{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:WGZKQX53IJMYDZJ2PJTCMILDSZ","short_pith_number":"pith:WGZKQX53","canonical_record":{"source":{"id":"1208.2112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-10T08:36:49Z","cross_cats_sorted":[],"title_canon_sha256":"0b79aa0ae17ccbc0f80b092d071164317326245ccca5751aaf37557ff9f07a6e","abstract_canon_sha256":"f588ae5988dff998400beb93d9f97ca6bdb1e934b300554982aca2fbbe8099dc"},"schema_version":"1.0"},"canonical_sha256":"b1b2a85fbb425981e53a7a66262163967b7ceddee277688aee8e76794314fb07","source":{"kind":"arxiv","id":"1208.2112","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1208.2112","created_at":"2026-05-18T03:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"1208.2112v2","created_at":"2026-05-18T03:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.2112","created_at":"2026-05-18T03:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"WGZKQX53IJMY","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"WGZKQX53IJMYDZJ2","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"WGZKQX53","created_at":"2026-05-18T12:27:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:WGZKQX53IJMYDZJ2PJTCMILDSZ","target":"record","payload":{"canonical_record":{"source":{"id":"1208.2112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-10T08:36:49Z","cross_cats_sorted":[],"title_canon_sha256":"0b79aa0ae17ccbc0f80b092d071164317326245ccca5751aaf37557ff9f07a6e","abstract_canon_sha256":"f588ae5988dff998400beb93d9f97ca6bdb1e934b300554982aca2fbbe8099dc"},"schema_version":"1.0"},"canonical_sha256":"b1b2a85fbb425981e53a7a66262163967b7ceddee277688aee8e76794314fb07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:04.342187Z","signature_b64":"q9eC/8fF3U44do5b/zyw0HyWwQQcKVDdWnCka+iCRDRPced+rrK4zS+k57JnfEW4nShwnhy5es1/JrN2tgtiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1b2a85fbb425981e53a7a66262163967b7ceddee277688aee8e76794314fb07","last_reissued_at":"2026-05-18T03:36:04.341503Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:04.341503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1208.2112","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":"2026-05-18T03:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oR92wbUKXtOrq8l7kT7vmU0ENFU46M4Cz8TXIvPa3RhgDQJmOZzG2sIoprskDtznslS9j7MbHN3iT3JNz/vQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T16:32:20.729748Z"},"content_sha256":"6372f477fed3585e62e0ec2640a3cd1923b5c428b50cc9f73b6eefea4c569cf6","schema_version":"1.0","event_id":"sha256:6372f477fed3585e62e0ec2640a3cd1923b5c428b50cc9f73b6eefea4c569cf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:WGZKQX53IJMYDZJ2PJTCMILDSZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning with Gaussian Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peter A. Beling, Qifeng Qiao","submitted_at":"2012-08-10T08:36:49Z","abstract_excerpt":"We present new algorithms for inverse reinforcement learning (IRL, or inverse optimal control) in convex optimization settings. We argue that finite-space IRL can be posed as a convex quadratic program under a Bayesian inference framework with the objective of maximum a posterior estimation. To deal with problems in large or even infinite state space, we propose a Gaussian process model and use preference graphs to represent observations of decision trajectories. Our method is distinguished from other approaches to IRL in that it makes no assumptions about the form of the reward function and y"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.2112","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":""},"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":"2026-05-18T03:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FNEXImPShAMoinpb8FiPjcNI0VeXZCvUHPMhtOowVCJi/uAPuOGGH73LbgyO3qjbyOtkpb6oLkQe+2Ol1AQxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T16:32:20.730074Z"},"content_sha256":"cda9025c38808304e3e0735c527306f4dcd8116e099258ff7b628992fdfb5680","schema_version":"1.0","event_id":"sha256:cda9025c38808304e3e0735c527306f4dcd8116e099258ff7b628992fdfb5680"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WGZKQX53IJMYDZJ2PJTCMILDSZ/bundle.json","state_url":"https://pith.science/pith/WGZKQX53IJMYDZJ2PJTCMILDSZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WGZKQX53IJMYDZJ2PJTCMILDSZ/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":"2026-06-26T16:32:20Z","links":{"resolver":"https://pith.science/pith/WGZKQX53IJMYDZJ2PJTCMILDSZ","bundle":"https://pith.science/pith/WGZKQX53IJMYDZJ2PJTCMILDSZ/bundle.json","state":"https://pith.science/pith/WGZKQX53IJMYDZJ2PJTCMILDSZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WGZKQX53IJMYDZJ2PJTCMILDSZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:WGZKQX53IJMYDZJ2PJTCMILDSZ","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":"f588ae5988dff998400beb93d9f97ca6bdb1e934b300554982aca2fbbe8099dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-10T08:36:49Z","title_canon_sha256":"0b79aa0ae17ccbc0f80b092d071164317326245ccca5751aaf37557ff9f07a6e"},"schema_version":"1.0","source":{"id":"1208.2112","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1208.2112","created_at":"2026-05-18T03:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"1208.2112v2","created_at":"2026-05-18T03:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.2112","created_at":"2026-05-18T03:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"WGZKQX53IJMY","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"WGZKQX53IJMYDZJ2","created_at":"2026-05-18T12:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"WGZKQX53","created_at":"2026-05-18T12:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:cda9025c38808304e3e0735c527306f4dcd8116e099258ff7b628992fdfb5680","target":"graph","created_at":"2026-05-18T03:36:04Z","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":"We present new algorithms for inverse reinforcement learning (IRL, or inverse optimal control) in convex optimization settings. We argue that finite-space IRL can be posed as a convex quadratic program under a Bayesian inference framework with the objective of maximum a posterior estimation. To deal with problems in large or even infinite state space, we propose a Gaussian process model and use preference graphs to represent observations of decision trajectories. Our method is distinguished from other approaches to IRL in that it makes no assumptions about the form of the reward function and y","authors_text":"Peter A. Beling, Qifeng Qiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-10T08:36:49Z","title":"Inverse Reinforcement Learning with Gaussian Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.2112","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":"sha256:6372f477fed3585e62e0ec2640a3cd1923b5c428b50cc9f73b6eefea4c569cf6","target":"record","created_at":"2026-05-18T03:36:04Z","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":"f588ae5988dff998400beb93d9f97ca6bdb1e934b300554982aca2fbbe8099dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-08-10T08:36:49Z","title_canon_sha256":"0b79aa0ae17ccbc0f80b092d071164317326245ccca5751aaf37557ff9f07a6e"},"schema_version":"1.0","source":{"id":"1208.2112","kind":"arxiv","version":2}},"canonical_sha256":"b1b2a85fbb425981e53a7a66262163967b7ceddee277688aee8e76794314fb07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1b2a85fbb425981e53a7a66262163967b7ceddee277688aee8e76794314fb07","first_computed_at":"2026-05-18T03:36:04.341503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:36:04.341503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q9eC/8fF3U44do5b/zyw0HyWwQQcKVDdWnCka+iCRDRPced+rrK4zS+k57JnfEW4nShwnhy5es1/JrN2tgtiBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:36:04.342187Z","signed_message":"canonical_sha256_bytes"},"source_id":"1208.2112","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6372f477fed3585e62e0ec2640a3cd1923b5c428b50cc9f73b6eefea4c569cf6","sha256:cda9025c38808304e3e0735c527306f4dcd8116e099258ff7b628992fdfb5680"],"state_sha256":"43dcf125e61626310cd464acd8b6c1c7f1ce657edb48f3fd4f591d9c92daf415"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UF9asKZG8ZuyPA610Eh20HIrmYIueo14i4J7kuogDGV2JKgIiD0y2WyLiQjKb0zvv9nmICRHwJikoG5n1HPUAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T16:32:20.731895Z","bundle_sha256":"16679729b9250bbc94760e6502c343b273992dd2bc59282aa26e133c8dd9c9b0"}}