{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DGEONM2V7VFMGWRIU24Z5U6AOV","short_pith_number":"pith:DGEONM2V","canonical_record":{"source":{"id":"1604.03912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-13T19:06:41Z","cross_cats_sorted":["cs.LG","cs.SY","stat.ML"],"title_canon_sha256":"573fcf22c6d67b4414f9a5f6c3779ae7c3ea89fca1d14f0be581882fcfebb85c","abstract_canon_sha256":"b02996cc4a4cb563f42b2954f264e346a8b42277268e33a77e95cbaabff9abd1"},"schema_version":"1.0"},"canonical_sha256":"1988e6b355fd4ac35a28a6b99ed3c0754ce392b0e12bfcbdea349ff5537600fd","source":{"kind":"arxiv","id":"1604.03912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.03912","created_at":"2026-05-18T01:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"1604.03912v1","created_at":"2026-05-18T01:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03912","created_at":"2026-05-18T01:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"DGEONM2V7VFM","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DGEONM2V7VFMGWRI","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DGEONM2V","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DGEONM2V7VFMGWRIU24Z5U6AOV","target":"record","payload":{"canonical_record":{"source":{"id":"1604.03912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-13T19:06:41Z","cross_cats_sorted":["cs.LG","cs.SY","stat.ML"],"title_canon_sha256":"573fcf22c6d67b4414f9a5f6c3779ae7c3ea89fca1d14f0be581882fcfebb85c","abstract_canon_sha256":"b02996cc4a4cb563f42b2954f264e346a8b42277268e33a77e95cbaabff9abd1"},"schema_version":"1.0"},"canonical_sha256":"1988e6b355fd4ac35a28a6b99ed3c0754ce392b0e12bfcbdea349ff5537600fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:10.686572Z","signature_b64":"P0T4aZ4Gllb7oV6EQGq7R7WM/YGsjPn8kKGpmJuaiK1CGUTCf+28LjgTEokP9I3Z55owex6N88ExR/DbM6B1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1988e6b355fd4ac35a28a6b99ed3c0754ce392b0e12bfcbdea349ff5537600fd","last_reissued_at":"2026-05-18T01:17:10.685340Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:10.685340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.03912","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":"2026-05-18T01:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n6PWttUJthaJCynx+OJMAsUl5hUlXsZBauSji+HFm3T8m4WTrx1W5Xb5gElczNomxm2jEf10VnvbrNaglKUJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T22:51:25.869185Z"},"content_sha256":"690f2262ab5ca750e30e229b767db1f8a52d1ca4b8506f9d368694a4758127a3","schema_version":"1.0","event_id":"sha256:690f2262ab5ca750e30e229b767db1f8a52d1ca4b8506f9d368694a4758127a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DGEONM2V7VFMGWRIU24Z5U6AOV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","stat.ML"],"primary_cat":"cs.AI","authors_text":"Felix Schmitt, J\\\"org Wagner, Michael Herman, Tobias Gindele, Wolfram Burgard","submitted_at":"2016-04-13T19:06:41Z","abstract_excerpt":"Inverse Reinforcement Learning (IRL) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the solution of the inverse problem is significantly influenced by both. Current IRL approaches assume that if the transition model is unknown, additional samples from the system's dynamics are accessible, or the observed behavior provides enough samples of the system's dynamics to s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03912","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":"2026-05-18T01:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bcEvT8rRDPVWBC4FC89dSrjjRcPg8muJGQCGA8kaKh/tBBWPt8l9zw3gO8+CaSzC9GTE9sKRCNIcQ6pznRZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T22:51:25.869881Z"},"content_sha256":"7acb980d1ee6eec286befb37cc73708103e68991b619f2e442bd30bad3d1804e","schema_version":"1.0","event_id":"sha256:7acb980d1ee6eec286befb37cc73708103e68991b619f2e442bd30bad3d1804e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DGEONM2V7VFMGWRIU24Z5U6AOV/bundle.json","state_url":"https://pith.science/pith/DGEONM2V7VFMGWRIU24Z5U6AOV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DGEONM2V7VFMGWRIU24Z5U6AOV/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":"2026-05-29T22:51:25Z","links":{"resolver":"https://pith.science/pith/DGEONM2V7VFMGWRIU24Z5U6AOV","bundle":"https://pith.science/pith/DGEONM2V7VFMGWRIU24Z5U6AOV/bundle.json","state":"https://pith.science/pith/DGEONM2V7VFMGWRIU24Z5U6AOV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DGEONM2V7VFMGWRIU24Z5U6AOV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DGEONM2V7VFMGWRIU24Z5U6AOV","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":"b02996cc4a4cb563f42b2954f264e346a8b42277268e33a77e95cbaabff9abd1","cross_cats_sorted":["cs.LG","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-13T19:06:41Z","title_canon_sha256":"573fcf22c6d67b4414f9a5f6c3779ae7c3ea89fca1d14f0be581882fcfebb85c"},"schema_version":"1.0","source":{"id":"1604.03912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.03912","created_at":"2026-05-18T01:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"1604.03912v1","created_at":"2026-05-18T01:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.03912","created_at":"2026-05-18T01:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"DGEONM2V7VFM","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"DGEONM2V7VFMGWRI","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"DGEONM2V","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:7acb980d1ee6eec286befb37cc73708103e68991b619f2e442bd30bad3d1804e","target":"graph","created_at":"2026-05-18T01:17:10Z","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) describes the problem of learning an unknown reward function of a Markov Decision Process (MDP) from observed behavior of an agent. Since the agent's behavior originates in its policy and MDP policies depend on both the stochastic system dynamics as well as the reward function, the solution of the inverse problem is significantly influenced by both. Current IRL approaches assume that if the transition model is unknown, additional samples from the system's dynamics are accessible, or the observed behavior provides enough samples of the system's dynamics to s","authors_text":"Felix Schmitt, J\\\"org Wagner, Michael Herman, Tobias Gindele, Wolfram Burgard","cross_cats":["cs.LG","cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-13T19:06:41Z","title":"Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.03912","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":"sha256:690f2262ab5ca750e30e229b767db1f8a52d1ca4b8506f9d368694a4758127a3","target":"record","created_at":"2026-05-18T01:17:10Z","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":"b02996cc4a4cb563f42b2954f264e346a8b42277268e33a77e95cbaabff9abd1","cross_cats_sorted":["cs.LG","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-04-13T19:06:41Z","title_canon_sha256":"573fcf22c6d67b4414f9a5f6c3779ae7c3ea89fca1d14f0be581882fcfebb85c"},"schema_version":"1.0","source":{"id":"1604.03912","kind":"arxiv","version":1}},"canonical_sha256":"1988e6b355fd4ac35a28a6b99ed3c0754ce392b0e12bfcbdea349ff5537600fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1988e6b355fd4ac35a28a6b99ed3c0754ce392b0e12bfcbdea349ff5537600fd","first_computed_at":"2026-05-18T01:17:10.685340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:10.685340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P0T4aZ4Gllb7oV6EQGq7R7WM/YGsjPn8kKGpmJuaiK1CGUTCf+28LjgTEokP9I3Z55owex6N88ExR/DbM6B1BA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:10.686572Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.03912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:690f2262ab5ca750e30e229b767db1f8a52d1ca4b8506f9d368694a4758127a3","sha256:7acb980d1ee6eec286befb37cc73708103e68991b619f2e442bd30bad3d1804e"],"state_sha256":"658d8bab66f9e682277c387ca9e58c4178a2406a99415023e3195c2fce6fc97b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mn4w9eJpKvtt/bsKNRBfPI/LI/FdaCyf1IpdswvY9S/o2pYxZdqga0ddUgbG6RReOeIhkhD9moZ2e1zJRFq7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T22:51:25.873501Z","bundle_sha256":"5b4786b05e00742dab52b41991d1a4d2a22c6e9bcabb7c075e69e3e952423af1"}}