{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HX6TBEY37E2ZWVEWLMJK54QSNH","short_pith_number":"pith:HX6TBEY3","schema_version":"1.0","canonical_sha256":"3dfd30931bf9359b54965b12aef21269edf197e205c1bed713c4d80cdbfd353b","source":{"kind":"arxiv","id":"2403.00690","version":1},"attestation_state":"computed","paper":{"title":"Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Diego Perez-Liebana, Dominik Jeurissen, Duygu Cakmak, James Kwan, Jeremy Gow","submitted_at":"2024-03-01T17:22:16Z","abstract_excerpt":"Large Language Models (LLMs) have shown great success as high-level planners for zero-shot game-playing agents. However, these agents are primarily evaluated on Minecraft, where long-term planning is relatively straightforward. In contrast, agents tested in dynamic robot environments face limitations due to simplistic environments with only a few objects and interactions. To fill this gap in the literature, we present NetPlay, the first LLM-powered zero-shot agent for the challenging roguelike NetHack. NetHack is a particularly challenging environment due to its diverse set of items and monste"},"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":"2403.00690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-01T17:22:16Z","cross_cats_sorted":[],"title_canon_sha256":"d92da9da53a43154b3a92494e4cc8e53f8c89953bd3997cb3591f027643ae45b","abstract_canon_sha256":"ff3fe6a42cb527b4fee512368140415ebac8724875ac56db1cd3a4ddbba0179b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:07.333370Z","signature_b64":"usKs5SzMj0ITTxJ9Q4PAJE/cmUipAVppP+xNeuMMGZFoV9x4KUlN+UAdcn/uQG/WXvLK8QdXO3AOvuEye65kDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dfd30931bf9359b54965b12aef21269edf197e205c1bed713c4d80cdbfd353b","last_reissued_at":"2026-07-05T07:51:07.332868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:07.332868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Diego Perez-Liebana, Dominik Jeurissen, Duygu Cakmak, James Kwan, Jeremy Gow","submitted_at":"2024-03-01T17:22:16Z","abstract_excerpt":"Large Language Models (LLMs) have shown great success as high-level planners for zero-shot game-playing agents. However, these agents are primarily evaluated on Minecraft, where long-term planning is relatively straightforward. In contrast, agents tested in dynamic robot environments face limitations due to simplistic environments with only a few objects and interactions. To fill this gap in the literature, we present NetPlay, the first LLM-powered zero-shot agent for the challenging roguelike NetHack. NetHack is a particularly challenging environment due to its diverse set of items and monste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00690","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/2403.00690/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":"2403.00690","created_at":"2026-07-05T07:51:07.332928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00690v1","created_at":"2026-07-05T07:51:07.332928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00690","created_at":"2026-07-05T07:51:07.332928+00:00"},{"alias_kind":"pith_short_12","alias_value":"HX6TBEY37E2Z","created_at":"2026-07-05T07:51:07.332928+00:00"},{"alias_kind":"pith_short_16","alias_value":"HX6TBEY37E2ZWVEW","created_at":"2026-07-05T07:51:07.332928+00:00"},{"alias_kind":"pith_short_8","alias_value":"HX6TBEY3","created_at":"2026-07-05T07:51:07.332928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15815","citing_title":"LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH","json":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH.json","graph_json":"https://pith.science/api/pith-number/HX6TBEY37E2ZWVEWLMJK54QSNH/graph.json","events_json":"https://pith.science/api/pith-number/HX6TBEY37E2ZWVEWLMJK54QSNH/events.json","paper":"https://pith.science/paper/HX6TBEY3"},"agent_actions":{"view_html":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH","download_json":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH.json","view_paper":"https://pith.science/paper/HX6TBEY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00690&json=true","fetch_graph":"https://pith.science/api/pith-number/HX6TBEY37E2ZWVEWLMJK54QSNH/graph.json","fetch_events":"https://pith.science/api/pith-number/HX6TBEY37E2ZWVEWLMJK54QSNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH/action/storage_attestation","attest_author":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH/action/author_attestation","sign_citation":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH/action/citation_signature","submit_replication":"https://pith.science/pith/HX6TBEY37E2ZWVEWLMJK54QSNH/action/replication_record"}},"created_at":"2026-07-05T07:51:07.332928+00:00","updated_at":"2026-07-05T07:51:07.332928+00:00"}