{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PFCWD2NWVFENTAINV3KE3J43GO","short_pith_number":"pith:PFCWD2NW","canonical_record":{"source":{"id":"2302.04449","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T05:47:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5846f9c0aa0c5817c097c8599ac189b5d91b7543da2d33fcedaab8829c3bf1a9","abstract_canon_sha256":"cdb9eb2dbd9b0e22c4c0262e713ff25da5651988f63bfd410460d82e6815e602"},"schema_version":"1.0"},"canonical_sha256":"794561e9b6a948d9810daed44da79b33b4dd0d8330135467f26a6e847e33eeb3","source":{"kind":"arxiv","id":"2302.04449","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04449","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04449v4","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04449","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"PFCWD2NWVFEN","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"pith_short_16","alias_value":"PFCWD2NWVFENTAIN","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"pith_short_8","alias_value":"PFCWD2NW","created_at":"2026-07-05T08:46:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PFCWD2NWVFENTAINV3KE3J43GO","target":"record","payload":{"canonical_record":{"source":{"id":"2302.04449","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T05:47:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"5846f9c0aa0c5817c097c8599ac189b5d91b7543da2d33fcedaab8829c3bf1a9","abstract_canon_sha256":"cdb9eb2dbd9b0e22c4c0262e713ff25da5651988f63bfd410460d82e6815e602"},"schema_version":"1.0"},"canonical_sha256":"794561e9b6a948d9810daed44da79b33b4dd0d8330135467f26a6e847e33eeb3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:16.146136Z","signature_b64":"90x5PwaNCVJm/NF2RCQ2D4w9wY4zfjhdW1/vuqUazvApb8GW4n8Bg7Iai4hJYh6bMBtMD5nfogd3DcbozyglDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"794561e9b6a948d9810daed44da79b33b4dd0d8330135467f26a6e847e33eeb3","last_reissued_at":"2026-07-05T08:46:16.145597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:16.145597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.04449","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:46:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9ehmM9+OQbKliHAQk6yIwx2zedDq3qaD7075gV/MmVo0kdfgU2yog/GN56OCvwiSSvM2pkeIGD8cIjfT5m3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:37:16.799339Z"},"content_sha256":"e08cbd259c2bb1d0d88dfc91544985de5f189cde87041b0f8811604ecd611da8","schema_version":"1.0","event_id":"sha256:e08cbd259c2bb1d0d88dfc91544985de5f189cde87041b0f8811604ecd611da8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PFCWD2NWVFENTAINV3KE3J43GO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Amos Azaria, Paul Pu Liang, Tom M. Mitchell, Yewen Fan, Yuanzhi Li, Yue Wu","submitted_at":"2023-02-09T05:47:03Z","abstract_excerpt":"High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and reward structures. Therefore, we hypothesize that the ability to utilize human-written instruction manuals to assist learning policies for specific tasks should lead to a more efficient and better-perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04449","kind":"arxiv","version":4},"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/2302.04449/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":"2026-07-05T08:46:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GksSM0Mgg4JNL3E/EHwmjz6b89LUgWFBDG169kls2twt+B+Ml+OeGeTyszzGplpj9WlB54UJgAzqdjS7LG1GDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:37:16.799880Z"},"content_sha256":"3f8a43b9c738403657def6745c4f6fec8d919db1ea4b79c2fb3cdc2d3583c1fb","schema_version":"1.0","event_id":"sha256:3f8a43b9c738403657def6745c4f6fec8d919db1ea4b79c2fb3cdc2d3583c1fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PFCWD2NWVFENTAINV3KE3J43GO/bundle.json","state_url":"https://pith.science/pith/PFCWD2NWVFENTAINV3KE3J43GO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PFCWD2NWVFENTAINV3KE3J43GO/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":"2026-08-15T03:37:16Z","links":{"resolver":"https://pith.science/pith/PFCWD2NWVFENTAINV3KE3J43GO","bundle":"https://pith.science/pith/PFCWD2NWVFENTAINV3KE3J43GO/bundle.json","state":"https://pith.science/pith/PFCWD2NWVFENTAINV3KE3J43GO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PFCWD2NWVFENTAINV3KE3J43GO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PFCWD2NWVFENTAINV3KE3J43GO","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":"cdb9eb2dbd9b0e22c4c0262e713ff25da5651988f63bfd410460d82e6815e602","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T05:47:03Z","title_canon_sha256":"5846f9c0aa0c5817c097c8599ac189b5d91b7543da2d33fcedaab8829c3bf1a9"},"schema_version":"1.0","source":{"id":"2302.04449","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04449","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04449v4","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04449","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"PFCWD2NWVFEN","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"pith_short_16","alias_value":"PFCWD2NWVFENTAIN","created_at":"2026-07-05T08:46:16Z"},{"alias_kind":"pith_short_8","alias_value":"PFCWD2NW","created_at":"2026-07-05T08:46:16Z"}],"graph_snapshots":[{"event_id":"sha256:3f8a43b9c738403657def6745c4f6fec8d919db1ea4b79c2fb3cdc2d3583c1fb","target":"graph","created_at":"2026-07-05T08:46:16Z","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/2302.04449/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and policies or task-specific environmental dynamics and reward structures. Therefore, we hypothesize that the ability to utilize human-written instruction manuals to assist learning policies for specific tasks should lead to a more efficient and better-perfo","authors_text":"Amos Azaria, Paul Pu Liang, Tom M. Mitchell, Yewen Fan, Yuanzhi Li, Yue Wu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T05:47:03Z","title":"Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04449","kind":"arxiv","version":4},"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:e08cbd259c2bb1d0d88dfc91544985de5f189cde87041b0f8811604ecd611da8","target":"record","created_at":"2026-07-05T08:46:16Z","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":"cdb9eb2dbd9b0e22c4c0262e713ff25da5651988f63bfd410460d82e6815e602","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-09T05:47:03Z","title_canon_sha256":"5846f9c0aa0c5817c097c8599ac189b5d91b7543da2d33fcedaab8829c3bf1a9"},"schema_version":"1.0","source":{"id":"2302.04449","kind":"arxiv","version":4}},"canonical_sha256":"794561e9b6a948d9810daed44da79b33b4dd0d8330135467f26a6e847e33eeb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"794561e9b6a948d9810daed44da79b33b4dd0d8330135467f26a6e847e33eeb3","first_computed_at":"2026-07-05T08:46:16.145597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:16.145597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"90x5PwaNCVJm/NF2RCQ2D4w9wY4zfjhdW1/vuqUazvApb8GW4n8Bg7Iai4hJYh6bMBtMD5nfogd3DcbozyglDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:16.146136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.04449","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e08cbd259c2bb1d0d88dfc91544985de5f189cde87041b0f8811604ecd611da8","sha256:3f8a43b9c738403657def6745c4f6fec8d919db1ea4b79c2fb3cdc2d3583c1fb"],"state_sha256":"4980e60ecaa6dfcd6e0c722c84c0db89c327560fb2ad318eeb5055fe170377a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2kafFkdst8tWdUC2YdKqG6TnAfcIEJTVz3iwwyC6OYNYVxGJBl+OrDP7xeVWohgHuSlcqdANHK+CNsj/wlaLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T03:37:16.806032Z","bundle_sha256":"3eb14fdbbf1ae4895f99979396781fd1b67370d0bc3cbe4445e2897e6ffb3af5"}}