{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CSHAH4V3O2XQ7AGXIV25HB7EER","short_pith_number":"pith:CSHAH4V3","schema_version":"1.0","canonical_sha256":"148e03f2bb76af0f80d74575d387e424500c31f44acf21baac309d7f241a0002","source":{"kind":"arxiv","id":"1905.02265","version":3},"attestation_state":"computed","paper":{"title":"Comprehensible Context-driven Text Game Playing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jonathan May, Xusen Yin","submitted_at":"2019-05-06T21:14:41Z","abstract_excerpt":"In order to train a computer agent to play a text-based computer game, we must represent each hidden state of the game. A Long Short-Term Memory (LSTM) model running over observed texts is a common choice for state construction. However, a normal Deep Q-learning Network (DQN) for such an agent requires millions of steps of training or more to converge. As such, an LSTM-based DQN can take tens of days to finish the training process. Though we can use a Convolutional Neural Network (CNN) as a text-encoder to construct states much faster than the LSTM, doing so without an understanding of the syn"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.02265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-06T21:14:41Z","cross_cats_sorted":[],"title_canon_sha256":"19f76a798194b6db77e17439a8d88324e6718f5f7d45eef790d0c7cbe5991efd","abstract_canon_sha256":"9d0a2f8ed21f1ab8ba94cf075be42910fb8f55d1dcc5c0a444013092dacf52d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:25.513186Z","signature_b64":"FbXNjMRDlvm5vPO7anYxXiNTQb8ucNlTlzzDQml2gsW3LcyN7/kpNkMyoYGYAvUxM9nxtfn7YrgX4Sc3qtpwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"148e03f2bb76af0f80d74575d387e424500c31f44acf21baac309d7f241a0002","last_reissued_at":"2026-07-05T00:00:25.512778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:25.512778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comprehensible Context-driven Text Game Playing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jonathan May, Xusen Yin","submitted_at":"2019-05-06T21:14:41Z","abstract_excerpt":"In order to train a computer agent to play a text-based computer game, we must represent each hidden state of the game. A Long Short-Term Memory (LSTM) model running over observed texts is a common choice for state construction. However, a normal Deep Q-learning Network (DQN) for such an agent requires millions of steps of training or more to converge. As such, an LSTM-based DQN can take tens of days to finish the training process. Though we can use a Convolutional Neural Network (CNN) as a text-encoder to construct states much faster than the LSTM, doing so without an understanding of the syn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02265","kind":"arxiv","version":3},"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/1905.02265/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.02265","created_at":"2026-07-05T00:00:25.512837+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02265v3","created_at":"2026-07-05T00:00:25.512837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02265","created_at":"2026-07-05T00:00:25.512837+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSHAH4V3O2XQ","created_at":"2026-07-05T00:00:25.512837+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSHAH4V3O2XQ7AGX","created_at":"2026-07-05T00:00:25.512837+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSHAH4V3","created_at":"2026-07-05T00:00:25.512837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER","json":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER.json","graph_json":"https://pith.science/api/pith-number/CSHAH4V3O2XQ7AGXIV25HB7EER/graph.json","events_json":"https://pith.science/api/pith-number/CSHAH4V3O2XQ7AGXIV25HB7EER/events.json","paper":"https://pith.science/paper/CSHAH4V3"},"agent_actions":{"view_html":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER","download_json":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER.json","view_paper":"https://pith.science/paper/CSHAH4V3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02265&json=true","fetch_graph":"https://pith.science/api/pith-number/CSHAH4V3O2XQ7AGXIV25HB7EER/graph.json","fetch_events":"https://pith.science/api/pith-number/CSHAH4V3O2XQ7AGXIV25HB7EER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER/action/storage_attestation","attest_author":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER/action/author_attestation","sign_citation":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER/action/citation_signature","submit_replication":"https://pith.science/pith/CSHAH4V3O2XQ7AGXIV25HB7EER/action/replication_record"}},"created_at":"2026-07-05T00:00:25.512837+00:00","updated_at":"2026-07-05T00:00:25.512837+00:00"}