{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MQPOOQEDA3FO25F6VWPKXRE5CD","short_pith_number":"pith:MQPOOQED","schema_version":"1.0","canonical_sha256":"641ee7408306caed74bead9eabc49d10d553ce69b3fe70f38b0ca910ec82a175","source":{"kind":"arxiv","id":"2311.01468","version":1},"attestation_state":"computed","paper":{"title":"Remember what you did so you know what to do next","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Hedges, Justin Martin, Manuel R. Ciosici, Marjorie Freedman, Ralph Weischedel, Yash Kankanampati","submitted_at":"2023-10-30T19:29:00Z","abstract_excerpt":"We explore using a moderately sized large language model (GPT-J 6B parameters) to create a plan for a simulated robot to achieve 30 classes of goals in ScienceWorld, a text game simulator for elementary science experiments. Previously published empirical work claimed that large language models (LLMs) are a poor fit (Wang et al., 2022) compared to reinforcement learning. Using the Markov assumption (a single previous step), the LLM outperforms the reinforcement learning-based approach by a factor of 1.4. When we fill the LLM's input buffer with as many prior steps as possible, improvement rises"},"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":"2311.01468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T19:29:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4251dbe684e7ec5cb1082abe4ca6cec0198adfc9d309cc572420d9584fa5fccc","abstract_canon_sha256":"6d0771861071bd2cdd154ccc7be8486bb63a5eacbb670c432714374d314c1261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:00.266462Z","signature_b64":"/GFkLTaSJLo/PfjY9xLQQY1TWJEYdJEl7MSqxMYxUi8OX/ZuMv3Nz8ULMI4sUQnjbLevMEUvhekbreH4LMfQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641ee7408306caed74bead9eabc49d10d553ce69b3fe70f38b0ca910ec82a175","last_reissued_at":"2026-05-25T02:01:00.265683Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:00.265683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Remember what you did so you know what to do next","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Hedges, Justin Martin, Manuel R. Ciosici, Marjorie Freedman, Ralph Weischedel, Yash Kankanampati","submitted_at":"2023-10-30T19:29:00Z","abstract_excerpt":"We explore using a moderately sized large language model (GPT-J 6B parameters) to create a plan for a simulated robot to achieve 30 classes of goals in ScienceWorld, a text game simulator for elementary science experiments. Previously published empirical work claimed that large language models (LLMs) are a poor fit (Wang et al., 2022) compared to reinforcement learning. Using the Markov assumption (a single previous step), the LLM outperforms the reinforcement learning-based approach by a factor of 1.4. When we fill the LLM's input buffer with as many prior steps as possible, improvement rises"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01468","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/2311.01468/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":"2311.01468","created_at":"2026-05-25T02:01:00.265791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01468v1","created_at":"2026-05-25T02:01:00.265791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01468","created_at":"2026-05-25T02:01:00.265791+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQPOOQEDA3FO","created_at":"2026-05-25T02:01:00.265791+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQPOOQEDA3FO25F6","created_at":"2026-05-25T02:01:00.265791+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQPOOQED","created_at":"2026-05-25T02:01:00.265791+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/MQPOOQEDA3FO25F6VWPKXRE5CD","json":"https://pith.science/pith/MQPOOQEDA3FO25F6VWPKXRE5CD.json","graph_json":"https://pith.science/api/pith-number/MQPOOQEDA3FO25F6VWPKXRE5CD/graph.json","events_json":"https://pith.science/api/pith-number/MQPOOQEDA3FO25F6VWPKXRE5CD/events.json","paper":"https://pith.science/paper/MQPOOQED"},"agent_actions":{"view_html":"https://pith.science/pith/MQPOOQEDA3FO25F6VWPKXRE5CD","download_json":"https://pith.science/pith/MQPOOQEDA3FO25F6VWPKXRE5CD.json","view_paper":"https://pith.science/paper/MQPOOQED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01468&json=true","fetch_graph":"https://pith.science/api/pith-number/MQPOOQEDA3FO25F6VWPKXRE5CD/graph.json","fetch_events":"https://pith.science/api/pith-number/MQPOOQEDA3FO25F6VWPKXRE5CD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQPOOQEDA3FO25F6VWPKXRE5CD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQPOOQEDA3FO25F6VWPKXRE5CD/action/storage_attestation","attest_author":"https://pith.science/pith/MQPOOQEDA3FO25F6VWPKXRE5CD/action/author_attestation","sign_citation":"https://pith.science/pith/MQPOOQEDA3FO25F6VWPKXRE5CD/action/citation_signature","submit_replication":"https://pith.science/pith/MQPOOQEDA3FO25F6VWPKXRE5CD/action/replication_record"}},"created_at":"2026-05-25T02:01:00.265791+00:00","updated_at":"2026-05-25T02:01:00.265791+00:00"}