{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:JBZQNYZGGGEBJW4LX6GZBDRIEK","short_pith_number":"pith:JBZQNYZG","canonical_record":{"source":{"id":"1507.04888","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-17T09:30:03Z","cross_cats_sorted":[],"title_canon_sha256":"608f82bdd286161df37b110977caff59d6bf14ce4f718c9fda346b366759ca0b","abstract_canon_sha256":"f4b057575db1539d5dc454652ec5b9434eca63572f02b9d050054a88c348889b"},"schema_version":"1.0"},"canonical_sha256":"487306e326318814db8bbf8d908e28229724ad128e183b25144155d58def0baa","source":{"kind":"arxiv","id":"1507.04888","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.04888","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"1507.04888v3","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.04888","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"JBZQNYZGGGEB","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JBZQNYZGGGEBJW4L","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JBZQNYZG","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:JBZQNYZGGGEBJW4LX6GZBDRIEK","target":"record","payload":{"canonical_record":{"source":{"id":"1507.04888","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-17T09:30:03Z","cross_cats_sorted":[],"title_canon_sha256":"608f82bdd286161df37b110977caff59d6bf14ce4f718c9fda346b366759ca0b","abstract_canon_sha256":"f4b057575db1539d5dc454652ec5b9434eca63572f02b9d050054a88c348889b"},"schema_version":"1.0"},"canonical_sha256":"487306e326318814db8bbf8d908e28229724ad128e183b25144155d58def0baa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:16.016217Z","signature_b64":"+pbssdTMGE4hgUQHqPMO5ISlBesFwmCg0pKFs0+hE385mfFa3GsKgYYh0ITp8pvYyPSLSiE/hqFKiLGWEqIvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"487306e326318814db8bbf8d908e28229724ad128e183b25144155d58def0baa","last_reissued_at":"2026-05-18T01:19:16.015869Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:16.015869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.04888","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9JC06aFfAZpFgRN0t6yreujIKx+zO3sL8Iiq/sF90z+04oBFw2bYtBcMW9ITO8kwXg8KMrFCspsEVrkaa1WBCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:45:48.712787Z"},"content_sha256":"553da81b5f7da18693b75a6347c459fae855f55fa295ef46a69b303145f4d769","schema_version":"1.0","event_id":"sha256:553da81b5f7da18693b75a6347c459fae855f55fa295ef46a69b303145f4d769"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:JBZQNYZGGGEBJW4LX6GZBDRIEK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maximum Entropy Deep Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ingmar Posner, Markus Wulfmeier, Peter Ondruska","submitted_at":"2015-07-17T09:30:03Z","abstract_excerpt":"This paper presents a general framework for exploiting the representational capacity of neural networks to approximate complex, nonlinear reward functions in the context of solving the inverse reinforcement learning (IRL) problem. We show in this context that the Maximum Entropy paradigm for IRL lends itself naturally to the efficient training of deep architectures. At test time, the approach leads to a computational complexity independent of the number of demonstrations, which makes it especially well-suited for applications in life-long learning scenarios. Our approach achieves performance c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.04888","kind":"arxiv","version":3},"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":"2026-05-18T01:19:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VZZgNJbfrgbgo+00lPusqxqQT0A7m0mYiodeK+eGs3RxTrka4BPDZvfqEX/vXr3AKMT4HWmKsZiF54HhE91kAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T03:45:48.713124Z"},"content_sha256":"22a85287027d877ed677d2447b6c0ad6340b6b83f74d8c85313fd9a487a0f284","schema_version":"1.0","event_id":"sha256:22a85287027d877ed677d2447b6c0ad6340b6b83f74d8c85313fd9a487a0f284"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JBZQNYZGGGEBJW4LX6GZBDRIEK/bundle.json","state_url":"https://pith.science/pith/JBZQNYZGGGEBJW4LX6GZBDRIEK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JBZQNYZGGGEBJW4LX6GZBDRIEK/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":"2026-06-03T03:45:48Z","links":{"resolver":"https://pith.science/pith/JBZQNYZGGGEBJW4LX6GZBDRIEK","bundle":"https://pith.science/pith/JBZQNYZGGGEBJW4LX6GZBDRIEK/bundle.json","state":"https://pith.science/pith/JBZQNYZGGGEBJW4LX6GZBDRIEK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JBZQNYZGGGEBJW4LX6GZBDRIEK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:JBZQNYZGGGEBJW4LX6GZBDRIEK","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":"f4b057575db1539d5dc454652ec5b9434eca63572f02b9d050054a88c348889b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-17T09:30:03Z","title_canon_sha256":"608f82bdd286161df37b110977caff59d6bf14ce4f718c9fda346b366759ca0b"},"schema_version":"1.0","source":{"id":"1507.04888","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.04888","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"1507.04888v3","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.04888","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"JBZQNYZGGGEB","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JBZQNYZGGGEBJW4L","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JBZQNYZG","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:22a85287027d877ed677d2447b6c0ad6340b6b83f74d8c85313fd9a487a0f284","target":"graph","created_at":"2026-05-18T01:19:16Z","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":"This paper presents a general framework for exploiting the representational capacity of neural networks to approximate complex, nonlinear reward functions in the context of solving the inverse reinforcement learning (IRL) problem. We show in this context that the Maximum Entropy paradigm for IRL lends itself naturally to the efficient training of deep architectures. At test time, the approach leads to a computational complexity independent of the number of demonstrations, which makes it especially well-suited for applications in life-long learning scenarios. Our approach achieves performance c","authors_text":"Ingmar Posner, Markus Wulfmeier, Peter Ondruska","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-17T09:30:03Z","title":"Maximum Entropy Deep Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.04888","kind":"arxiv","version":3},"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":"sha256:553da81b5f7da18693b75a6347c459fae855f55fa295ef46a69b303145f4d769","target":"record","created_at":"2026-05-18T01:19:16Z","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":"f4b057575db1539d5dc454652ec5b9434eca63572f02b9d050054a88c348889b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-17T09:30:03Z","title_canon_sha256":"608f82bdd286161df37b110977caff59d6bf14ce4f718c9fda346b366759ca0b"},"schema_version":"1.0","source":{"id":"1507.04888","kind":"arxiv","version":3}},"canonical_sha256":"487306e326318814db8bbf8d908e28229724ad128e183b25144155d58def0baa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"487306e326318814db8bbf8d908e28229724ad128e183b25144155d58def0baa","first_computed_at":"2026-05-18T01:19:16.015869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:19:16.015869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+pbssdTMGE4hgUQHqPMO5ISlBesFwmCg0pKFs0+hE385mfFa3GsKgYYh0ITp8pvYyPSLSiE/hqFKiLGWEqIvBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:19:16.016217Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.04888","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:553da81b5f7da18693b75a6347c459fae855f55fa295ef46a69b303145f4d769","sha256:22a85287027d877ed677d2447b6c0ad6340b6b83f74d8c85313fd9a487a0f284"],"state_sha256":"ca5b20ac1d6c2108441912dbaa3ded3a4b4f540f80f69568395b64f7610411c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSBeJBfBMzsQmjpZJirDBEmpFNYczdLLbLARKGvQpm8M6F41dnPmtLio9+nPElyKzI8niK6YYQ9GypjQtHdYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T03:45:48.715026Z","bundle_sha256":"4cf89157b701030014439b50ab4e2dbeb04753436f5d0cbfccdfef5a54fd7d5c"}}