{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AX3EB2RFKUDT4AGAPRJMA2BAGV","short_pith_number":"pith:AX3EB2RF","canonical_record":{"source":{"id":"1906.03926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T12:17:45Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"782441fbe63fda63b96339cc0a363c9bd4472ec2582203be48e3b63be6ce41f2","abstract_canon_sha256":"570c1ddb07dbd16f86d7a4aaa159a4d06a3e1a780cd627d18cc7444671c2f0ae"},"schema_version":"1.0"},"canonical_sha256":"05f640ea2555073e00c07c52c0682035625d7d30d34a2bcb4bb45c52c75cdd70","source":{"kind":"arxiv","id":"1906.03926","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03926","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03926v1","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03926","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"AX3EB2RFKUDT","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AX3EB2RFKUDT4AGA","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AX3EB2RF","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AX3EB2RFKUDT4AGAPRJMA2BAGV","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T12:17:45Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"782441fbe63fda63b96339cc0a363c9bd4472ec2582203be48e3b63be6ce41f2","abstract_canon_sha256":"570c1ddb07dbd16f86d7a4aaa159a4d06a3e1a780cd627d18cc7444671c2f0ae"},"schema_version":"1.0"},"canonical_sha256":"05f640ea2555073e00c07c52c0682035625d7d30d34a2bcb4bb45c52c75cdd70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:44.519572Z","signature_b64":"ARaUbqvYdmElEqxtRjV3nwgKG6eKpMzpJjH6H32EblZ9B7brOz5Yjg5mh63H8AVNH1cSgJz/bNCLrNExDiTVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f640ea2555073e00c07c52c0682035625d7d30d34a2bcb4bb45c52c75cdd70","last_reissued_at":"2026-05-17T23:43:44.518905Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:44.518905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03926","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":"2026-05-17T23:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gU1O7hBCefjGN8StFVAaJkS/62dEeqADDk7afnEtIcoJzPCCnUNNLJAJlXg7esq+6Ka/d9sl/1Atpat4dqdKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T02:27:23.894489Z"},"content_sha256":"bd70ff47672f627d54fb5a69453cf9d23eb8b697a065b42cd7a416ba038b531b","schema_version":"1.0","event_id":"sha256:bd70ff47672f627d54fb5a69453cf9d23eb8b697a065b42cd7a416ba038b531b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AX3EB2RFKUDT4AGAPRJMA2BAGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Reinforcement Learning Informed by Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Edward Grefenstette, Gregory Farquhar, Jacob Andreas, Jakob Foerster, Jelena Luketina, Nantas Nardelli, Shimon Whiteson, Tim Rockt\\\"aschel","submitted_at":"2019-06-10T12:17:45Z","abstract_excerpt":"To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03926","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":"2026-05-17T23:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pPP8HJ2VOFo7QzslbqmNqJ1vNzUkYvR5e8C/L9BKG1iQxpgADprqIYQdaabbIGLrPh15vOeY/i7hz3RPL7cTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T02:27:23.895155Z"},"content_sha256":"d9918b67d0322a5c1d14b78210d1c19b4c81f262d12e8824e52aa58277b8f174","schema_version":"1.0","event_id":"sha256:d9918b67d0322a5c1d14b78210d1c19b4c81f262d12e8824e52aa58277b8f174"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AX3EB2RFKUDT4AGAPRJMA2BAGV/bundle.json","state_url":"https://pith.science/pith/AX3EB2RFKUDT4AGAPRJMA2BAGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AX3EB2RFKUDT4AGAPRJMA2BAGV/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":"2026-05-21T02:27:23Z","links":{"resolver":"https://pith.science/pith/AX3EB2RFKUDT4AGAPRJMA2BAGV","bundle":"https://pith.science/pith/AX3EB2RFKUDT4AGAPRJMA2BAGV/bundle.json","state":"https://pith.science/pith/AX3EB2RFKUDT4AGAPRJMA2BAGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AX3EB2RFKUDT4AGAPRJMA2BAGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AX3EB2RFKUDT4AGAPRJMA2BAGV","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":"570c1ddb07dbd16f86d7a4aaa159a4d06a3e1a780cd627d18cc7444671c2f0ae","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T12:17:45Z","title_canon_sha256":"782441fbe63fda63b96339cc0a363c9bd4472ec2582203be48e3b63be6ce41f2"},"schema_version":"1.0","source":{"id":"1906.03926","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03926","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03926v1","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03926","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"AX3EB2RFKUDT","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"AX3EB2RFKUDT4AGA","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"AX3EB2RF","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:d9918b67d0322a5c1d14b78210d1c19b4c81f262d12e8824e52aa58277b8f174","target":"graph","created_at":"2026-05-17T23:43:44Z","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":"To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction","authors_text":"Edward Grefenstette, Gregory Farquhar, Jacob Andreas, Jakob Foerster, Jelena Luketina, Nantas Nardelli, Shimon Whiteson, Tim Rockt\\\"aschel","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T12:17:45Z","title":"A Survey of Reinforcement Learning Informed by Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03926","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:bd70ff47672f627d54fb5a69453cf9d23eb8b697a065b42cd7a416ba038b531b","target":"record","created_at":"2026-05-17T23:43:44Z","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":"570c1ddb07dbd16f86d7a4aaa159a4d06a3e1a780cd627d18cc7444671c2f0ae","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T12:17:45Z","title_canon_sha256":"782441fbe63fda63b96339cc0a363c9bd4472ec2582203be48e3b63be6ce41f2"},"schema_version":"1.0","source":{"id":"1906.03926","kind":"arxiv","version":1}},"canonical_sha256":"05f640ea2555073e00c07c52c0682035625d7d30d34a2bcb4bb45c52c75cdd70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05f640ea2555073e00c07c52c0682035625d7d30d34a2bcb4bb45c52c75cdd70","first_computed_at":"2026-05-17T23:43:44.518905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:44.518905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ARaUbqvYdmElEqxtRjV3nwgKG6eKpMzpJjH6H32EblZ9B7brOz5Yjg5mh63H8AVNH1cSgJz/bNCLrNExDiTVCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:44.519572Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03926","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd70ff47672f627d54fb5a69453cf9d23eb8b697a065b42cd7a416ba038b531b","sha256:d9918b67d0322a5c1d14b78210d1c19b4c81f262d12e8824e52aa58277b8f174"],"state_sha256":"67cf0bee963a9ae755c998051739a3fb0e539eb7c63685874996f36285193354"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nRKoCre2d8fS6DG+fOtzl2KnuvaRE7FRvtIgjua4O3WQLwojpG6NE0rFkN7enysopJearnP/flmyw0bUekz8BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T02:27:23.898590Z","bundle_sha256":"9f68f912e582eba0d04d2a47c3c22141643119a46034ec783f7ad766a5bee33c"}}