{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AWGECPPQALRWJGJOCCMFLEBSQK","short_pith_number":"pith:AWGECPPQ","canonical_record":{"source":{"id":"2402.07246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T17:10:31Z","cross_cats_sorted":[],"title_canon_sha256":"75f8774231f3ead68b88832bd4e71459a5bfe954b668206afe91838fa4640d8d","abstract_canon_sha256":"1a7d6f90347bd68d7498cc2bdc9a0957d60a9ba78824ae9449a6d51572c5a755"},"schema_version":"1.0"},"canonical_sha256":"058c413df002e364992e109855903282bbc6e41791aa9c9eebd70e15f733c8f8","source":{"kind":"arxiv","id":"2402.07246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07246","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07246v1","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07246","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"pith_short_12","alias_value":"AWGECPPQALRW","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"pith_short_16","alias_value":"AWGECPPQALRWJGJO","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"pith_short_8","alias_value":"AWGECPPQ","created_at":"2026-07-05T07:44:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AWGECPPQALRWJGJOCCMFLEBSQK","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T17:10:31Z","cross_cats_sorted":[],"title_canon_sha256":"75f8774231f3ead68b88832bd4e71459a5bfe954b668206afe91838fa4640d8d","abstract_canon_sha256":"1a7d6f90347bd68d7498cc2bdc9a0957d60a9ba78824ae9449a6d51572c5a755"},"schema_version":"1.0"},"canonical_sha256":"058c413df002e364992e109855903282bbc6e41791aa9c9eebd70e15f733c8f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:03.216556Z","signature_b64":"DVlFJPRvXmOFWOTU3Nc+uPJfHEebBefWQTYZzBXmtBDxfavB0NdnKsyD9hxjQNE+CgFQvyGn1sYJPZOGP+ZXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"058c413df002e364992e109855903282bbc6e41791aa9c9eebd70e15f733c8f8","last_reissued_at":"2026-07-05T07:44:03.216133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:03.216133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07246","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":"2026-07-05T07:44:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PkFkYNihBjsAxIKEgDTtWnmYcMxgtnnh8uo5IDa8hJ2+j7H3l6Ltg3ItrdmFaKEpibzne1btPMRBS/J7BxjnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:35:37.010352Z"},"content_sha256":"287bf446ced411eb44197658a17083f10002336f8b0cd9d83a44ec82f7dbbfd0","schema_version":"1.0","event_id":"sha256:287bf446ced411eb44197658a17083f10002336f8b0cd9d83a44ec82f7dbbfd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AWGECPPQALRWJGJOCCMFLEBSQK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Generalized Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chaosheng Dong, Yijia Wang","submitted_at":"2024-02-11T17:10:31Z","abstract_excerpt":"This paper studies generalized inverse reinforcement learning (GIRL) in Markov decision processes (MDPs), that is, the problem of learning the basic components of an MDP given observed behavior (policy) that might not be optimal. These components include not only the reward function and transition probability matrices, but also the action space and state space that are not exactly known but are known to belong to given uncertainty sets. We address two key challenges in GIRL: first, the need to quantify the discrepancy between the observed policy and the underlying optimal policy; second, the d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07246","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/2402.07246/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":"2026-07-05T07:44:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTK4bml5Q5C1EVtZcw2mhpJahU7P613M0JdG+HWae/t3xWaYf0/LaUegOM4Ttksgk0sLWTeEUQiUxEjmGnRFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:35:37.010869Z"},"content_sha256":"8ecc4cdf02e3f93604b2e935c8ffc6d21ce9c4c776e86da01e34792c0dd2fe0e","schema_version":"1.0","event_id":"sha256:8ecc4cdf02e3f93604b2e935c8ffc6d21ce9c4c776e86da01e34792c0dd2fe0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWGECPPQALRWJGJOCCMFLEBSQK/bundle.json","state_url":"https://pith.science/pith/AWGECPPQALRWJGJOCCMFLEBSQK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWGECPPQALRWJGJOCCMFLEBSQK/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":"2026-07-10T09:35:37Z","links":{"resolver":"https://pith.science/pith/AWGECPPQALRWJGJOCCMFLEBSQK","bundle":"https://pith.science/pith/AWGECPPQALRWJGJOCCMFLEBSQK/bundle.json","state":"https://pith.science/pith/AWGECPPQALRWJGJOCCMFLEBSQK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWGECPPQALRWJGJOCCMFLEBSQK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AWGECPPQALRWJGJOCCMFLEBSQK","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":"1a7d6f90347bd68d7498cc2bdc9a0957d60a9ba78824ae9449a6d51572c5a755","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T17:10:31Z","title_canon_sha256":"75f8774231f3ead68b88832bd4e71459a5bfe954b668206afe91838fa4640d8d"},"schema_version":"1.0","source":{"id":"2402.07246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07246","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07246v1","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07246","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"pith_short_12","alias_value":"AWGECPPQALRW","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"pith_short_16","alias_value":"AWGECPPQALRWJGJO","created_at":"2026-07-05T07:44:03Z"},{"alias_kind":"pith_short_8","alias_value":"AWGECPPQ","created_at":"2026-07-05T07:44:03Z"}],"graph_snapshots":[{"event_id":"sha256:8ecc4cdf02e3f93604b2e935c8ffc6d21ce9c4c776e86da01e34792c0dd2fe0e","target":"graph","created_at":"2026-07-05T07:44:03Z","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/2402.07246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies generalized inverse reinforcement learning (GIRL) in Markov decision processes (MDPs), that is, the problem of learning the basic components of an MDP given observed behavior (policy) that might not be optimal. These components include not only the reward function and transition probability matrices, but also the action space and state space that are not exactly known but are known to belong to given uncertainty sets. We address two key challenges in GIRL: first, the need to quantify the discrepancy between the observed policy and the underlying optimal policy; second, the d","authors_text":"Chaosheng Dong, Yijia Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T17:10:31Z","title":"Towards Generalized Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07246","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":"sha256:287bf446ced411eb44197658a17083f10002336f8b0cd9d83a44ec82f7dbbfd0","target":"record","created_at":"2026-07-05T07:44:03Z","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":"1a7d6f90347bd68d7498cc2bdc9a0957d60a9ba78824ae9449a6d51572c5a755","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T17:10:31Z","title_canon_sha256":"75f8774231f3ead68b88832bd4e71459a5bfe954b668206afe91838fa4640d8d"},"schema_version":"1.0","source":{"id":"2402.07246","kind":"arxiv","version":1}},"canonical_sha256":"058c413df002e364992e109855903282bbc6e41791aa9c9eebd70e15f733c8f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"058c413df002e364992e109855903282bbc6e41791aa9c9eebd70e15f733c8f8","first_computed_at":"2026-07-05T07:44:03.216133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:03.216133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DVlFJPRvXmOFWOTU3Nc+uPJfHEebBefWQTYZzBXmtBDxfavB0NdnKsyD9hxjQNE+CgFQvyGn1sYJPZOGP+ZXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:03.216556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:287bf446ced411eb44197658a17083f10002336f8b0cd9d83a44ec82f7dbbfd0","sha256:8ecc4cdf02e3f93604b2e935c8ffc6d21ce9c4c776e86da01e34792c0dd2fe0e"],"state_sha256":"5ec9824b4f3d7c5bebceabe1b512fdb4349ee448515505a076faa58c76ae11cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TF+/PDrKCEouZvoyOf7x3WgNUnCx1LzOHyjjH6kNq04NNGSDZq4hv/rQ7XY92s6S7DKDmPi52qzJuWigGb9CCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T09:35:37.012764Z","bundle_sha256":"eb044f2d6e1d03097823668257aca06f6d385cf97345aa1d9e5bf649fbf430ee"}}