d3cf46ac6e44f9540799cd5dee96a98dfccf18761546548a2e1e56c466c6d","last_reissued_at":"2026-06-01T02:03:35.890766Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:35.890766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mollified Value Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Aniket Bera, Damon Conover, Hrishikesh Viswanath, Juanwu Lu, Mihir Chauhan, S. Talha Bukhari, Ziran Wang","submitted_at":"2026-02-26T17:53:46Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static datasets, but accurate value estimation remains challenging under limited state-action coverage. Existing physics-informed approaches address this by imposing pointwise distance-like geometric constraints derived from Hamilton--Jacobi--Bellman (HJB) optimality principles, often through first-order partial differential equations such as the Eikonal equation. However, enforcing local consistency through explicit differential structure can become unstable in complex, high-dimensional environments. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23280","kind":"arxiv","version":2},"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/2602.23280/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":"2602.23280","created_at":"2026-06-01T02:03:35.891029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23280v2","created_at":"2026-06-01T02:03:35.891029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23280","created_at":"2026-06-01T02:03:35.891029+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYGTZ5DKY3SE","created_at":"2026-06-01T02:03:35.891029+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYGTZ5DKY3SE7FKA","created_at":"2026-06-01T02:03:35.891029+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYGTZ5DK","created_at":"2026-06-01T02:03:35.891029+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/XYGTZ5DKY3SE7FKAPGONLXXJNK","json":"https://pith.science/pith/XYGTZ5DKY3SE7FKAPGONLXXJNK.json","graph_json":"https://pith.science/api/pith-number/XYGTZ5DKY3SE7FKAPGONLXXJNK/graph.json","events_json":"https://pith.science/api/pith-number/XYGTZ5DKY3SE7FKAPGONLXXJNK/events.json","paper":"https://pith.science/paper/XYGTZ5DK"},"agent_actions":{"view_html":"https://pith.science/pith/XYGTZ5DKY3SE7FKAPGONLXXJNK","download_json":"https://pith.science/pith/XYGTZ5DKY3SE7FKAPGONLXXJNK.json","view_paper":"https://pith.science/paper/XYGTZ5DK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23280&json=true","fetch_graph":"https://pith.science/api/pith-number/XYGTZ5DKY3SE7FKAPGONLXXJNK/graph.json","fetch_events":"https://pith.science/api/pith-number/XYGTZ5DKY3SE7FKAPGONLXXJNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYGTZ5DKY3SE7FKAPGONLXXJNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYGTZ5DKY3SE7FKAPGONLXXJNK/action/storage_attestation","attest_author":"https://pith.science/pith/XYGTZ5DKY3SE7FKAPGONLXXJNK/action/author_attestation","sign_citation":"https://pith.science/pith/XYGTZ5DKY3SE7FKAPGONLXXJNK/action/citation_signature","submit_replication":"https://pith.science/pith/XYGTZ5DKY3SE7FKAPGONLXXJNK/action/replication_record"}},"created_at":"2026-06-01T02:03:35.891029+00:00","updated_at":"2026-06-01T02:03:35.891029+00:00"}