{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7I6P4N3ZCYQ4FPGDSDQIQJHIFX","short_pith_number":"pith:7I6P4N3Z","canonical_record":{"source":{"id":"2303.00599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-01T15:46:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"dce4bdd8b4b6bfc99227f11616727766cd4190dc61ad39c45102b45e3b34b01f","abstract_canon_sha256":"b43c7360cf2f9470eecabf93bf8addbd1339a59848ea4ca6f86d32c234ff4db0"},"schema_version":"1.0"},"canonical_sha256":"fa3cfe37791621c2bcc390e08824e82decc46167d590b8c1f8ada3564e95ef0f","source":{"kind":"arxiv","id":"2303.00599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00599","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00599v1","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00599","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"pith_short_12","alias_value":"7I6P4N3ZCYQ4","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"pith_short_16","alias_value":"7I6P4N3ZCYQ4FPGD","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"pith_short_8","alias_value":"7I6P4N3Z","created_at":"2026-07-05T05:47:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7I6P4N3ZCYQ4FPGDSDQIQJHIFX","target":"record","payload":{"canonical_record":{"source":{"id":"2303.00599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-01T15:46:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"dce4bdd8b4b6bfc99227f11616727766cd4190dc61ad39c45102b45e3b34b01f","abstract_canon_sha256":"b43c7360cf2f9470eecabf93bf8addbd1339a59848ea4ca6f86d32c234ff4db0"},"schema_version":"1.0"},"canonical_sha256":"fa3cfe37791621c2bcc390e08824e82decc46167d590b8c1f8ada3564e95ef0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:10.848205Z","signature_b64":"xkZZY7smYrUUUORdNXyppTnWrLlRuv+1VJ7fZ7XWbGEZ3HLMrQM+Op8y+2/qthHrLOcgz6RLQ2N2BJrhIG6IAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa3cfe37791621c2bcc390e08824e82decc46167d590b8c1f8ada3564e95ef0f","last_reissued_at":"2026-07-05T05:47:10.847762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:10.847762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.00599","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":"2026-07-05T05:47:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IWtAnFmhg2xNixWSG8AMI5AnDu6xNtNkumUV3mERhn4EdSLANuoROpwzHjVByo7R9xG0EHeX4tpPVrPQYyv5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:50:08.970283Z"},"content_sha256":"ab8f8bbc4e6a04a49f6b49d68ce79da3c439079c05d6f0656e37119824360edc","schema_version":"1.0","event_id":"sha256:ab8f8bbc4e6a04a49f6b49d68ce79da3c439079c05d6f0656e37119824360edc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7I6P4N3ZCYQ4FPGDSDQIQJHIFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Davide Tateo, Firas Al-Hafez, Guoping Zhao, Jan Peters, Oleg Arenz","submitted_at":"2023-03-01T15:46:12Z","abstract_excerpt":"Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability and often mistreat absorbing states. Previous works show that a squared norm regularization on the implicit reward function is effective, but do not provide a theoretical analysis of the resulting properties of the algorithms. In this work, we show that using this regularizer under a mixture distribution of the policy and the expert provides a particularly il"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00599","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.00599/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":"2026-07-05T05:47:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74Vgvhe6PjamX2SAfNZVq30xbAnPh5y5IrWPseHv/oOOS1u6OOk5eLRsh2jK3v3HmV7Pw6zDrFR6iks+Mww5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:50:08.970819Z"},"content_sha256":"3cbb4b4a172ff0c162728e48d65c533b0f4784dd86e14b2b09ed1b6da3ac68f7","schema_version":"1.0","event_id":"sha256:3cbb4b4a172ff0c162728e48d65c533b0f4784dd86e14b2b09ed1b6da3ac68f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7I6P4N3ZCYQ4FPGDSDQIQJHIFX/bundle.json","state_url":"https://pith.science/pith/7I6P4N3ZCYQ4FPGDSDQIQJHIFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7I6P4N3ZCYQ4FPGDSDQIQJHIFX/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":"2026-08-04T05:50:08Z","links":{"resolver":"https://pith.science/pith/7I6P4N3ZCYQ4FPGDSDQIQJHIFX","bundle":"https://pith.science/pith/7I6P4N3ZCYQ4FPGDSDQIQJHIFX/bundle.json","state":"https://pith.science/pith/7I6P4N3ZCYQ4FPGDSDQIQJHIFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7I6P4N3ZCYQ4FPGDSDQIQJHIFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7I6P4N3ZCYQ4FPGDSDQIQJHIFX","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":"b43c7360cf2f9470eecabf93bf8addbd1339a59848ea4ca6f86d32c234ff4db0","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-01T15:46:12Z","title_canon_sha256":"dce4bdd8b4b6bfc99227f11616727766cd4190dc61ad39c45102b45e3b34b01f"},"schema_version":"1.0","source":{"id":"2303.00599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00599","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00599v1","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00599","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"pith_short_12","alias_value":"7I6P4N3ZCYQ4","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"pith_short_16","alias_value":"7I6P4N3ZCYQ4FPGD","created_at":"2026-07-05T05:47:10Z"},{"alias_kind":"pith_short_8","alias_value":"7I6P4N3Z","created_at":"2026-07-05T05:47:10Z"}],"graph_snapshots":[{"event_id":"sha256:3cbb4b4a172ff0c162728e48d65c533b0f4784dd86e14b2b09ed1b6da3ac68f7","target":"graph","created_at":"2026-07-05T05:47:10Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.00599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability and often mistreat absorbing states. Previous works show that a squared norm regularization on the implicit reward function is effective, but do not provide a theoretical analysis of the resulting properties of the algorithms. In this work, we show that using this regularizer under a mixture distribution of the policy and the expert provides a particularly il","authors_text":"Davide Tateo, Firas Al-Hafez, Guoping Zhao, Jan Peters, Oleg Arenz","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-01T15:46:12Z","title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00599","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:ab8f8bbc4e6a04a49f6b49d68ce79da3c439079c05d6f0656e37119824360edc","target":"record","created_at":"2026-07-05T05:47:10Z","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":"b43c7360cf2f9470eecabf93bf8addbd1339a59848ea4ca6f86d32c234ff4db0","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-01T15:46:12Z","title_canon_sha256":"dce4bdd8b4b6bfc99227f11616727766cd4190dc61ad39c45102b45e3b34b01f"},"schema_version":"1.0","source":{"id":"2303.00599","kind":"arxiv","version":1}},"canonical_sha256":"fa3cfe37791621c2bcc390e08824e82decc46167d590b8c1f8ada3564e95ef0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa3cfe37791621c2bcc390e08824e82decc46167d590b8c1f8ada3564e95ef0f","first_computed_at":"2026-07-05T05:47:10.847762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:10.847762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xkZZY7smYrUUUORdNXyppTnWrLlRuv+1VJ7fZ7XWbGEZ3HLMrQM+Op8y+2/qthHrLOcgz6RLQ2N2BJrhIG6IAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:10.848205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab8f8bbc4e6a04a49f6b49d68ce79da3c439079c05d6f0656e37119824360edc","sha256:3cbb4b4a172ff0c162728e48d65c533b0f4784dd86e14b2b09ed1b6da3ac68f7"],"state_sha256":"4cbb5f6c8c0d86e915aa34a2ea79f5575e0c14c025b25ad2828553b688929c92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9OHXymGwgBXrrdUqyHptt2ZBaESf6gNrtuNPuQEmlVarTd7V/SxM3X2/exMg430x96JILazC+2nM/3qsUCzCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:50:08.974329Z","bundle_sha256":"c19cc4121340a2af419f036ab145c9b847e4b20f6bc393c4df5c442373501384"}}