{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T2LJMYQ7HAUAVPVDWW7QCNI5XK","short_pith_number":"pith:T2LJMYQ7","schema_version":"1.0","canonical_sha256":"9e9696621f38280abea3b5bf01351dbabeddee6192f9c7771a45a5ddadf00278","source":{"kind":"arxiv","id":"2602.01962","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Off-Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arip Asadulaev, Dmitry Dylov, Fakhri Karray, Maksim Bobrin, Martin Takac, Salem Lahlou","submitted_at":"2026-02-02T11:06:31Z","abstract_excerpt":"Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function overestimation bias. These issues become even more noticeable in zero-shot reinforcement learning, where an agent trained on reward-free data must adapt to new tasks at test time without additional training. In this work, we address the off-policy problem in a zero-shot setting by discovering a theoretical connection of successor measures to stationary density ratio"},"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":"2602.01962","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T11:06:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fd7482d2d777af103abcc99bcf4b0e9021eca130f837302c79d48513307e298","abstract_canon_sha256":"a4ca5826fc7b6dd1b9d7bbe967473a6410e88721ad6774a4fb8fa662c205aa11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:41.886011Z","signature_b64":"T7tQda4XtAf5LoQ3IfXr1G7NqIXDZwuPtxjhmMOHQrfViP+QfWHCc2cvJzwpH/UG7KDPSLtXX8jjYEsLQ3TnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e9696621f38280abea3b5bf01351dbabeddee6192f9c7771a45a5ddadf00278","last_reissued_at":"2026-06-02T01:03:41.885492Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:41.885492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Off-Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arip Asadulaev, Dmitry Dylov, Fakhri Karray, Maksim Bobrin, Martin Takac, Salem Lahlou","submitted_at":"2026-02-02T11:06:31Z","abstract_excerpt":"Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function overestimation bias. These issues become even more noticeable in zero-shot reinforcement learning, where an agent trained on reward-free data must adapt to new tasks at test time without additional training. In this work, we address the off-policy problem in a zero-shot setting by discovering a theoretical connection of successor measures to stationary density ratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01962","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/2602.01962/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":"2602.01962","created_at":"2026-06-02T01:03:41.885569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01962v2","created_at":"2026-06-02T01:03:41.885569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01962","created_at":"2026-06-02T01:03:41.885569+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2LJMYQ7HAUA","created_at":"2026-06-02T01:03:41.885569+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2LJMYQ7HAUAVPVD","created_at":"2026-06-02T01:03:41.885569+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2LJMYQ7","created_at":"2026-06-02T01:03:41.885569+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.21707","citing_title":"Zero-shot adaptation to order book dynamics","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK","json":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK.json","graph_json":"https://pith.science/api/pith-number/T2LJMYQ7HAUAVPVDWW7QCNI5XK/graph.json","events_json":"https://pith.science/api/pith-number/T2LJMYQ7HAUAVPVDWW7QCNI5XK/events.json","paper":"https://pith.science/paper/T2LJMYQ7"},"agent_actions":{"view_html":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK","download_json":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK.json","view_paper":"https://pith.science/paper/T2LJMYQ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01962&json=true","fetch_graph":"https://pith.science/api/pith-number/T2LJMYQ7HAUAVPVDWW7QCNI5XK/graph.json","fetch_events":"https://pith.science/api/pith-number/T2LJMYQ7HAUAVPVDWW7QCNI5XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/action/storage_attestation","attest_author":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/action/author_attestation","sign_citation":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/action/citation_signature","submit_replication":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/action/replication_record"}},"created_at":"2026-06-02T01:03:41.885569+00:00","updated_at":"2026-06-02T01:03:41.885569+00:00"}