{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5MVL4OVD3POCMARGBSUUO7VQPO","short_pith_number":"pith:5MVL4OVD","schema_version":"1.0","canonical_sha256":"eb2abe3aa3dbdc2602260ca9477eb07ba902f34758243bc4fc36e84d650fcf4b","source":{"kind":"arxiv","id":"2302.05507","version":2},"attestation_state":"computed","paper":{"title":"Language Decision Transformers with Exponential Tilt for Interactive Text Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christopher Pal, David Vazquez, Issam Laradji, Nicolas Gontier, Pau Rodriguez","submitted_at":"2023-02-10T20:50:58Z","abstract_excerpt":"Text-based game environments are challenging because agents must deal with long sequences of text, execute compositional actions using text and learn from sparse rewards. We address these challenges by proposing Language Decision Transformers (LDTs), a framework that is based on transformer language models and decision transformers (DTs). Our LDTs extend DTs with 3 components: (1) exponential tilt to guide the agent towards high obtainable goals, (2) novel goal conditioning methods yielding better results than the traditional return-to-go (sum of all future rewards), and (3) a model of future "},"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":"2302.05507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-10T20:50:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"25380e291ce8ef8454fd2ec215e41929378a4a9d93ca78d9feddccee7e99988f","abstract_canon_sha256":"a05dde4c92ad10937deb957cc92d1b3dad30f953a5c76d4fa279b258270b2902"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:09.268904Z","signature_b64":"oRxTCpJ1+7NJE9/anGFAVOXjDhtmx8T41L1hDoX0ZYQgQFozP0qJPE5qxc8NVfaRaSb6hJxcPlTrwQ9Y3YpDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb2abe3aa3dbdc2602260ca9477eb07ba902f34758243bc4fc36e84d650fcf4b","last_reissued_at":"2026-07-05T07:14:09.268453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:09.268453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Decision Transformers with Exponential Tilt for Interactive Text Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Christopher Pal, David Vazquez, Issam Laradji, Nicolas Gontier, Pau Rodriguez","submitted_at":"2023-02-10T20:50:58Z","abstract_excerpt":"Text-based game environments are challenging because agents must deal with long sequences of text, execute compositional actions using text and learn from sparse rewards. We address these challenges by proposing Language Decision Transformers (LDTs), a framework that is based on transformer language models and decision transformers (DTs). Our LDTs extend DTs with 3 components: (1) exponential tilt to guide the agent towards high obtainable goals, (2) novel goal conditioning methods yielding better results than the traditional return-to-go (sum of all future rewards), and (3) a model of future "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05507","kind":"arxiv","version":2},"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/2302.05507/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":"2302.05507","created_at":"2026-07-05T07:14:09.268509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05507v2","created_at":"2026-07-05T07:14:09.268509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05507","created_at":"2026-07-05T07:14:09.268509+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MVL4OVD3POC","created_at":"2026-07-05T07:14:09.268509+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MVL4OVD3POCMARG","created_at":"2026-07-05T07:14:09.268509+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MVL4OVD","created_at":"2026-07-05T07:14:09.268509+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/5MVL4OVD3POCMARGBSUUO7VQPO","json":"https://pith.science/pith/5MVL4OVD3POCMARGBSUUO7VQPO.json","graph_json":"https://pith.science/api/pith-number/5MVL4OVD3POCMARGBSUUO7VQPO/graph.json","events_json":"https://pith.science/api/pith-number/5MVL4OVD3POCMARGBSUUO7VQPO/events.json","paper":"https://pith.science/paper/5MVL4OVD"},"agent_actions":{"view_html":"https://pith.science/pith/5MVL4OVD3POCMARGBSUUO7VQPO","download_json":"https://pith.science/pith/5MVL4OVD3POCMARGBSUUO7VQPO.json","view_paper":"https://pith.science/paper/5MVL4OVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05507&json=true","fetch_graph":"https://pith.science/api/pith-number/5MVL4OVD3POCMARGBSUUO7VQPO/graph.json","fetch_events":"https://pith.science/api/pith-number/5MVL4OVD3POCMARGBSUUO7VQPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MVL4OVD3POCMARGBSUUO7VQPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MVL4OVD3POCMARGBSUUO7VQPO/action/storage_attestation","attest_author":"https://pith.science/pith/5MVL4OVD3POCMARGBSUUO7VQPO/action/author_attestation","sign_citation":"https://pith.science/pith/5MVL4OVD3POCMARGBSUUO7VQPO/action/citation_signature","submit_replication":"https://pith.science/pith/5MVL4OVD3POCMARGBSUUO7VQPO/action/replication_record"}},"created_at":"2026-07-05T07:14:09.268509+00:00","updated_at":"2026-07-05T07:14:09.268509+00:00"}