{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MASMQGFR2HZZIDNR4CYC66Y5SL","short_pith_number":"pith:MASMQGFR","canonical_record":{"source":{"id":"2605.27834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T01:46:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"174e322ea0de8a1610d0c348cab6ed89f52bdf468349d8694ab0d9df34aeeeb1","abstract_canon_sha256":"1901a2a205841a36a10145a960575e9570e1038e830f2274579117ab742f8fe1"},"schema_version":"1.0"},"canonical_sha256":"6024c818b1d1f3940db1e0b02f7b1d92c5136a7f07d61fc1d1dd15c33fd2fe5b","source":{"kind":"arxiv","id":"2605.27834","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27834","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27834v1","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27834","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"MASMQGFR2HZZ","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"MASMQGFR2HZZIDNR","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"MASMQGFR","created_at":"2026-05-28T01:04:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MASMQGFR2HZZIDNR4CYC66Y5SL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T01:46:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"174e322ea0de8a1610d0c348cab6ed89f52bdf468349d8694ab0d9df34aeeeb1","abstract_canon_sha256":"1901a2a205841a36a10145a960575e9570e1038e830f2274579117ab742f8fe1"},"schema_version":"1.0"},"canonical_sha256":"6024c818b1d1f3940db1e0b02f7b1d92c5136a7f07d61fc1d1dd15c33fd2fe5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:49.951046Z","signature_b64":"TxbesPfs8AICQsnyPKlI3UDIOrA5nP2Pwcx5yo/m0kZwRUWpx7Oq4vdHT3ugBwnIgL68m3G+sH0O1cWSLwwOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6024c818b1d1f3940db1e0b02f7b1d92c5136a7f07d61fc1d1dd15c33fd2fe5b","last_reissued_at":"2026-05-28T01:04:49.950681Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:49.950681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27834","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SDalJ3D7Islia6c6+dlfkDCwjxRKsypruX4HbKIQSlgGURPG0ItCmOlh7mxcBIY4v+y6QjfyCjGKozvhcsX1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:56:42.551589Z"},"content_sha256":"751a6c53dc427f625effc196970b8b6a7e3a1e12ef93775bbd1ff03673584c70","schema_version":"1.0","event_id":"sha256:751a6c53dc427f625effc196970b8b6a7e3a1e12ef93775bbd1ff03673584c70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MASMQGFR2HZZIDNR4CYC66Y5SL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aur\\'elien Bibaut, Guang-Yuan Hao, Lars van der Laan, Nathan Kallus","submitted_at":"2026-05-27T01:46:20Z","abstract_excerpt":"We study the transfer of rewards learned using inverse reinforcement learning from expert demonstrations in one environment to reinforcement learning in a new, different environment. This arises naturally when demonstrations are collected in a controlled environment. We formulate the problem as a joint system of Bellman equations across the source and target environments and develop minimax estimators for the target soft-$q$-function. Whereas a sequential solution approach first estimates the source reward and then plugs it into the target control problem, a coupled approach solves the source "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27834","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/2605.27834/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":"2026-05-28T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zyKqncBDF42K8JKZg7kVUW9Mlix2PuC7P/rOoEuZtsPipsaDr0LKQuvT7BWOeOH3HSlw4cwsVLisgsXv8sXZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T07:56:42.551967Z"},"content_sha256":"ee3e2a78c48e5682a924d42fb25860c8f35ae11e5cd53269fe685a39874e729b","schema_version":"1.0","event_id":"sha256:ee3e2a78c48e5682a924d42fb25860c8f35ae11e5cd53269fe685a39874e729b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MASMQGFR2HZZIDNR4CYC66Y5SL/bundle.json","state_url":"https://pith.science/pith/MASMQGFR2HZZIDNR4CYC66Y5SL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MASMQGFR2HZZIDNR4CYC66Y5SL/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":"2026-06-02T07:56:42Z","links":{"resolver":"https://pith.science/pith/MASMQGFR2HZZIDNR4CYC66Y5SL","bundle":"https://pith.science/pith/MASMQGFR2HZZIDNR4CYC66Y5SL/bundle.json","state":"https://pith.science/pith/MASMQGFR2HZZIDNR4CYC66Y5SL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MASMQGFR2HZZIDNR4CYC66Y5SL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MASMQGFR2HZZIDNR4CYC66Y5SL","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":"1901a2a205841a36a10145a960575e9570e1038e830f2274579117ab742f8fe1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T01:46:20Z","title_canon_sha256":"174e322ea0de8a1610d0c348cab6ed89f52bdf468349d8694ab0d9df34aeeeb1"},"schema_version":"1.0","source":{"id":"2605.27834","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27834","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27834v1","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27834","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"MASMQGFR2HZZ","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"MASMQGFR2HZZIDNR","created_at":"2026-05-28T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"MASMQGFR","created_at":"2026-05-28T01:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:ee3e2a78c48e5682a924d42fb25860c8f35ae11e5cd53269fe685a39874e729b","target":"graph","created_at":"2026-05-28T01:04:49Z","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/2605.27834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the transfer of rewards learned using inverse reinforcement learning from expert demonstrations in one environment to reinforcement learning in a new, different environment. This arises naturally when demonstrations are collected in a controlled environment. We formulate the problem as a joint system of Bellman equations across the source and target environments and develop minimax estimators for the target soft-$q$-function. Whereas a sequential solution approach first estimates the source reward and then plugs it into the target control problem, a coupled approach solves the source ","authors_text":"Aur\\'elien Bibaut, Guang-Yuan Hao, Lars van der Laan, Nathan Kallus","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T01:46:20Z","title":"Reward Transfer from Inverse Reinforcement Learning: A Coupled Minimax Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27834","kind":"arxiv","version":1},"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":"sha256:751a6c53dc427f625effc196970b8b6a7e3a1e12ef93775bbd1ff03673584c70","target":"record","created_at":"2026-05-28T01:04:49Z","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":"1901a2a205841a36a10145a960575e9570e1038e830f2274579117ab742f8fe1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T01:46:20Z","title_canon_sha256":"174e322ea0de8a1610d0c348cab6ed89f52bdf468349d8694ab0d9df34aeeeb1"},"schema_version":"1.0","source":{"id":"2605.27834","kind":"arxiv","version":1}},"canonical_sha256":"6024c818b1d1f3940db1e0b02f7b1d92c5136a7f07d61fc1d1dd15c33fd2fe5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6024c818b1d1f3940db1e0b02f7b1d92c5136a7f07d61fc1d1dd15c33fd2fe5b","first_computed_at":"2026-05-28T01:04:49.950681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:49.950681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TxbesPfs8AICQsnyPKlI3UDIOrA5nP2Pwcx5yo/m0kZwRUWpx7Oq4vdHT3ugBwnIgL68m3G+sH0O1cWSLwwOBA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:49.951046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27834","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:751a6c53dc427f625effc196970b8b6a7e3a1e12ef93775bbd1ff03673584c70","sha256:ee3e2a78c48e5682a924d42fb25860c8f35ae11e5cd53269fe685a39874e729b"],"state_sha256":"7c7b6ea744bb2f225fa4a402b63a9ad473a9884d9b1ac35607e5672aba892fee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vN+4gyykQOXGyWXMiLgKzW/lLUiH70w5LCLCL8A5rw2DDfl6DWlKMTNblMQL0WqilBHWpmGUpllGp4fEHyIECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T07:56:42.554125Z","bundle_sha256":"6ee7b28793339929410b38ea451b5d658a93a869c1fc9e24033604188a62e07e"}}