{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7SODFRMO4QP7DFKWVEJWBOYZIC","short_pith_number":"pith:7SODFRMO","canonical_record":{"source":{"id":"2008.07284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-17T13:12:44Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"8b38d39babf18a1705e6db2e9a79dce2ae4b450e670f7f81f72d531afec67079","abstract_canon_sha256":"8ac9c2be9192e26449d2a40b9d173e69681df82d648771da1cb88a29213b1e0a"},"schema_version":"1.0"},"canonical_sha256":"fc9c32c58ee41ff19556a91360bb1940ac514a7953b556b4f16ac827f9f44392","source":{"kind":"arxiv","id":"2008.07284","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.07284","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"arxiv_version","alias_value":"2008.07284v2","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07284","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_12","alias_value":"7SODFRMO4QP7","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_16","alias_value":"7SODFRMO4QP7DFKW","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_8","alias_value":"7SODFRMO","created_at":"2026-07-05T04:27:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7SODFRMO4QP7DFKWVEJWBOYZIC","target":"record","payload":{"canonical_record":{"source":{"id":"2008.07284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-17T13:12:44Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"8b38d39babf18a1705e6db2e9a79dce2ae4b450e670f7f81f72d531afec67079","abstract_canon_sha256":"8ac9c2be9192e26449d2a40b9d173e69681df82d648771da1cb88a29213b1e0a"},"schema_version":"1.0"},"canonical_sha256":"fc9c32c58ee41ff19556a91360bb1940ac514a7953b556b4f16ac827f9f44392","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:41.311728Z","signature_b64":"AdM+uiOumJH8QmVQHGadbDhWcQXPs1nDhTqN+X5eaC16ZcASJhKQglpGllZ/4Zjuq/4MM/Nqt22K8Kb0IFxgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc9c32c58ee41ff19556a91360bb1940ac514a7953b556b4f16ac827f9f44392","last_reissued_at":"2026-07-05T04:27:41.311305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:41.311305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.07284","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":"2026-07-05T04:27:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y8tcC/OtxzHPVQdRP2u1Ouo30114c7Vs6uItQY54qt6gWxgcsWCte+kerMN310HvrK8i3sKoUCn0Wj53qX5QBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:48:01.740165Z"},"content_sha256":"941693fe19b6105061bfd19f077c0fb6b274179c9e2b31415f1489be2cf8d5f4","schema_version":"1.0","event_id":"sha256:941693fe19b6105061bfd19f077c0fb6b274179c9e2b31415f1489be2cf8d5f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7SODFRMO4QP7DFKWVEJWBOYZIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Forward and inverse reinforcement learning sharing network weights and hyperparameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Eiji Uchibe, Kenji Doya","submitted_at":"2020-08-17T13:12:44Z","abstract_excerpt":"This paper proposes model-free imitation learning named Entropy-Regularized Imitation Learning (ERIL) that minimizes the reverse Kullback-Leibler (KL) divergence. ERIL combines forward and inverse reinforcement learning (RL) under the framework of an entropy-regularized Markov decision process. An inverse RL step computes the log-ratio between two distributions by evaluating two binary discriminators. The first discriminator distinguishes the state generated by the forward RL step from the expert's state. The second discriminator, which is structured by the theory of entropy regularization, di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07284","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.07284/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":"2026-07-05T04:27:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xWzXy0Q6KK+97v8ksGOLCL67y1ThSnIAoFY/S+3gjXU8istuvqVPEMDpnqDrMPa5KpG9qE7Ls8fs80r+I7cwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:48:01.740705Z"},"content_sha256":"0fb995650ddfaaae7127b19fb87bb36f841d0b65cef0165de438c8ee460f0e6d","schema_version":"1.0","event_id":"sha256:0fb995650ddfaaae7127b19fb87bb36f841d0b65cef0165de438c8ee460f0e6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7SODFRMO4QP7DFKWVEJWBOYZIC/bundle.json","state_url":"https://pith.science/pith/7SODFRMO4QP7DFKWVEJWBOYZIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7SODFRMO4QP7DFKWVEJWBOYZIC/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":"2026-08-12T18:48:01Z","links":{"resolver":"https://pith.science/pith/7SODFRMO4QP7DFKWVEJWBOYZIC","bundle":"https://pith.science/pith/7SODFRMO4QP7DFKWVEJWBOYZIC/bundle.json","state":"https://pith.science/pith/7SODFRMO4QP7DFKWVEJWBOYZIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7SODFRMO4QP7DFKWVEJWBOYZIC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7SODFRMO4QP7DFKWVEJWBOYZIC","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":"8ac9c2be9192e26449d2a40b9d173e69681df82d648771da1cb88a29213b1e0a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-17T13:12:44Z","title_canon_sha256":"8b38d39babf18a1705e6db2e9a79dce2ae4b450e670f7f81f72d531afec67079"},"schema_version":"1.0","source":{"id":"2008.07284","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.07284","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"arxiv_version","alias_value":"2008.07284v2","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07284","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_12","alias_value":"7SODFRMO4QP7","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_16","alias_value":"7SODFRMO4QP7DFKW","created_at":"2026-07-05T04:27:41Z"},{"alias_kind":"pith_short_8","alias_value":"7SODFRMO","created_at":"2026-07-05T04:27:41Z"}],"graph_snapshots":[{"event_id":"sha256:0fb995650ddfaaae7127b19fb87bb36f841d0b65cef0165de438c8ee460f0e6d","target":"graph","created_at":"2026-07-05T04:27:41Z","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/2008.07284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes model-free imitation learning named Entropy-Regularized Imitation Learning (ERIL) that minimizes the reverse Kullback-Leibler (KL) divergence. ERIL combines forward and inverse reinforcement learning (RL) under the framework of an entropy-regularized Markov decision process. An inverse RL step computes the log-ratio between two distributions by evaluating two binary discriminators. The first discriminator distinguishes the state generated by the forward RL step from the expert's state. The second discriminator, which is structured by the theory of entropy regularization, di","authors_text":"Eiji Uchibe, Kenji Doya","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-17T13:12:44Z","title":"Forward and inverse reinforcement learning sharing network weights and hyperparameters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07284","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":"sha256:941693fe19b6105061bfd19f077c0fb6b274179c9e2b31415f1489be2cf8d5f4","target":"record","created_at":"2026-07-05T04:27:41Z","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":"8ac9c2be9192e26449d2a40b9d173e69681df82d648771da1cb88a29213b1e0a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-17T13:12:44Z","title_canon_sha256":"8b38d39babf18a1705e6db2e9a79dce2ae4b450e670f7f81f72d531afec67079"},"schema_version":"1.0","source":{"id":"2008.07284","kind":"arxiv","version":2}},"canonical_sha256":"fc9c32c58ee41ff19556a91360bb1940ac514a7953b556b4f16ac827f9f44392","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc9c32c58ee41ff19556a91360bb1940ac514a7953b556b4f16ac827f9f44392","first_computed_at":"2026-07-05T04:27:41.311305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:41.311305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AdM+uiOumJH8QmVQHGadbDhWcQXPs1nDhTqN+X5eaC16ZcASJhKQglpGllZ/4Zjuq/4MM/Nqt22K8Kb0IFxgCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:41.311728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.07284","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:941693fe19b6105061bfd19f077c0fb6b274179c9e2b31415f1489be2cf8d5f4","sha256:0fb995650ddfaaae7127b19fb87bb36f841d0b65cef0165de438c8ee460f0e6d"],"state_sha256":"5baedc6c519d6e6df0da9e74631e09c9124fbc0eb09af9dc21743db993d89d86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"atc/ANR95hJ29vTIETup+GF2ZOzXqcn50x/kjQ0gwOzwGfg+9KJWhFJvFk1cjepQsjU6xbQV+fAtQobSPPAyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:48:01.747955Z","bundle_sha256":"47653c946bb82c4938f622f1fdedaa39e669c14b3cea94996584b67cd5474ac3"}}