{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:R5BJS6ZFNEPIDWL7EMM6ZDQ73C","short_pith_number":"pith:R5BJS6ZF","canonical_record":{"source":{"id":"1704.05539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-18T21:31:29Z","cross_cats_sorted":[],"title_canon_sha256":"2db2155adffd757c13f7249d8b1d6ef100250a6b5a7fa6af6f8e6e03af09e38e","abstract_canon_sha256":"be3e8ebfaa8ee85f3e6626e3b6b78a5723efded865a21d52b97f497f1d570dfd"},"schema_version":"1.0"},"canonical_sha256":"8f42997b25691e81d97f2319ec8e1fd8a6b6247893063af70d6640e8e06724c2","source":{"kind":"arxiv","id":"1704.05539","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.05539","created_at":"2026-05-18T00:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1704.05539v1","created_at":"2026-05-18T00:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05539","created_at":"2026-05-18T00:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"R5BJS6ZFNEPI","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R5BJS6ZFNEPIDWL7","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R5BJS6ZF","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:R5BJS6ZFNEPIDWL7EMM6ZDQ73C","target":"record","payload":{"canonical_record":{"source":{"id":"1704.05539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-18T21:31:29Z","cross_cats_sorted":[],"title_canon_sha256":"2db2155adffd757c13f7249d8b1d6ef100250a6b5a7fa6af6f8e6e03af09e38e","abstract_canon_sha256":"be3e8ebfaa8ee85f3e6626e3b6b78a5723efded865a21d52b97f497f1d570dfd"},"schema_version":"1.0"},"canonical_sha256":"8f42997b25691e81d97f2319ec8e1fd8a6b6247893063af70d6640e8e06724c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:07.177907Z","signature_b64":"PBU81CL5wDp4VCI945l5W9IdOK0cT1+/LhQYEnCo0dtNPV7fRLUJ1D0Jnk0jiyi0H89koNj2OfRgDWvduuAlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f42997b25691e81d97f2319ec8e1fd8a6b6247893063af70d6640e8e06724c2","last_reissued_at":"2026-05-18T00:46:07.177525Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:07.177525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.05539","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":"2026-05-18T00:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oecs2WGXmaNdXIC3qir6oINQmM8gaBLZI1hkj+RZ54CZaPLGBO39iRMntIwhYJ+C1lBDDPrAz3wTpSL7qdDFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:19:50.123439Z"},"content_sha256":"689e35dcdb795ed352d9bcc91f0614211e3cc757208e861ef563af462a0c1615","schema_version":"1.0","event_id":"sha256:689e35dcdb795ed352d9bcc91f0614211e3cc757208e861ef563af462a0c1615"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:R5BJS6ZFNEPIDWL7EMM6ZDQ73C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beating Atari with Natural Language Guided Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Sosa, Christopher Sauer, Russell Kaplan","submitted_at":"2017-04-18T21:31:29Z","abstract_excerpt":"We introduce the first deep reinforcement learning agent that learns to beat Atari games with the aid of natural language instructions. The agent uses a multimodal embedding between environment observations and natural language to self-monitor progress through a list of English instructions, granting itself reward for completing instructions in addition to increasing the game score. Our agent significantly outperforms Deep Q-Networks (DQNs), Asynchronous Advantage Actor-Critic (A3C) agents, and the best agents posted to OpenAI Gym on what is often considered the hardest Atari 2600 environment:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.05539","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":"2026-05-18T00:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MYtw7P8qX0b6BQx3NHNKQCnmq1n+iuiq1X2ip8WyTrfM7R2mL37J2eH723CKpscuzHKAdV5tMrNfp7069/RhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:19:50.124311Z"},"content_sha256":"9f822df3fa1fa4a1eda0d4d69c1cdd6774674b831d5bb901c9fdbdef2c12773d","schema_version":"1.0","event_id":"sha256:9f822df3fa1fa4a1eda0d4d69c1cdd6774674b831d5bb901c9fdbdef2c12773d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5BJS6ZFNEPIDWL7EMM6ZDQ73C/bundle.json","state_url":"https://pith.science/pith/R5BJS6ZFNEPIDWL7EMM6ZDQ73C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5BJS6ZFNEPIDWL7EMM6ZDQ73C/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":"2026-08-14T03:19:50Z","links":{"resolver":"https://pith.science/pith/R5BJS6ZFNEPIDWL7EMM6ZDQ73C","bundle":"https://pith.science/pith/R5BJS6ZFNEPIDWL7EMM6ZDQ73C/bundle.json","state":"https://pith.science/pith/R5BJS6ZFNEPIDWL7EMM6ZDQ73C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5BJS6ZFNEPIDWL7EMM6ZDQ73C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:R5BJS6ZFNEPIDWL7EMM6ZDQ73C","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":"be3e8ebfaa8ee85f3e6626e3b6b78a5723efded865a21d52b97f497f1d570dfd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-18T21:31:29Z","title_canon_sha256":"2db2155adffd757c13f7249d8b1d6ef100250a6b5a7fa6af6f8e6e03af09e38e"},"schema_version":"1.0","source":{"id":"1704.05539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.05539","created_at":"2026-05-18T00:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1704.05539v1","created_at":"2026-05-18T00:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05539","created_at":"2026-05-18T00:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"R5BJS6ZFNEPI","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R5BJS6ZFNEPIDWL7","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R5BJS6ZF","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:9f822df3fa1fa4a1eda0d4d69c1cdd6774674b831d5bb901c9fdbdef2c12773d","target":"graph","created_at":"2026-05-18T00:46:07Z","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":"We introduce the first deep reinforcement learning agent that learns to beat Atari games with the aid of natural language instructions. The agent uses a multimodal embedding between environment observations and natural language to self-monitor progress through a list of English instructions, granting itself reward for completing instructions in addition to increasing the game score. Our agent significantly outperforms Deep Q-Networks (DQNs), Asynchronous Advantage Actor-Critic (A3C) agents, and the best agents posted to OpenAI Gym on what is often considered the hardest Atari 2600 environment:","authors_text":"Alexander Sosa, Christopher Sauer, Russell Kaplan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-18T21:31:29Z","title":"Beating Atari with Natural Language Guided Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.05539","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":"sha256:689e35dcdb795ed352d9bcc91f0614211e3cc757208e861ef563af462a0c1615","target":"record","created_at":"2026-05-18T00:46:07Z","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":"be3e8ebfaa8ee85f3e6626e3b6b78a5723efded865a21d52b97f497f1d570dfd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-04-18T21:31:29Z","title_canon_sha256":"2db2155adffd757c13f7249d8b1d6ef100250a6b5a7fa6af6f8e6e03af09e38e"},"schema_version":"1.0","source":{"id":"1704.05539","kind":"arxiv","version":1}},"canonical_sha256":"8f42997b25691e81d97f2319ec8e1fd8a6b6247893063af70d6640e8e06724c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f42997b25691e81d97f2319ec8e1fd8a6b6247893063af70d6640e8e06724c2","first_computed_at":"2026-05-18T00:46:07.177525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:07.177525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PBU81CL5wDp4VCI945l5W9IdOK0cT1+/LhQYEnCo0dtNPV7fRLUJ1D0Jnk0jiyi0H89koNj2OfRgDWvduuAlCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:07.177907Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.05539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:689e35dcdb795ed352d9bcc91f0614211e3cc757208e861ef563af462a0c1615","sha256:9f822df3fa1fa4a1eda0d4d69c1cdd6774674b831d5bb901c9fdbdef2c12773d"],"state_sha256":"958fd2d4354d8689ac84c1fa26600aaef2042b39101d075bb75ca0e254db07d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UEas4V0w+TaP0XCgk4VdC/C7zWrnR5P4PHyV3CGBgAsE2cBX7h8ob9Mi5fUItfWTwgx2daPN422BIsUlr5jVCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T03:19:50.131870Z","bundle_sha256":"cbe74bc96f567a4957addd155bde1c02eee80fbe3f65b61e60202d41efbfc5bd"}}