{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GXICZDSXUYPO6JOUTU6XRGAXYV","short_pith_number":"pith:GXICZDSX","schema_version":"1.0","canonical_sha256":"35d02c8e57a61eef25d49d3d789817c55e75d27826867fee6bbbbdfdfcf6b8c6","source":{"kind":"arxiv","id":"2002.09127","version":4},"attestation_state":"computed","paper":{"title":"Learning Dynamic Belief Graphs to Generalize on Text-Based Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Trischler, Ashutosh Adhikari, Jian Tang, Marc-Alexandre C\\^ot\\'e, Marc-Antoine Rondeau, Mikul\\'a\\v{s} Zelinka, Pascal Poupart, Romain Laroche, William L. Hamilton, Xingdi Yuan","submitted_at":"2020-02-21T04:38:37Z","abstract_excerpt":"Playing text-based games requires skills in processing natural language and sequential decision making. Achieving human-level performance on text-based games remains an open challenge, and prior research has largely relied on hand-crafted structured representations and heuristics. In this work, we investigate how an agent can plan and generalize in text-based games using graph-structured representations learned end-to-end from raw text. We propose a novel graph-aided transformer agent (GATA) that infers and updates latent belief graphs during planning to enable effective action selection by ca"},"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":"2002.09127","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-21T04:38:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"712e34a60c718e7d8b28502e84de0b95871b141896a8432c41bbdf93e35c6718","abstract_canon_sha256":"006b4044762cec95fa76e07a1ad0b8249798844ff366c74c43754c9e6583cea9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:00.517140Z","signature_b64":"UDyRGLABenLxJrr0eStyFnsQyDEM09nsCAFvPwbfqPWEv3bfQI5Z66Xrzozj5+I27PxhACYYYpRprkTOQtoWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35d02c8e57a61eef25d49d3d789817c55e75d27826867fee6bbbbdfdfcf6b8c6","last_reissued_at":"2026-07-05T02:39:00.516778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:00.516778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Dynamic Belief Graphs to Generalize on Text-Based Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Trischler, Ashutosh Adhikari, Jian Tang, Marc-Alexandre C\\^ot\\'e, Marc-Antoine Rondeau, Mikul\\'a\\v{s} Zelinka, Pascal Poupart, Romain Laroche, William L. Hamilton, Xingdi Yuan","submitted_at":"2020-02-21T04:38:37Z","abstract_excerpt":"Playing text-based games requires skills in processing natural language and sequential decision making. Achieving human-level performance on text-based games remains an open challenge, and prior research has largely relied on hand-crafted structured representations and heuristics. In this work, we investigate how an agent can plan and generalize in text-based games using graph-structured representations learned end-to-end from raw text. We propose a novel graph-aided transformer agent (GATA) that infers and updates latent belief graphs during planning to enable effective action selection by ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09127","kind":"arxiv","version":4},"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/2002.09127/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":"2002.09127","created_at":"2026-07-05T02:39:00.516839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09127v4","created_at":"2026-07-05T02:39:00.516839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09127","created_at":"2026-07-05T02:39:00.516839+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXICZDSXUYPO","created_at":"2026-07-05T02:39:00.516839+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXICZDSXUYPO6JOU","created_at":"2026-07-05T02:39:00.516839+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXICZDSX","created_at":"2026-07-05T02:39:00.516839+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/GXICZDSXUYPO6JOUTU6XRGAXYV","json":"https://pith.science/pith/GXICZDSXUYPO6JOUTU6XRGAXYV.json","graph_json":"https://pith.science/api/pith-number/GXICZDSXUYPO6JOUTU6XRGAXYV/graph.json","events_json":"https://pith.science/api/pith-number/GXICZDSXUYPO6JOUTU6XRGAXYV/events.json","paper":"https://pith.science/paper/GXICZDSX"},"agent_actions":{"view_html":"https://pith.science/pith/GXICZDSXUYPO6JOUTU6XRGAXYV","download_json":"https://pith.science/pith/GXICZDSXUYPO6JOUTU6XRGAXYV.json","view_paper":"https://pith.science/paper/GXICZDSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09127&json=true","fetch_graph":"https://pith.science/api/pith-number/GXICZDSXUYPO6JOUTU6XRGAXYV/graph.json","fetch_events":"https://pith.science/api/pith-number/GXICZDSXUYPO6JOUTU6XRGAXYV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXICZDSXUYPO6JOUTU6XRGAXYV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXICZDSXUYPO6JOUTU6XRGAXYV/action/storage_attestation","attest_author":"https://pith.science/pith/GXICZDSXUYPO6JOUTU6XRGAXYV/action/author_attestation","sign_citation":"https://pith.science/pith/GXICZDSXUYPO6JOUTU6XRGAXYV/action/citation_signature","submit_replication":"https://pith.science/pith/GXICZDSXUYPO6JOUTU6XRGAXYV/action/replication_record"}},"created_at":"2026-07-05T02:39:00.516839+00:00","updated_at":"2026-07-05T02:39:00.516839+00:00"}