{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZWNBR7QIRG42FN6CMP3ICGVSXI","short_pith_number":"pith:ZWNBR7QI","canonical_record":{"source":{"id":"1805.11686","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T19:55:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"37e1d7abb32a9af9d109a5c12e1006ace3de0d67656dec571d7dc17746038ac3","abstract_canon_sha256":"c212800b73f56351d4452e7d4362b063f0a65ccff60524cfb8f7c4a6efa00708"},"schema_version":"1.0"},"canonical_sha256":"cd9a18fe0889b9a2b7c263f6811ab2ba02c2331efa48d85cd919a350caaefc5c","source":{"kind":"arxiv","id":"1805.11686","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11686","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11686v3","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11686","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZWNBR7QIRG42","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZWNBR7QIRG42FN6C","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZWNBR7QI","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZWNBR7QIRG42FN6CMP3ICGVSXI","target":"record","payload":{"canonical_record":{"source":{"id":"1805.11686","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T19:55:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"37e1d7abb32a9af9d109a5c12e1006ace3de0d67656dec571d7dc17746038ac3","abstract_canon_sha256":"c212800b73f56351d4452e7d4362b063f0a65ccff60524cfb8f7c4a6efa00708"},"schema_version":"1.0"},"canonical_sha256":"cd9a18fe0889b9a2b7c263f6811ab2ba02c2331efa48d85cd919a350caaefc5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:01.808645Z","signature_b64":"+9G1F/cLBFPhCBicDcUAtxDnraYwGlUl4zeBVaMNkFBsBdsKOa9WaR0RC3rdqUtXoWxx2jWOcCNvOC8h0aYxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd9a18fe0889b9a2b7c263f6811ab2ba02c2331efa48d85cd919a350caaefc5c","last_reissued_at":"2026-05-18T00:01:01.808100Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:01.808100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.11686","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":"2026-05-18T00:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d440XKZucEcQ83aBOAgLrRq+LfHYhrkGh/YE6MK7njuSG0v+c7/CiK60fAkmidlaVx//XLYVKVgk/CnfuRY5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:29:53.542908Z"},"content_sha256":"a6c70f4ae91075c9c2787cc8af106c3fe2b36c631b621628dd65e1d6d90487be","schema_version":"1.0","event_id":"sha256:a6c70f4ae91075c9c2787cc8af106c3fe2b36c631b621628dd65e1d6d90487be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZWNBR7QIRG42FN6CMP3ICGVSXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Avi Singh, Dibya Ghosh, Justin Fu, Larry Yang, Sergey Levine","submitted_at":"2018-05-29T19:55:10Z","abstract_excerpt":"The design of a reward function often poses a major practical challenge to real-world applications of reinforcement learning. Approaches such as inverse reinforcement learning attempt to overcome this challenge, but require expert demonstrations, which can be difficult or expensive to obtain in practice. We propose variational inverse control with events (VICE), which generalizes inverse reinforcement learning methods to cases where full demonstrations are not needed, such as when only samples of desired goal states are available. Our method is grounded in an alternative perspective on control"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11686","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":"2026-05-18T00:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PqurNl9qOdUNr4DPj+Bi0tKOEiKWjuJZXXRrHucGIG2iWW5h3eZ82M85WHEsi91yYIWgxr8UsBJPERhbM3ESAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:29:53.543270Z"},"content_sha256":"0b230bde8347eec7b7660f4724ccba873fb13c168bda9475d237e6adde0c3685","schema_version":"1.0","event_id":"sha256:0b230bde8347eec7b7660f4724ccba873fb13c168bda9475d237e6adde0c3685"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZWNBR7QIRG42FN6CMP3ICGVSXI/bundle.json","state_url":"https://pith.science/pith/ZWNBR7QIRG42FN6CMP3ICGVSXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZWNBR7QIRG42FN6CMP3ICGVSXI/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":"2026-05-29T20:29:53Z","links":{"resolver":"https://pith.science/pith/ZWNBR7QIRG42FN6CMP3ICGVSXI","bundle":"https://pith.science/pith/ZWNBR7QIRG42FN6CMP3ICGVSXI/bundle.json","state":"https://pith.science/pith/ZWNBR7QIRG42FN6CMP3ICGVSXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZWNBR7QIRG42FN6CMP3ICGVSXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZWNBR7QIRG42FN6CMP3ICGVSXI","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":"c212800b73f56351d4452e7d4362b063f0a65ccff60524cfb8f7c4a6efa00708","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T19:55:10Z","title_canon_sha256":"37e1d7abb32a9af9d109a5c12e1006ace3de0d67656dec571d7dc17746038ac3"},"schema_version":"1.0","source":{"id":"1805.11686","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11686","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11686v3","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11686","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZWNBR7QIRG42","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZWNBR7QIRG42FN6C","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZWNBR7QI","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:0b230bde8347eec7b7660f4724ccba873fb13c168bda9475d237e6adde0c3685","target":"graph","created_at":"2026-05-18T00:01:01Z","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":"The design of a reward function often poses a major practical challenge to real-world applications of reinforcement learning. Approaches such as inverse reinforcement learning attempt to overcome this challenge, but require expert demonstrations, which can be difficult or expensive to obtain in practice. We propose variational inverse control with events (VICE), which generalizes inverse reinforcement learning methods to cases where full demonstrations are not needed, such as when only samples of desired goal states are available. Our method is grounded in an alternative perspective on control","authors_text":"Avi Singh, Dibya Ghosh, Justin Fu, Larry Yang, Sergey Levine","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T19:55:10Z","title":"Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11686","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:a6c70f4ae91075c9c2787cc8af106c3fe2b36c631b621628dd65e1d6d90487be","target":"record","created_at":"2026-05-18T00:01:01Z","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":"c212800b73f56351d4452e7d4362b063f0a65ccff60524cfb8f7c4a6efa00708","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-29T19:55:10Z","title_canon_sha256":"37e1d7abb32a9af9d109a5c12e1006ace3de0d67656dec571d7dc17746038ac3"},"schema_version":"1.0","source":{"id":"1805.11686","kind":"arxiv","version":3}},"canonical_sha256":"cd9a18fe0889b9a2b7c263f6811ab2ba02c2331efa48d85cd919a350caaefc5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd9a18fe0889b9a2b7c263f6811ab2ba02c2331efa48d85cd919a350caaefc5c","first_computed_at":"2026-05-18T00:01:01.808100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:01.808100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+9G1F/cLBFPhCBicDcUAtxDnraYwGlUl4zeBVaMNkFBsBdsKOa9WaR0RC3rdqUtXoWxx2jWOcCNvOC8h0aYxCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:01.808645Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11686","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6c70f4ae91075c9c2787cc8af106c3fe2b36c631b621628dd65e1d6d90487be","sha256:0b230bde8347eec7b7660f4724ccba873fb13c168bda9475d237e6adde0c3685"],"state_sha256":"e2d8c172042e96e12e8339854056662904e55e856d89f5808acb24d19af11b28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1GSNoYLAUtu5xRmq1RiqDZJkygPIQ6+tD95UgEC3dlGJnJmoqSuJolR8pcZUHxq0wmRFw1j0YRx6mMD5lzUMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T20:29:53.545267Z","bundle_sha256":"2285c74c1ff89b37613c6306b6a8d11e3e3eef997c9122afaec7699d59aa37ff"}}