{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:ICQTKXNMV3Y4MKZEAEDSDDUUJP","short_pith_number":"pith:ICQTKXNM","canonical_record":{"source":{"id":"1202.1558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T23:14:36Z","cross_cats_sorted":[],"title_canon_sha256":"c88d50f2a04a558a4819cbb98e77d935897f028b0186e67f09bb116934246879","abstract_canon_sha256":"9abef66cbf4eca299ddc01f5c713b7b46fb00ee941f1687da4371d24610fa56a"},"schema_version":"1.0"},"canonical_sha256":"40a1355dacaef1c62b240107218e944be60bbbb8eac70f53ee64d121bc7629ea","source":{"kind":"arxiv","id":"1202.1558","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.1558","created_at":"2026-05-18T04:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"1202.1558v1","created_at":"2026-05-18T04:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.1558","created_at":"2026-05-18T04:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"ICQTKXNMV3Y4","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"ICQTKXNMV3Y4MKZE","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"ICQTKXNM","created_at":"2026-05-18T12:27:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:ICQTKXNMV3Y4MKZEAEDSDDUUJP","target":"record","payload":{"canonical_record":{"source":{"id":"1202.1558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T23:14:36Z","cross_cats_sorted":[],"title_canon_sha256":"c88d50f2a04a558a4819cbb98e77d935897f028b0186e67f09bb116934246879","abstract_canon_sha256":"9abef66cbf4eca299ddc01f5c713b7b46fb00ee941f1687da4371d24610fa56a"},"schema_version":"1.0"},"canonical_sha256":"40a1355dacaef1c62b240107218e944be60bbbb8eac70f53ee64d121bc7629ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:02:52.033641Z","signature_b64":"ChwtasUYQPU5JYFAlRduQWwscow/qLGemMnJS+LwUKFhipyvlLISl7sw6TQL1aVVGIL+Yd2LkyAK3034Hmf9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40a1355dacaef1c62b240107218e944be60bbbb8eac70f53ee64d121bc7629ea","last_reissued_at":"2026-05-18T04:02:52.032992Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:02:52.032992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1202.1558","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":"2026-05-18T04:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yWCkq8FS8b0x9jfPFFkeR7TDGo77vhJcyd5j+pUk7mI40oDgQzBKGIg3+ztNdWiY8B0rHt6v3licEv+vhda9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:23:09.981542Z"},"content_sha256":"158e5ad53c6e4c09ed0ae0a689da8063cda57595a76ebf062ee5421a4f288e7a","schema_version":"1.0","event_id":"sha256:158e5ad53c6e4c09ed0ae0a689da8063cda57595a76ebf062ee5421a4f288e7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:ICQTKXNMV3Y4MKZEAEDSDDUUJP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Performance of Maximum Likelihood Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"H\\'ector Ratia, Luis Montesano, Ruben Martinez-Cantin","submitted_at":"2012-02-07T23:14:36Z","abstract_excerpt":"Inverse reinforcement learning (IRL) addresses the problem of recovering a task description given a demonstration of the optimal policy used to solve such a task. The optimal policy is usually provided by an expert or teacher, making IRL specially suitable for the problem of apprenticeship learning. The task description is encoded in the form of a reward function of a Markov decision process (MDP). Several algorithms have been proposed to find the reward function corresponding to a set of demonstrations. One of the algorithms that has provided best results in different applications is a gradie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.1558","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":""},"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":"2026-05-18T04:02:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hNr//5nuOMGc3zKEfin+aDQHUKRFN3VJT1vtUWhdhAOQ9z9IEY5EbSj3HMik/JMl5Raat3gRC98brvJERTvZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:23:09.981928Z"},"content_sha256":"3565381489a8255c699e9953e0ee7606777c097fc7757fae99bd82e26f14e8a3","schema_version":"1.0","event_id":"sha256:3565381489a8255c699e9953e0ee7606777c097fc7757fae99bd82e26f14e8a3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICQTKXNMV3Y4MKZEAEDSDDUUJP/bundle.json","state_url":"https://pith.science/pith/ICQTKXNMV3Y4MKZEAEDSDDUUJP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICQTKXNMV3Y4MKZEAEDSDDUUJP/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":"2026-06-09T08:23:09Z","links":{"resolver":"https://pith.science/pith/ICQTKXNMV3Y4MKZEAEDSDDUUJP","bundle":"https://pith.science/pith/ICQTKXNMV3Y4MKZEAEDSDDUUJP/bundle.json","state":"https://pith.science/pith/ICQTKXNMV3Y4MKZEAEDSDDUUJP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICQTKXNMV3Y4MKZEAEDSDDUUJP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:ICQTKXNMV3Y4MKZEAEDSDDUUJP","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":"9abef66cbf4eca299ddc01f5c713b7b46fb00ee941f1687da4371d24610fa56a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T23:14:36Z","title_canon_sha256":"c88d50f2a04a558a4819cbb98e77d935897f028b0186e67f09bb116934246879"},"schema_version":"1.0","source":{"id":"1202.1558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.1558","created_at":"2026-05-18T04:02:52Z"},{"alias_kind":"arxiv_version","alias_value":"1202.1558v1","created_at":"2026-05-18T04:02:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.1558","created_at":"2026-05-18T04:02:52Z"},{"alias_kind":"pith_short_12","alias_value":"ICQTKXNMV3Y4","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"ICQTKXNMV3Y4MKZE","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"ICQTKXNM","created_at":"2026-05-18T12:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:3565381489a8255c699e9953e0ee7606777c097fc7757fae99bd82e26f14e8a3","target":"graph","created_at":"2026-05-18T04:02:52Z","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"},"paper":{"abstract_excerpt":"Inverse reinforcement learning (IRL) addresses the problem of recovering a task description given a demonstration of the optimal policy used to solve such a task. The optimal policy is usually provided by an expert or teacher, making IRL specially suitable for the problem of apprenticeship learning. The task description is encoded in the form of a reward function of a Markov decision process (MDP). Several algorithms have been proposed to find the reward function corresponding to a set of demonstrations. One of the algorithms that has provided best results in different applications is a gradie","authors_text":"H\\'ector Ratia, Luis Montesano, Ruben Martinez-Cantin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T23:14:36Z","title":"On the Performance of Maximum Likelihood Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.1558","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":"sha256:158e5ad53c6e4c09ed0ae0a689da8063cda57595a76ebf062ee5421a4f288e7a","target":"record","created_at":"2026-05-18T04:02:52Z","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":"9abef66cbf4eca299ddc01f5c713b7b46fb00ee941f1687da4371d24610fa56a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T23:14:36Z","title_canon_sha256":"c88d50f2a04a558a4819cbb98e77d935897f028b0186e67f09bb116934246879"},"schema_version":"1.0","source":{"id":"1202.1558","kind":"arxiv","version":1}},"canonical_sha256":"40a1355dacaef1c62b240107218e944be60bbbb8eac70f53ee64d121bc7629ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40a1355dacaef1c62b240107218e944be60bbbb8eac70f53ee64d121bc7629ea","first_computed_at":"2026-05-18T04:02:52.032992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:02:52.032992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ChwtasUYQPU5JYFAlRduQWwscow/qLGemMnJS+LwUKFhipyvlLISl7sw6TQL1aVVGIL+Yd2LkyAK3034Hmf9CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:02:52.033641Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.1558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:158e5ad53c6e4c09ed0ae0a689da8063cda57595a76ebf062ee5421a4f288e7a","sha256:3565381489a8255c699e9953e0ee7606777c097fc7757fae99bd82e26f14e8a3"],"state_sha256":"9ab6337fb92383a27ffa8d5151a83a10a45d21d81ba56fc6a383c40382456a1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bFO4gISMw1OBUV9MrOzHDYiOAmys8OaIfVlSA3S/FhU2HP9AmPJzVvcAKXplTW0F21XpoXS17SZWMBKa1EI6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T08:23:09.985274Z","bundle_sha256":"87bbfec06ba169b72282975c4718759b9a5d6d158fe110f239c822bc32f02b92"}}