{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T2LJMYQ7HAUAVPVDWW7QCNI5XK","short_pith_number":"pith:T2LJMYQ7","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"},"canonical_sha256":"9e9696621f38280abea3b5bf01351dbabeddee6192f9c7771a45a5ddadf00278","source":{"kind":"arxiv","id":"2602.01962","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01962","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01962v2","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01962","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"T2LJMYQ7HAUA","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"T2LJMYQ7HAUAVPVD","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"T2LJMYQ7","created_at":"2026-06-02T01:03:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T2LJMYQ7HAUAVPVDWW7QCNI5XK","target":"record","payload":{"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"},"canonical_sha256":"9e9696621f38280abea3b5bf01351dbabeddee6192f9c7771a45a5ddadf00278","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"},"source_kind":"arxiv","source_id":"2602.01962","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kC5CHMV+F2DgtNvaedkrbKbqpavDKWZQRF8ulF093G5ja0pGr/sHEAFPNtBwNF+D0AmPO7EnCGg1oZNJvvrtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:37:29.548839Z"},"content_sha256":"4bef0570eba571c8d664a7ca62fc729a259474f0fd2e4a280103f4e013da8d53","schema_version":"1.0","event_id":"sha256:4bef0570eba571c8d664a7ca62fc729a259474f0fd2e4a280103f4e013da8d53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T2LJMYQ7HAUAVPVDWW7QCNI5XK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d56mXGfuPqjkxywawxzSbk0lExqnbb0x6a7ibl1YS9z6YLv2VYpW+yrL0Tnny1JX6kTZMulmb/9YhicxOzGNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:37:29.549213Z"},"content_sha256":"a8bde47342acfe4edde423ec68da4adecd39f8afb46f4b24b2060e81c56d03c4","schema_version":"1.0","event_id":"sha256:a8bde47342acfe4edde423ec68da4adecd39f8afb46f4b24b2060e81c56d03c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/bundle.json","state_url":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T14:37:29Z","links":{"resolver":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK","bundle":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/bundle.json","state":"https://pith.science/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T2LJMYQ7HAUAVPVDWW7QCNI5XK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T2LJMYQ7HAUAVPVDWW7QCNI5XK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a4ca5826fc7b6dd1b9d7bbe967473a6410e88721ad6774a4fb8fa662c205aa11","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T11:06:31Z","title_canon_sha256":"2fd7482d2d777af103abcc99bcf4b0e9021eca130f837302c79d48513307e298"},"schema_version":"1.0","source":{"id":"2602.01962","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.01962","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.01962v2","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01962","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"T2LJMYQ7HAUA","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"T2LJMYQ7HAUAVPVD","created_at":"2026-06-02T01:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"T2LJMYQ7","created_at":"2026-06-02T01:03:41Z"}],"graph_snapshots":[{"event_id":"sha256:a8bde47342acfe4edde423ec68da4adecd39f8afb46f4b24b2060e81c56d03c4","target":"graph","created_at":"2026-06-02T01:03:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.01962/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Arip Asadulaev, Dmitry Dylov, Fakhri Karray, Maksim Bobrin, Martin Takac, Salem Lahlou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T11:06:31Z","title":"Zero-Shot Off-Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01962","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4bef0570eba571c8d664a7ca62fc729a259474f0fd2e4a280103f4e013da8d53","target":"record","created_at":"2026-06-02T01:03:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a4ca5826fc7b6dd1b9d7bbe967473a6410e88721ad6774a4fb8fa662c205aa11","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T11:06:31Z","title_canon_sha256":"2fd7482d2d777af103abcc99bcf4b0e9021eca130f837302c79d48513307e298"},"schema_version":"1.0","source":{"id":"2602.01962","kind":"arxiv","version":2}},"canonical_sha256":"9e9696621f38280abea3b5bf01351dbabeddee6192f9c7771a45a5ddadf00278","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e9696621f38280abea3b5bf01351dbabeddee6192f9c7771a45a5ddadf00278","first_computed_at":"2026-06-02T01:03:41.885492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:41.885492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T7tQda4XtAf5LoQ3IfXr1G7NqIXDZwuPtxjhmMOHQrfViP+QfWHCc2cvJzwpH/UG7KDPSLtXX8jjYEsLQ3TnBg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:41.886011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.01962","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bef0570eba571c8d664a7ca62fc729a259474f0fd2e4a280103f4e013da8d53","sha256:a8bde47342acfe4edde423ec68da4adecd39f8afb46f4b24b2060e81c56d03c4"],"state_sha256":"ad3dad937908a1e64c94e52de4473255359a74335dfa8473461cfb1ccee04ecc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yizqUPJHEjneGOHwZeAVLuWuo4Y0eotKmXacW+gos5J3VpciWxP28LDzZO8lgS3eHQr3CWjIHfST9sk/W+MYDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:37:29.551229Z","bundle_sha256":"ca9360dd04f0f50cf20cf91d659f09de86e8616e433fb6ba7b7eec8b66d858d8"}}