{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZTIKOTIRQMC2J27HGJFL3B3HPL","short_pith_number":"pith:ZTIKOTIR","canonical_record":{"source":{"id":"2306.08232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T04:06:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5c7e61adc7f5fe732e63971d780351580965d197293d53a4595c1ec5ca4ade2","abstract_canon_sha256":"0fc87f19413becf93b8e0352503e2894ac43187857d0bddb285941aa4d9c3301"},"schema_version":"1.0"},"canonical_sha256":"ccd0a74d118305a4ebe7324abd87677ae6de62b2eb1097b84e03cc99f2c2ea49","source":{"kind":"arxiv","id":"2306.08232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08232","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08232v1","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08232","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"pith_short_12","alias_value":"ZTIKOTIRQMC2","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"pith_short_16","alias_value":"ZTIKOTIRQMC2J27H","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"pith_short_8","alias_value":"ZTIKOTIR","created_at":"2026-07-05T06:20:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZTIKOTIRQMC2J27HGJFL3B3HPL","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08232","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T04:06:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5c7e61adc7f5fe732e63971d780351580965d197293d53a4595c1ec5ca4ade2","abstract_canon_sha256":"0fc87f19413becf93b8e0352503e2894ac43187857d0bddb285941aa4d9c3301"},"schema_version":"1.0"},"canonical_sha256":"ccd0a74d118305a4ebe7324abd87677ae6de62b2eb1097b84e03cc99f2c2ea49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:49.857464Z","signature_b64":"mUZOoIDyoy0NaPzaj3Aor0V9jtycahGPIFxqJPRGf4ifcHa42In1In4DGvj0bnkfELXmo0tZab9mjVPb+pldDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccd0a74d118305a4ebe7324abd87677ae6de62b2eb1097b84e03cc99f2c2ea49","last_reissued_at":"2026-07-05T06:20:49.856819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:49.856819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08232","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":"2026-07-05T06:20:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BHgd81FDLuqqWpff2Ss5gcIU/nKn5bDZ3PGZpRUTc66Ih/BdbL2Z09kJ1G6cQof6hoDYEgLgy9RVG7V+UIgdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:56:22.995048Z"},"content_sha256":"b51d7a8a76db96aa0f97e2c27a214b7716da1993433fcc2bf72567f98074ca4f","schema_version":"1.0","event_id":"sha256:b51d7a8a76db96aa0f97e2c27a214b7716da1993433fcc2bf72567f98074ca4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZTIKOTIRQMC2J27HGJFL3B3HPL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curricular Subgoals for Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongyan Wu, Jiangtao Zhang, Jingyuan Cong, Mingli Song, Shunyu Liu, Shuqi Xu, Tianhao Chen, Yunfu Liu, Yunpeng Qing","submitted_at":"2023-06-14T04:06:41Z","abstract_excerpt":"Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success in imitation learning. To promote expert-like behavior, existing IRL methods mainly focus on learning global reward functions to minimize the trajectory difference between the imitator and the expert. However, these global designs are still limited by the redundant noise and error propagation problems, leading to the unsuitable reward assignment and thus downgrading the agent capability in complex multi-stage tasks. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08232","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/2306.08232/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":"2026-07-05T06:20:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rEh5KyW6q3mvXynxpCqw/aBKg8jcYld4EiqXd12LSseSCL9/2CkWYnGZYgoy9aXoBnguft1LHY4k/lRuVfrzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:56:22.995558Z"},"content_sha256":"77e5eddc484b4ea58424c6398b61f46e532b8bf20364aa27134bc5f85c4630a5","schema_version":"1.0","event_id":"sha256:77e5eddc484b4ea58424c6398b61f46e532b8bf20364aa27134bc5f85c4630a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTIKOTIRQMC2J27HGJFL3B3HPL/bundle.json","state_url":"https://pith.science/pith/ZTIKOTIRQMC2J27HGJFL3B3HPL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTIKOTIRQMC2J27HGJFL3B3HPL/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":"2026-08-07T06:56:22Z","links":{"resolver":"https://pith.science/pith/ZTIKOTIRQMC2J27HGJFL3B3HPL","bundle":"https://pith.science/pith/ZTIKOTIRQMC2J27HGJFL3B3HPL/bundle.json","state":"https://pith.science/pith/ZTIKOTIRQMC2J27HGJFL3B3HPL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTIKOTIRQMC2J27HGJFL3B3HPL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZTIKOTIRQMC2J27HGJFL3B3HPL","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":"0fc87f19413becf93b8e0352503e2894ac43187857d0bddb285941aa4d9c3301","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T04:06:41Z","title_canon_sha256":"f5c7e61adc7f5fe732e63971d780351580965d197293d53a4595c1ec5ca4ade2"},"schema_version":"1.0","source":{"id":"2306.08232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08232","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08232v1","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08232","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"pith_short_12","alias_value":"ZTIKOTIRQMC2","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"pith_short_16","alias_value":"ZTIKOTIRQMC2J27H","created_at":"2026-07-05T06:20:49Z"},{"alias_kind":"pith_short_8","alias_value":"ZTIKOTIR","created_at":"2026-07-05T06:20:49Z"}],"graph_snapshots":[{"event_id":"sha256:77e5eddc484b4ea58424c6398b61f46e532b8bf20364aa27134bc5f85c4630a5","target":"graph","created_at":"2026-07-05T06:20:49Z","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/2306.08232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success in imitation learning. To promote expert-like behavior, existing IRL methods mainly focus on learning global reward functions to minimize the trajectory difference between the imitator and the expert. However, these global designs are still limited by the redundant noise and error propagation problems, leading to the unsuitable reward assignment and thus downgrading the agent capability in complex multi-stage tasks. I","authors_text":"Hongyan Wu, Jiangtao Zhang, Jingyuan Cong, Mingli Song, Shunyu Liu, Shuqi Xu, Tianhao Chen, Yunfu Liu, Yunpeng Qing","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T04:06:41Z","title":"Curricular Subgoals for Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08232","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:b51d7a8a76db96aa0f97e2c27a214b7716da1993433fcc2bf72567f98074ca4f","target":"record","created_at":"2026-07-05T06:20:49Z","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":"0fc87f19413becf93b8e0352503e2894ac43187857d0bddb285941aa4d9c3301","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T04:06:41Z","title_canon_sha256":"f5c7e61adc7f5fe732e63971d780351580965d197293d53a4595c1ec5ca4ade2"},"schema_version":"1.0","source":{"id":"2306.08232","kind":"arxiv","version":1}},"canonical_sha256":"ccd0a74d118305a4ebe7324abd87677ae6de62b2eb1097b84e03cc99f2c2ea49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccd0a74d118305a4ebe7324abd87677ae6de62b2eb1097b84e03cc99f2c2ea49","first_computed_at":"2026-07-05T06:20:49.856819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:49.856819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mUZOoIDyoy0NaPzaj3Aor0V9jtycahGPIFxqJPRGf4ifcHa42In1In4DGvj0bnkfELXmo0tZab9mjVPb+pldDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:49.857464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b51d7a8a76db96aa0f97e2c27a214b7716da1993433fcc2bf72567f98074ca4f","sha256:77e5eddc484b4ea58424c6398b61f46e532b8bf20364aa27134bc5f85c4630a5"],"state_sha256":"87369550b1b01ef00c50c2f4607c29985a3be5759117d18cd2ce259b3bfbf571"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BipcMdk+o8Mmmm7eFpjR0Y0p56RpIzfEZDRyQBCJ3fcP2bhyIhP0aFhJcZ6e6ydo4PwcoofFmVG6eubuEZ41Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:56:22.999887Z","bundle_sha256":"4b97410c30337900dc65bff092b6d7879a95347d6871a285f8b671790ac367be"}}