{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SUG6MCJZCMOCKARURESN6THZXY","short_pith_number":"pith:SUG6MCJZ","canonical_record":{"source":{"id":"1902.10754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T19:53:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c9a52779d7a4db35ca049fae0573be43e11070a6c4384fe88bf9d6e298ccf65f","abstract_canon_sha256":"2f1188812472570b21cef280f68e23bf7aba66bfdcab9c6f35b1bcd39393a585"},"schema_version":"1.0"},"canonical_sha256":"950de60939131c2502348924df4cf9be2563a3e39d6aa54753cbd6d5682de522","source":{"kind":"arxiv","id":"1902.10754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10754","created_at":"2026-05-17T23:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10754v1","created_at":"2026-05-17T23:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10754","created_at":"2026-05-17T23:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"SUG6MCJZCMOC","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SUG6MCJZCMOCKARU","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SUG6MCJZ","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SUG6MCJZCMOCKARURESN6THZXY","target":"record","payload":{"canonical_record":{"source":{"id":"1902.10754","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T19:53:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c9a52779d7a4db35ca049fae0573be43e11070a6c4384fe88bf9d6e298ccf65f","abstract_canon_sha256":"2f1188812472570b21cef280f68e23bf7aba66bfdcab9c6f35b1bcd39393a585"},"schema_version":"1.0"},"canonical_sha256":"950de60939131c2502348924df4cf9be2563a3e39d6aa54753cbd6d5682de522","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:29.794953Z","signature_b64":"UKc7sUpVAxUMdQu00r9XJP3VfhqdOBQKI8s/73gbNaO/7awxi3b9JX+IHJAgCf5Aau+zb5FFlJHIt2cjx9VXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"950de60939131c2502348924df4cf9be2563a3e39d6aa54753cbd6d5682de522","last_reissued_at":"2026-05-17T23:52:29.794408Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:29.794408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.10754","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":"2026-05-17T23:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yMkXsL9OEHMMkuu+QsVI7+3/o/RZmafGwkcekU9Ozv9QRGm3ySH8DQ0/XQhr23BHL8LyYqIVs5YUnS9fc0KnAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:33:07.006726Z"},"content_sha256":"f966b40bc65ede8dba1abc43e3ff523805160bae351c23a81a1238b982971586","schema_version":"1.0","event_id":"sha256:f966b40bc65ede8dba1abc43e3ff523805160bae351c23a81a1238b982971586"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SUG6MCJZCMOCKARURESN6THZXY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Introspection Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chris R. Serrano, Michael A. Warren","submitted_at":"2019-02-27T19:53:01Z","abstract_excerpt":"Traditional reinforcement learning agents learn from experience, past or present, gained through interaction with their environment. Our approach synthesizes experience, without requiring an agent to interact with their environment, by asking the policy directly \"Are there situations X, Y, and Z, such that in these situations you would select actions A, B, and C?\" In this paper we present Introspection Learning, an algorithm that allows for the asking of these types of questions of neural network policies. Introspection Learning is reinforcement learning algorithm agnostic and the states retur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10754","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":""},"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":"2026-05-17T23:52:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vfBNB7dc9vd+TeM+v6WfouvVMBlmjKghbJ58Oa30a7/+eLoz1XkcvsNnKL/Js1pZWK3HJCIyJ89k81V0EINaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T17:33:07.007370Z"},"content_sha256":"0b3cfcc62ec1ddedd587f31fe4d71e5828f9825df140c531e60737ad6d7f75c5","schema_version":"1.0","event_id":"sha256:0b3cfcc62ec1ddedd587f31fe4d71e5828f9825df140c531e60737ad6d7f75c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SUG6MCJZCMOCKARURESN6THZXY/bundle.json","state_url":"https://pith.science/pith/SUG6MCJZCMOCKARURESN6THZXY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SUG6MCJZCMOCKARURESN6THZXY/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":"2026-06-02T17:33:07Z","links":{"resolver":"https://pith.science/pith/SUG6MCJZCMOCKARURESN6THZXY","bundle":"https://pith.science/pith/SUG6MCJZCMOCKARURESN6THZXY/bundle.json","state":"https://pith.science/pith/SUG6MCJZCMOCKARURESN6THZXY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SUG6MCJZCMOCKARURESN6THZXY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SUG6MCJZCMOCKARURESN6THZXY","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":"2f1188812472570b21cef280f68e23bf7aba66bfdcab9c6f35b1bcd39393a585","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T19:53:01Z","title_canon_sha256":"c9a52779d7a4db35ca049fae0573be43e11070a6c4384fe88bf9d6e298ccf65f"},"schema_version":"1.0","source":{"id":"1902.10754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.10754","created_at":"2026-05-17T23:52:29Z"},{"alias_kind":"arxiv_version","alias_value":"1902.10754v1","created_at":"2026-05-17T23:52:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.10754","created_at":"2026-05-17T23:52:29Z"},{"alias_kind":"pith_short_12","alias_value":"SUG6MCJZCMOC","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SUG6MCJZCMOCKARU","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SUG6MCJZ","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:0b3cfcc62ec1ddedd587f31fe4d71e5828f9825df140c531e60737ad6d7f75c5","target":"graph","created_at":"2026-05-17T23:52:29Z","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":"Traditional reinforcement learning agents learn from experience, past or present, gained through interaction with their environment. Our approach synthesizes experience, without requiring an agent to interact with their environment, by asking the policy directly \"Are there situations X, Y, and Z, such that in these situations you would select actions A, B, and C?\" In this paper we present Introspection Learning, an algorithm that allows for the asking of these types of questions of neural network policies. Introspection Learning is reinforcement learning algorithm agnostic and the states retur","authors_text":"Chris R. Serrano, Michael A. Warren","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T19:53:01Z","title":"Introspection Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.10754","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:f966b40bc65ede8dba1abc43e3ff523805160bae351c23a81a1238b982971586","target":"record","created_at":"2026-05-17T23:52:29Z","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":"2f1188812472570b21cef280f68e23bf7aba66bfdcab9c6f35b1bcd39393a585","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-27T19:53:01Z","title_canon_sha256":"c9a52779d7a4db35ca049fae0573be43e11070a6c4384fe88bf9d6e298ccf65f"},"schema_version":"1.0","source":{"id":"1902.10754","kind":"arxiv","version":1}},"canonical_sha256":"950de60939131c2502348924df4cf9be2563a3e39d6aa54753cbd6d5682de522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"950de60939131c2502348924df4cf9be2563a3e39d6aa54753cbd6d5682de522","first_computed_at":"2026-05-17T23:52:29.794408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:29.794408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UKc7sUpVAxUMdQu00r9XJP3VfhqdOBQKI8s/73gbNaO/7awxi3b9JX+IHJAgCf5Aau+zb5FFlJHIt2cjx9VXDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:29.794953Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.10754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f966b40bc65ede8dba1abc43e3ff523805160bae351c23a81a1238b982971586","sha256:0b3cfcc62ec1ddedd587f31fe4d71e5828f9825df140c531e60737ad6d7f75c5"],"state_sha256":"b0ba0e5f88c6014debfb3c9df76484927452001927de0e21f118d041bfbdf00a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XxSviYnM2REZ0BRFKk+DbmcBUA6EYa/LPMraJa43f29u3z2968PQHRtLF9Qgmn9LisOydT498riN/VNkJG30Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T17:33:07.011118Z","bundle_sha256":"486dc1b6699a420dc34aadd8d83d6207c22966ab6e5b4479f65923af44054858"}}