{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QVFUFJEH4JNSNNXQWRB2ECSGKP","short_pith_number":"pith:QVFUFJEH","canonical_record":{"source":{"id":"1805.07914","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T06:49:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c67b1494675f945c5bc1d7c75facb49d36fae4567841d875d492163509be85bc","abstract_canon_sha256":"9342c53c467d4c87446fa679ab81e6f6c4a5346cb318929ac9aa130cf694230c"},"schema_version":"1.0"},"canonical_sha256":"854b42a487e25b26b6f0b443a20a4653e66743b60df67256e7b74a954f7beded","source":{"kind":"arxiv","id":"1805.07914","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07914","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07914v3","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07914","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"pith_short_12","alias_value":"QVFUFJEH4JNS","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QVFUFJEH4JNSNNXQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QVFUFJEH","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QVFUFJEH4JNSNNXQWRB2ECSGKP","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07914","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T06:49:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c67b1494675f945c5bc1d7c75facb49d36fae4567841d875d492163509be85bc","abstract_canon_sha256":"9342c53c467d4c87446fa679ab81e6f6c4a5346cb318929ac9aa130cf694230c"},"schema_version":"1.0"},"canonical_sha256":"854b42a487e25b26b6f0b443a20a4653e66743b60df67256e7b74a954f7beded","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:30.464772Z","signature_b64":"qPzkcEmbVbG4lxaU8DxKJxTaLaJ7SmRXU2YFs3T7Xzt4+Ri7qgRmdbOvDXrFJHMX8v9DqIilrTfaOFgqLc6tDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854b42a487e25b26b6f0b443a20a4653e66743b60df67256e7b74a954f7beded","last_reissued_at":"2026-05-17T23:46:30.463958Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:30.463958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07914","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sn1w/eHfRnpDN77jNTPcjonb4Bw25qO/Il2pNnVItjq6mfJQ9QUjhkBGgVHe97hlwWTPbTSrQT87hM4G5YAHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:09:20.456741Z"},"content_sha256":"d9b174459e49dfc4a7e84997e740af0eefa1297631e8fffa2775a9d3c80060f7","schema_version":"1.0","event_id":"sha256:d9b174459e49dfc4a7e84997e740af0eefa1297631e8fffa2775a9d3c80060f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QVFUFJEH4JNSNNXQWRB2ECSGKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imitating Latent Policies from Observation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashley D. Edwards, Charles L. Isbell, Himanshu Sahni, Yannick Schroecker","submitted_at":"2018-05-21T06:49:57Z","abstract_excerpt":"In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while simultaneously predicting their likelihood. We then outline an action alignment procedure that leverages a small amount of environment interactions to determine a mapping between the latent and real-world actions. We show that this corrected labeling can be used for imitating the observed behavior, even though no expert actions are given. We evaluate our approach within"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07914","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:46:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8CBYyszsITaIFhB/A98U+3AHuGypMi4NTcdDUP68VvscjsK/JfwFwxRMwm7/SEubWQtOAzuwbNj7Q367h/9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T14:09:20.457542Z"},"content_sha256":"cec27edd87f84a60b6d3fe0a35aa967d688b06168cadaec2f43ac9a3f86256b9","schema_version":"1.0","event_id":"sha256:cec27edd87f84a60b6d3fe0a35aa967d688b06168cadaec2f43ac9a3f86256b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QVFUFJEH4JNSNNXQWRB2ECSGKP/bundle.json","state_url":"https://pith.science/pith/QVFUFJEH4JNSNNXQWRB2ECSGKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QVFUFJEH4JNSNNXQWRB2ECSGKP/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":"2026-06-10T14:09:20Z","links":{"resolver":"https://pith.science/pith/QVFUFJEH4JNSNNXQWRB2ECSGKP","bundle":"https://pith.science/pith/QVFUFJEH4JNSNNXQWRB2ECSGKP/bundle.json","state":"https://pith.science/pith/QVFUFJEH4JNSNNXQWRB2ECSGKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QVFUFJEH4JNSNNXQWRB2ECSGKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QVFUFJEH4JNSNNXQWRB2ECSGKP","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":"9342c53c467d4c87446fa679ab81e6f6c4a5346cb318929ac9aa130cf694230c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T06:49:57Z","title_canon_sha256":"c67b1494675f945c5bc1d7c75facb49d36fae4567841d875d492163509be85bc"},"schema_version":"1.0","source":{"id":"1805.07914","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07914","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07914v3","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07914","created_at":"2026-05-17T23:46:30Z"},{"alias_kind":"pith_short_12","alias_value":"QVFUFJEH4JNS","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QVFUFJEH4JNSNNXQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QVFUFJEH","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:cec27edd87f84a60b6d3fe0a35aa967d688b06168cadaec2f43ac9a3f86256b9","target":"graph","created_at":"2026-05-17T23:46:30Z","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"},"paper":{"abstract_excerpt":"In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while simultaneously predicting their likelihood. We then outline an action alignment procedure that leverages a small amount of environment interactions to determine a mapping between the latent and real-world actions. We show that this corrected labeling can be used for imitating the observed behavior, even though no expert actions are given. We evaluate our approach within","authors_text":"Ashley D. Edwards, Charles L. Isbell, Himanshu Sahni, Yannick Schroecker","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T06:49:57Z","title":"Imitating Latent Policies from Observation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07914","kind":"arxiv","version":3},"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:d9b174459e49dfc4a7e84997e740af0eefa1297631e8fffa2775a9d3c80060f7","target":"record","created_at":"2026-05-17T23:46:30Z","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":"9342c53c467d4c87446fa679ab81e6f6c4a5346cb318929ac9aa130cf694230c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T06:49:57Z","title_canon_sha256":"c67b1494675f945c5bc1d7c75facb49d36fae4567841d875d492163509be85bc"},"schema_version":"1.0","source":{"id":"1805.07914","kind":"arxiv","version":3}},"canonical_sha256":"854b42a487e25b26b6f0b443a20a4653e66743b60df67256e7b74a954f7beded","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"854b42a487e25b26b6f0b443a20a4653e66743b60df67256e7b74a954f7beded","first_computed_at":"2026-05-17T23:46:30.463958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:30.463958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qPzkcEmbVbG4lxaU8DxKJxTaLaJ7SmRXU2YFs3T7Xzt4+Ri7qgRmdbOvDXrFJHMX8v9DqIilrTfaOFgqLc6tDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:30.464772Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07914","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9b174459e49dfc4a7e84997e740af0eefa1297631e8fffa2775a9d3c80060f7","sha256:cec27edd87f84a60b6d3fe0a35aa967d688b06168cadaec2f43ac9a3f86256b9"],"state_sha256":"9f9ad833901d6df7e3405fdab30c32b945697b9b493944518d9fe161fb7132f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9V2AGYTlqAim4W1AlevVbF23ZRs82SSs1P/6FicaDU/Y9ycQCNqb7ZGZ8nbBBXo8H6CDv9LAbdd4ZWHtrukMDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T14:09:20.461454Z","bundle_sha256":"af19e16954458978b73080d76fd73e5a11c80c4a6842d847376f39ad60d1b046"}}