{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3OJIF3VRBNGFU4SV76CO5HIDYQ","short_pith_number":"pith:3OJIF3VR","schema_version":"1.0","canonical_sha256":"db9282eeb10b4c5a7255ff84ee9d03c4292c4a90c7cbb36b1016e75615ccd57a","source":{"kind":"arxiv","id":"2004.02986","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Learning of Text Adventure Games with Sentence-Level Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jonathan May, Xusen Yin","submitted_at":"2020-04-06T20:24:33Z","abstract_excerpt":"Reinforcement learning algorithms such as Q-learning have shown great promise in training models to learn the optimal action to take for a given system state; a goal in applications with an exploratory or adversarial nature such as task-oriented dialogues or games. However, models that do not have direct access to their state are harder to train; when the only state access is via the medium of language, this can be particularly pronounced. We introduce a new model amenable to deep Q-learning that incorporates a Siamese neural network architecture and a novel refactoring of the Q-value function"},"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":"2004.02986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T20:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"67cbdbeb2651b6e08c2f453f00bc9e0b52288b8b34df887c10c2ed15fd863490","abstract_canon_sha256":"2cd646a79e12847d162af832830f1e59f949031cb469ab495d902c581fd88c9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:22.151781Z","signature_b64":"xAtunXaKCYjrPxYXCTdSVExS2QxGXakM+qAirr6sV+b/LoeZsjtXuWsQfSgB9mm6eOyAZOLJ/0OTwXFtRBM2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db9282eeb10b4c5a7255ff84ee9d03c4292c4a90c7cbb36b1016e75615ccd57a","last_reissued_at":"2026-07-05T00:53:22.151409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:22.151409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Learning of Text Adventure Games with Sentence-Level Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jonathan May, Xusen Yin","submitted_at":"2020-04-06T20:24:33Z","abstract_excerpt":"Reinforcement learning algorithms such as Q-learning have shown great promise in training models to learn the optimal action to take for a given system state; a goal in applications with an exploratory or adversarial nature such as task-oriented dialogues or games. However, models that do not have direct access to their state are harder to train; when the only state access is via the medium of language, this can be particularly pronounced. We introduce a new model amenable to deep Q-learning that incorporates a Siamese neural network architecture and a novel refactoring of the Q-value function"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02986","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/2004.02986/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":"2004.02986","created_at":"2026-07-05T00:53:22.151473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.02986v1","created_at":"2026-07-05T00:53:22.151473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02986","created_at":"2026-07-05T00:53:22.151473+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OJIF3VRBNGF","created_at":"2026-07-05T00:53:22.151473+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OJIF3VRBNGFU4SV","created_at":"2026-07-05T00:53:22.151473+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OJIF3VR","created_at":"2026-07-05T00:53:22.151473+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/3OJIF3VRBNGFU4SV76CO5HIDYQ","json":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ.json","graph_json":"https://pith.science/api/pith-number/3OJIF3VRBNGFU4SV76CO5HIDYQ/graph.json","events_json":"https://pith.science/api/pith-number/3OJIF3VRBNGFU4SV76CO5HIDYQ/events.json","paper":"https://pith.science/paper/3OJIF3VR"},"agent_actions":{"view_html":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ","download_json":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ.json","view_paper":"https://pith.science/paper/3OJIF3VR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.02986&json=true","fetch_graph":"https://pith.science/api/pith-number/3OJIF3VRBNGFU4SV76CO5HIDYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3OJIF3VRBNGFU4SV76CO5HIDYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/action/storage_attestation","attest_author":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/action/author_attestation","sign_citation":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/action/citation_signature","submit_replication":"https://pith.science/pith/3OJIF3VRBNGFU4SV76CO5HIDYQ/action/replication_record"}},"created_at":"2026-07-05T00:53:22.151473+00:00","updated_at":"2026-07-05T00:53:22.151473+00:00"}