{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SOE6APMFY3XSOPQ6XXZMHRGYZK","short_pith_number":"pith:SOE6APMF","canonical_record":{"source":{"id":"2204.11446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T05:36:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9812e3ec6c479f56a47c8c98e387393a9a9cce7b8c43d79d25d059a391f3d425","abstract_canon_sha256":"e6f97d7d3f621be48815430302f464a53c5b1a06ef52249ed5e38b41940cc024"},"schema_version":"1.0"},"canonical_sha256":"9389e03d85c6ef273e1ebdf2c3c4d8cabe7b1a6e1c001a5bd1d8bb4c39d40829","source":{"kind":"arxiv","id":"2204.11446","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11446","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11446v1","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11446","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"SOE6APMFY3XS","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"pith_short_16","alias_value":"SOE6APMFY3XSOPQ6","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"pith_short_8","alias_value":"SOE6APMF","created_at":"2026-07-05T04:17:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SOE6APMFY3XSOPQ6XXZMHRGYZK","target":"record","payload":{"canonical_record":{"source":{"id":"2204.11446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T05:36:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9812e3ec6c479f56a47c8c98e387393a9a9cce7b8c43d79d25d059a391f3d425","abstract_canon_sha256":"e6f97d7d3f621be48815430302f464a53c5b1a06ef52249ed5e38b41940cc024"},"schema_version":"1.0"},"canonical_sha256":"9389e03d85c6ef273e1ebdf2c3c4d8cabe7b1a6e1c001a5bd1d8bb4c39d40829","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:27.987212Z","signature_b64":"FxX73Gn+RerHOngdeJZZ+D95Ov0v1x9kPhpKeORrJP95Vcvy7qEbKd8k58Bf46n/Zg8Qm4Z9Za8/PijHOKtPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9389e03d85c6ef273e1ebdf2c3c4d8cabe7b1a6e1c001a5bd1d8bb4c39d40829","last_reissued_at":"2026-07-05T04:17:27.986695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:27.986695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.11446","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":"2026-07-05T04:17:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0JDHy5OxYtRckBTLaHUGcQgjj6zqxV8XUGdHhXGqk+QBVDHwtg4YN6ez4ID2QQ0pac7ZfqnwJI1ii9wrj6zBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:30:44.490485Z"},"content_sha256":"dfdfc309aa5b33c680a90154c675d824f90201b768757833790531ff0e2f1ac8","schema_version":"1.0","event_id":"sha256:dfdfc309aa5b33c680a90154c675d824f90201b768757833790531ff0e2f1ac8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SOE6APMFY3XSOPQ6XXZMHRGYZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imitation Learning from Observations under Transition Model Disparity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Tanmay Gangwani, Yuan Zhou","submitted_at":"2022-04-25T05:36:54Z","abstract_excerpt":"Learning to perform tasks by leveraging a dataset of expert observations, also known as imitation learning from observations (ILO), is an important paradigm for learning skills without access to the expert reward function or the expert actions. We consider ILO in the setting where the expert and the learner agents operate in different environments, with the source of the discrepancy being the transition dynamics model. Recent methods for scalable ILO utilize adversarial learning to match the state-transition distributions of the expert and the learner, an approach that becomes challenging when"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11446","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/2204.11446/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":"2026-07-05T04:17:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zOM9naxwtyOXI4juQsz83ATgkQh0NosZaB2ooXDyCGCJFiYiv9A3IXdhMNeviWyVUveYQv6YI4NuZGNueyo8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T01:30:44.491030Z"},"content_sha256":"dc0f5209a8dfd38ce9668ca5b1e8f27ba13a32f74fd2ababd91c0409f7091e38","schema_version":"1.0","event_id":"sha256:dc0f5209a8dfd38ce9668ca5b1e8f27ba13a32f74fd2ababd91c0409f7091e38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SOE6APMFY3XSOPQ6XXZMHRGYZK/bundle.json","state_url":"https://pith.science/pith/SOE6APMFY3XSOPQ6XXZMHRGYZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SOE6APMFY3XSOPQ6XXZMHRGYZK/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":"2026-08-14T01:30:44Z","links":{"resolver":"https://pith.science/pith/SOE6APMFY3XSOPQ6XXZMHRGYZK","bundle":"https://pith.science/pith/SOE6APMFY3XSOPQ6XXZMHRGYZK/bundle.json","state":"https://pith.science/pith/SOE6APMFY3XSOPQ6XXZMHRGYZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SOE6APMFY3XSOPQ6XXZMHRGYZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SOE6APMFY3XSOPQ6XXZMHRGYZK","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":"e6f97d7d3f621be48815430302f464a53c5b1a06ef52249ed5e38b41940cc024","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T05:36:54Z","title_canon_sha256":"9812e3ec6c479f56a47c8c98e387393a9a9cce7b8c43d79d25d059a391f3d425"},"schema_version":"1.0","source":{"id":"2204.11446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.11446","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"2204.11446v1","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11446","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"SOE6APMFY3XS","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"pith_short_16","alias_value":"SOE6APMFY3XSOPQ6","created_at":"2026-07-05T04:17:27Z"},{"alias_kind":"pith_short_8","alias_value":"SOE6APMF","created_at":"2026-07-05T04:17:27Z"}],"graph_snapshots":[{"event_id":"sha256:dc0f5209a8dfd38ce9668ca5b1e8f27ba13a32f74fd2ababd91c0409f7091e38","target":"graph","created_at":"2026-07-05T04:17:27Z","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/2204.11446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to perform tasks by leveraging a dataset of expert observations, also known as imitation learning from observations (ILO), is an important paradigm for learning skills without access to the expert reward function or the expert actions. We consider ILO in the setting where the expert and the learner agents operate in different environments, with the source of the discrepancy being the transition dynamics model. Recent methods for scalable ILO utilize adversarial learning to match the state-transition distributions of the expert and the learner, an approach that becomes challenging when","authors_text":"Jian Peng, Tanmay Gangwani, Yuan Zhou","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T05:36:54Z","title":"Imitation Learning from Observations under Transition Model Disparity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11446","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:dfdfc309aa5b33c680a90154c675d824f90201b768757833790531ff0e2f1ac8","target":"record","created_at":"2026-07-05T04:17:27Z","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":"e6f97d7d3f621be48815430302f464a53c5b1a06ef52249ed5e38b41940cc024","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T05:36:54Z","title_canon_sha256":"9812e3ec6c479f56a47c8c98e387393a9a9cce7b8c43d79d25d059a391f3d425"},"schema_version":"1.0","source":{"id":"2204.11446","kind":"arxiv","version":1}},"canonical_sha256":"9389e03d85c6ef273e1ebdf2c3c4d8cabe7b1a6e1c001a5bd1d8bb4c39d40829","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9389e03d85c6ef273e1ebdf2c3c4d8cabe7b1a6e1c001a5bd1d8bb4c39d40829","first_computed_at":"2026-07-05T04:17:27.986695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:27.986695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FxX73Gn+RerHOngdeJZZ+D95Ov0v1x9kPhpKeORrJP95Vcvy7qEbKd8k58Bf46n/Zg8Qm4Z9Za8/PijHOKtPCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:27.987212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.11446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfdfc309aa5b33c680a90154c675d824f90201b768757833790531ff0e2f1ac8","sha256:dc0f5209a8dfd38ce9668ca5b1e8f27ba13a32f74fd2ababd91c0409f7091e38"],"state_sha256":"a4ca1af1c53703666e6530e3df25e8b64a4da2a32cd8974643e98cba89c42a9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8zhwcBWWESuI1ujshYnLPE5QcY9pIBjBmkXuO1CDL9Y2V8EHmWRieH3ZbYbCuFTQP5P5yLxZDD1IV4sYVwebBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T01:30:44.496328Z","bundle_sha256":"141f33263230c6dfa906f53bb4b9e67871ba04b66446af18eb80abe9443112b7"}}