{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:WZ7TQSDR3REZJ25LHRGTPRZG4W","short_pith_number":"pith:WZ7TQSDR","canonical_record":{"source":{"id":"1511.04636","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-14T23:30:39Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"84c761ba1d93973aa432022cc33ecf42cbecb30b6308eea2db17fea947aed71d","abstract_canon_sha256":"33d17478addf71e03b062a2b403845aeadc15a7b77d100ab80a7fe73e206fefa"},"schema_version":"1.0"},"canonical_sha256":"b67f384871dc4994ebab3c4d37c726e5acf752c6d984c701447fd3a9a5481719","source":{"kind":"arxiv","id":"1511.04636","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.04636","created_at":"2026-05-18T01:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"1511.04636v5","created_at":"2026-05-18T01:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04636","created_at":"2026-05-18T01:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"WZ7TQSDR3REZ","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WZ7TQSDR3REZJ25L","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WZ7TQSDR","created_at":"2026-05-18T12:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:WZ7TQSDR3REZJ25LHRGTPRZG4W","target":"record","payload":{"canonical_record":{"source":{"id":"1511.04636","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-14T23:30:39Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"84c761ba1d93973aa432022cc33ecf42cbecb30b6308eea2db17fea947aed71d","abstract_canon_sha256":"33d17478addf71e03b062a2b403845aeadc15a7b77d100ab80a7fe73e206fefa"},"schema_version":"1.0"},"canonical_sha256":"b67f384871dc4994ebab3c4d37c726e5acf752c6d984c701447fd3a9a5481719","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:43.351874Z","signature_b64":"ApdFgpSFSJiB2vMBf4NFE8diF+3dh4jggeFNuj9pki3h1YbagSMuEV1nZ0MQJxrj0VHMOh1Mafyi/uN96HBfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b67f384871dc4994ebab3c4d37c726e5acf752c6d984c701447fd3a9a5481719","last_reissued_at":"2026-05-18T01:12:43.351531Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:43.351531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.04636","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4TRe2yxFPAgYu7wI3G8zpPXryKHsH5ZEAyccoCQ+w0iskCz3kDIe7JbEoJcrjFvUDSLp8sIM1wwH0bnPDdwtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:41:31.589174Z"},"content_sha256":"09a4a87361d1001de4d6be2b293c1332f886a24811a04cb65f4d71b25f75569a","schema_version":"1.0","event_id":"sha256:09a4a87361d1001de4d6be2b293c1332f886a24811a04cb65f4d71b25f75569a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:WZ7TQSDR3REZJ25LHRGTPRZG4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with a Natural Language Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jianfeng Gao, Jianshu Chen, Ji He, Li Deng, Lihong Li, Mari Ostendorf, Xiaodong He","submitted_at":"2015-11-14T23:30:39Z","abstract_excerpt":"This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-based games. Termed a deep reinforcement relevance network (DRRN), the architecture represents action and state spaces with separate embedding vectors, which are combined with an interaction function to approximate the Q-function in reinforcement learning. We evaluate the DRRN on two popular text games, showing superior performance over other deep Q-learning architectures. Experiments with paraphrased acti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04636","kind":"arxiv","version":5},"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":"2026-05-18T01:12:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZ9USCfo1A5t2DdCjVbFugVjiu1iOf2vzeDDGBJGdbwjMyn6u0sZLnUETmYyjhxdAtItnfTeSjpqAj6D/U5WCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:41:31.589542Z"},"content_sha256":"f19e84ea19e0671d660a8ea60578128dcc33966c4f01c9aa6087ef98b1bde21f","schema_version":"1.0","event_id":"sha256:f19e84ea19e0671d660a8ea60578128dcc33966c4f01c9aa6087ef98b1bde21f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZ7TQSDR3REZJ25LHRGTPRZG4W/bundle.json","state_url":"https://pith.science/pith/WZ7TQSDR3REZJ25LHRGTPRZG4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZ7TQSDR3REZJ25LHRGTPRZG4W/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":"2026-05-28T14:41:31Z","links":{"resolver":"https://pith.science/pith/WZ7TQSDR3REZJ25LHRGTPRZG4W","bundle":"https://pith.science/pith/WZ7TQSDR3REZJ25LHRGTPRZG4W/bundle.json","state":"https://pith.science/pith/WZ7TQSDR3REZJ25LHRGTPRZG4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZ7TQSDR3REZJ25LHRGTPRZG4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:WZ7TQSDR3REZJ25LHRGTPRZG4W","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":"33d17478addf71e03b062a2b403845aeadc15a7b77d100ab80a7fe73e206fefa","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-14T23:30:39Z","title_canon_sha256":"84c761ba1d93973aa432022cc33ecf42cbecb30b6308eea2db17fea947aed71d"},"schema_version":"1.0","source":{"id":"1511.04636","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.04636","created_at":"2026-05-18T01:12:43Z"},{"alias_kind":"arxiv_version","alias_value":"1511.04636v5","created_at":"2026-05-18T01:12:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04636","created_at":"2026-05-18T01:12:43Z"},{"alias_kind":"pith_short_12","alias_value":"WZ7TQSDR3REZ","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"WZ7TQSDR3REZJ25L","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"WZ7TQSDR","created_at":"2026-05-18T12:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:f19e84ea19e0671d660a8ea60578128dcc33966c4f01c9aa6087ef98b1bde21f","target":"graph","created_at":"2026-05-18T01:12:43Z","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":"This paper introduces a novel architecture for reinforcement learning with deep neural networks designed to handle state and action spaces characterized by natural language, as found in text-based games. Termed a deep reinforcement relevance network (DRRN), the architecture represents action and state spaces with separate embedding vectors, which are combined with an interaction function to approximate the Q-function in reinforcement learning. We evaluate the DRRN on two popular text games, showing superior performance over other deep Q-learning architectures. Experiments with paraphrased acti","authors_text":"Jianfeng Gao, Jianshu Chen, Ji He, Li Deng, Lihong Li, Mari Ostendorf, Xiaodong He","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-14T23:30:39Z","title":"Deep Reinforcement Learning with a Natural Language Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04636","kind":"arxiv","version":5},"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":"sha256:09a4a87361d1001de4d6be2b293c1332f886a24811a04cb65f4d71b25f75569a","target":"record","created_at":"2026-05-18T01:12:43Z","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":"33d17478addf71e03b062a2b403845aeadc15a7b77d100ab80a7fe73e206fefa","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-14T23:30:39Z","title_canon_sha256":"84c761ba1d93973aa432022cc33ecf42cbecb30b6308eea2db17fea947aed71d"},"schema_version":"1.0","source":{"id":"1511.04636","kind":"arxiv","version":5}},"canonical_sha256":"b67f384871dc4994ebab3c4d37c726e5acf752c6d984c701447fd3a9a5481719","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b67f384871dc4994ebab3c4d37c726e5acf752c6d984c701447fd3a9a5481719","first_computed_at":"2026-05-18T01:12:43.351531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:43.351531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ApdFgpSFSJiB2vMBf4NFE8diF+3dh4jggeFNuj9pki3h1YbagSMuEV1nZ0MQJxrj0VHMOh1Mafyi/uN96HBfBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:43.351874Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.04636","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09a4a87361d1001de4d6be2b293c1332f886a24811a04cb65f4d71b25f75569a","sha256:f19e84ea19e0671d660a8ea60578128dcc33966c4f01c9aa6087ef98b1bde21f"],"state_sha256":"3808eee8b9ae8f821f54fd1dafca92c92a60da075d4cec86c311975f07c3d69d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYqQW9P2JILgIuvlfiMGIhz2ejGFahSKkbfmamFd76yJMbBUx9q3Yn4vycReP3Jr2NwaEekT2We8HVZC0LZLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T14:41:31.591445Z","bundle_sha256":"c1b8455cd23453c9d230146c557b3f8adbf88e5c17a4e8feba707815ad929a3d"}}