{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EKQSY3G7D5AD6OYQQNCGZNM6T2","short_pith_number":"pith:EKQSY3G7","canonical_record":{"source":{"id":"2309.16074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-28T00:11:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f90edf52a3ab381256a36381e7d428021b334033ec8884005f1796bec5ef87b","abstract_canon_sha256":"4f4ae47657bfeddd2d53bdb8e5cbc74b80e47c0d6c1eb3329bc603f1283551e4"},"schema_version":"1.0"},"canonical_sha256":"22a12c6cdf1f403f3b1083446cb59e9e8ef0ec18784f43ab02a549e4afe585ff","source":{"kind":"arxiv","id":"2309.16074","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16074","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16074v1","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16074","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"pith_short_12","alias_value":"EKQSY3G7D5AD","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"pith_short_16","alias_value":"EKQSY3G7D5AD6OYQ","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"pith_short_8","alias_value":"EKQSY3G7","created_at":"2026-07-05T06:55:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EKQSY3G7D5AD6OYQQNCGZNM6T2","target":"record","payload":{"canonical_record":{"source":{"id":"2309.16074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-28T00:11:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7f90edf52a3ab381256a36381e7d428021b334033ec8884005f1796bec5ef87b","abstract_canon_sha256":"4f4ae47657bfeddd2d53bdb8e5cbc74b80e47c0d6c1eb3329bc603f1283551e4"},"schema_version":"1.0"},"canonical_sha256":"22a12c6cdf1f403f3b1083446cb59e9e8ef0ec18784f43ab02a549e4afe585ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:11.108612Z","signature_b64":"I/lN4/K4ISNHb0+USJZMHMwnxB5OFYiRHq1FVw0ZP32PjifCUrcpAaRfhnB8WG/5TZuIZxMUJwww1BI18vNgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22a12c6cdf1f403f3b1083446cb59e9e8ef0ec18784f43ab02a549e4afe585ff","last_reissued_at":"2026-07-05T06:55:11.107664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:11.107664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.16074","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":"2026-07-05T06:55:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EE5G58ZO2Z4e+dkAXfADkeIT3OZBfVKL0GYcVR4XKK3ZVpFD6BHbJMUNUxp/viKh/k9/TrLPKluPkZU+DUxKBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:29:50.320914Z"},"content_sha256":"bfb830963511751d873c210ad1caac7ecf78a15886cadbff1fb15639514e4d48","schema_version":"1.0","event_id":"sha256:bfb830963511751d873c210ad1caac7ecf78a15886cadbff1fb15639514e4d48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EKQSY3G7D5AD6OYQQNCGZNM6T2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Anqi Wu, Feiyang Wu, Hanran Wu, Ye Zhao, Zhaoyuan Gu","submitted_at":"2023-09-28T00:11:06Z","abstract_excerpt":"Enabling bipedal walking robots to learn how to maneuver over highly uneven, dynamically changing terrains is challenging due to the complexity of robot dynamics and interacted environments. Recent advancements in learning from demonstrations have shown promising results for robot learning in complex environments. While imitation learning of expert policies has been well-explored, the study of learning expert reward functions is largely under-explored in legged locomotion. This paper brings state-of-the-art Inverse Reinforcement Learning (IRL) techniques to solving bipedal locomotion problems "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16074","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/2309.16074/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":"2026-07-05T06:55:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+alqP78OSGZiEX034CHBGbgcuKsPzHMFLTZF0U8U2bE96KigVSBFpKnEo0fQwaXf6udEKImeDUkSW4el5DKbAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:29:50.321531Z"},"content_sha256":"260960e65b39425e978cce173eb2dd7bd3e329c6657a30efe149931813f92d03","schema_version":"1.0","event_id":"sha256:260960e65b39425e978cce173eb2dd7bd3e329c6657a30efe149931813f92d03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EKQSY3G7D5AD6OYQQNCGZNM6T2/bundle.json","state_url":"https://pith.science/pith/EKQSY3G7D5AD6OYQQNCGZNM6T2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EKQSY3G7D5AD6OYQQNCGZNM6T2/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":"2026-08-07T00:29:50Z","links":{"resolver":"https://pith.science/pith/EKQSY3G7D5AD6OYQQNCGZNM6T2","bundle":"https://pith.science/pith/EKQSY3G7D5AD6OYQQNCGZNM6T2/bundle.json","state":"https://pith.science/pith/EKQSY3G7D5AD6OYQQNCGZNM6T2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EKQSY3G7D5AD6OYQQNCGZNM6T2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EKQSY3G7D5AD6OYQQNCGZNM6T2","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":"4f4ae47657bfeddd2d53bdb8e5cbc74b80e47c0d6c1eb3329bc603f1283551e4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-28T00:11:06Z","title_canon_sha256":"7f90edf52a3ab381256a36381e7d428021b334033ec8884005f1796bec5ef87b"},"schema_version":"1.0","source":{"id":"2309.16074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.16074","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"arxiv_version","alias_value":"2309.16074v1","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16074","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"pith_short_12","alias_value":"EKQSY3G7D5AD","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"pith_short_16","alias_value":"EKQSY3G7D5AD6OYQ","created_at":"2026-07-05T06:55:11Z"},{"alias_kind":"pith_short_8","alias_value":"EKQSY3G7","created_at":"2026-07-05T06:55:11Z"}],"graph_snapshots":[{"event_id":"sha256:260960e65b39425e978cce173eb2dd7bd3e329c6657a30efe149931813f92d03","target":"graph","created_at":"2026-07-05T06:55:11Z","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/2309.16074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Enabling bipedal walking robots to learn how to maneuver over highly uneven, dynamically changing terrains is challenging due to the complexity of robot dynamics and interacted environments. Recent advancements in learning from demonstrations have shown promising results for robot learning in complex environments. While imitation learning of expert policies has been well-explored, the study of learning expert reward functions is largely under-explored in legged locomotion. This paper brings state-of-the-art Inverse Reinforcement Learning (IRL) techniques to solving bipedal locomotion problems ","authors_text":"Anqi Wu, Feiyang Wu, Hanran Wu, Ye Zhao, Zhaoyuan Gu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-28T00:11:06Z","title":"Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16074","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:bfb830963511751d873c210ad1caac7ecf78a15886cadbff1fb15639514e4d48","target":"record","created_at":"2026-07-05T06:55:11Z","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":"4f4ae47657bfeddd2d53bdb8e5cbc74b80e47c0d6c1eb3329bc603f1283551e4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-09-28T00:11:06Z","title_canon_sha256":"7f90edf52a3ab381256a36381e7d428021b334033ec8884005f1796bec5ef87b"},"schema_version":"1.0","source":{"id":"2309.16074","kind":"arxiv","version":1}},"canonical_sha256":"22a12c6cdf1f403f3b1083446cb59e9e8ef0ec18784f43ab02a549e4afe585ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22a12c6cdf1f403f3b1083446cb59e9e8ef0ec18784f43ab02a549e4afe585ff","first_computed_at":"2026-07-05T06:55:11.107664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:11.107664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I/lN4/K4ISNHb0+USJZMHMwnxB5OFYiRHq1FVw0ZP32PjifCUrcpAaRfhnB8WG/5TZuIZxMUJwww1BI18vNgDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:11.108612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.16074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfb830963511751d873c210ad1caac7ecf78a15886cadbff1fb15639514e4d48","sha256:260960e65b39425e978cce173eb2dd7bd3e329c6657a30efe149931813f92d03"],"state_sha256":"d23e3d1a6931661d62d35508d8b52dc3f35bbda6d18e02699b8f45b46908d8dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMngpeLTgiq5gWo//9VHpKSpe9AiQumvzyzTzGcWxtLE2AYiNMJisAwGKHcn8x0UFLkIF7pIGZH5nplhSPXPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:29:50.324761Z","bundle_sha256":"eed0c355a4bab67ec7388b82be5f96ef74f3ba7c6f9cd71935af56054b6c96ff"}}