{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WLCVBEMUS4OZDSSN6I3CMUUBCZ","short_pith_number":"pith:WLCVBEMU","canonical_record":{"source":{"id":"2005.09382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-19T12:16:58Z","cross_cats_sorted":[],"title_canon_sha256":"8fb7f0af3a2e1c22c035cf82286c440c7022c59f09b85e99047a190f829b5fa0","abstract_canon_sha256":"8102ceea72f47d9c44c69017df38219ba163f09295bed165b5ef846413cb188c"},"schema_version":"1.0"},"canonical_sha256":"b2c5509194971d91ca4df236265281165094b876f3a376bba048bd0bdadcdc01","source":{"kind":"arxiv","id":"2005.09382","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09382","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09382v1","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09382","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"WLCVBEMUS4OZ","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"WLCVBEMUS4OZDSSN","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"WLCVBEMU","created_at":"2026-07-05T01:03:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WLCVBEMUS4OZDSSN6I3CMUUBCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2005.09382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-19T12:16:58Z","cross_cats_sorted":[],"title_canon_sha256":"8fb7f0af3a2e1c22c035cf82286c440c7022c59f09b85e99047a190f829b5fa0","abstract_canon_sha256":"8102ceea72f47d9c44c69017df38219ba163f09295bed165b5ef846413cb188c"},"schema_version":"1.0"},"canonical_sha256":"b2c5509194971d91ca4df236265281165094b876f3a376bba048bd0bdadcdc01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:49.760270Z","signature_b64":"XQOl0xQBq9vl4cHvd4TQG5YQY0CL/QHPrgSXFQuYWwgcVQu0AX/txhqJe9tGN3dlJ8iuqjPKD5JpAsmPgVmUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2c5509194971d91ca4df236265281165094b876f3a376bba048bd0bdadcdc01","last_reissued_at":"2026-07-05T01:03:49.759820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:49.759820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.09382","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":"2026-07-05T01:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZxLcNBIKtLuCvyNBawOL6iyQMVxOFLy84pdVUhXpe3iuFhOoasz2lliKWbrvZGlPbtUi6+OtNZA6+SLrekKBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:21:23.256767Z"},"content_sha256":"13d6a9bc71b0807d201e71186c82d1e0dcf0f1e502a6d903796ae5317ca3ad37","schema_version":"1.0","event_id":"sha256:13d6a9bc71b0807d201e71186c82d1e0dcf0f1e502a6d903796ae5317ca3ad37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WLCVBEMUS4OZDSSN6I3CMUUBCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Felix Hill, Nathaniel Wong, Sona Mokra, Tim Harley","submitted_at":"2020-05-19T12:16:58Z","abstract_excerpt":"Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human users. However, the optimisation of multi-goal motor policies via deep RL from scratch requires many episodes of experience. Consequently, instruction-following with deep RL typically involves language generated from templates (by an environment simulator), which does not reflect the varied or ambiguous expressions of real users. Here, we propose a conceptual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09382","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.09382/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":"2026-07-05T01:03:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3JAxiKzHN9v5YGISudGNLR3MkUXIDILf43xZIAauaf0vvskKBs+gG8w0HDssw9R4e+9kDjYSZA4eUGWaJH3MAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:21:23.257276Z"},"content_sha256":"cc1df3e1b927c04cb92ad38b5f4f0e8e52558f2208aeb0f90dce7e4be0f395f1","schema_version":"1.0","event_id":"sha256:cc1df3e1b927c04cb92ad38b5f4f0e8e52558f2208aeb0f90dce7e4be0f395f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLCVBEMUS4OZDSSN6I3CMUUBCZ/bundle.json","state_url":"https://pith.science/pith/WLCVBEMUS4OZDSSN6I3CMUUBCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLCVBEMUS4OZDSSN6I3CMUUBCZ/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":"2026-08-07T10:21:23Z","links":{"resolver":"https://pith.science/pith/WLCVBEMUS4OZDSSN6I3CMUUBCZ","bundle":"https://pith.science/pith/WLCVBEMUS4OZDSSN6I3CMUUBCZ/bundle.json","state":"https://pith.science/pith/WLCVBEMUS4OZDSSN6I3CMUUBCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLCVBEMUS4OZDSSN6I3CMUUBCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WLCVBEMUS4OZDSSN6I3CMUUBCZ","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":"8102ceea72f47d9c44c69017df38219ba163f09295bed165b5ef846413cb188c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-19T12:16:58Z","title_canon_sha256":"8fb7f0af3a2e1c22c035cf82286c440c7022c59f09b85e99047a190f829b5fa0"},"schema_version":"1.0","source":{"id":"2005.09382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09382","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09382v1","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09382","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"WLCVBEMUS4OZ","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"WLCVBEMUS4OZDSSN","created_at":"2026-07-05T01:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"WLCVBEMU","created_at":"2026-07-05T01:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:cc1df3e1b927c04cb92ad38b5f4f0e8e52558f2208aeb0f90dce7e4be0f395f1","target":"graph","created_at":"2026-07-05T01:03:49Z","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/2005.09382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an intelligent agent or robot that can be instructed by human users. However, the optimisation of multi-goal motor policies via deep RL from scratch requires many episodes of experience. Consequently, instruction-following with deep RL typically involves language generated from templates (by an environment simulator), which does not reflect the varied or ambiguous expressions of real users. Here, we propose a conceptual","authors_text":"Felix Hill, Nathaniel Wong, Sona Mokra, Tim Harley","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-19T12:16:58Z","title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09382","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":"sha256:13d6a9bc71b0807d201e71186c82d1e0dcf0f1e502a6d903796ae5317ca3ad37","target":"record","created_at":"2026-07-05T01:03:49Z","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":"8102ceea72f47d9c44c69017df38219ba163f09295bed165b5ef846413cb188c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-19T12:16:58Z","title_canon_sha256":"8fb7f0af3a2e1c22c035cf82286c440c7022c59f09b85e99047a190f829b5fa0"},"schema_version":"1.0","source":{"id":"2005.09382","kind":"arxiv","version":1}},"canonical_sha256":"b2c5509194971d91ca4df236265281165094b876f3a376bba048bd0bdadcdc01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2c5509194971d91ca4df236265281165094b876f3a376bba048bd0bdadcdc01","first_computed_at":"2026-07-05T01:03:49.759820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:49.759820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XQOl0xQBq9vl4cHvd4TQG5YQY0CL/QHPrgSXFQuYWwgcVQu0AX/txhqJe9tGN3dlJ8iuqjPKD5JpAsmPgVmUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:49.760270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.09382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13d6a9bc71b0807d201e71186c82d1e0dcf0f1e502a6d903796ae5317ca3ad37","sha256:cc1df3e1b927c04cb92ad38b5f4f0e8e52558f2208aeb0f90dce7e4be0f395f1"],"state_sha256":"92d405f3d87feee56d56f76f1977d68836abebd7092b5a6e50045c53f1873ae8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CtocUdtGKt2BVmFnnjULAPupqIpADHYkKSSbXhVtRZNUZX67URM8mJHq4JoHYEWfzJ6zrJ1uJ7ka35AENM0/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:21:23.261498Z","bundle_sha256":"0d46fed91bb0268bab00a870a49f3fbb32a6dc614d59be69ad8aba1d0c7ab983"}}