{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IHISWYQCDX3AW7DNRHQZK5NALI","short_pith_number":"pith:IHISWYQC","schema_version":"1.0","canonical_sha256":"41d12b62021df60b7c6d89e19575a05a37feb4c5ba84c556becbcfee8c510769","source":{"kind":"arxiv","id":"2403.19913","version":2},"attestation_state":"computed","paper":{"title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CL","authors_text":"Hongyuan Mei, Jiading Fang, Jing Li, Kangrui Wang, Matthew R. Walter, Mo Yu, Peng Ding, Peng Li, Xiaochen Zhou","submitted_at":"2024-03-29T01:53:24Z","abstract_excerpt":"Large language models such as ChatGPT and GPT-4 have recently achieved astonishing performance on a variety of natural language processing tasks. In this paper, we propose MANGO, a benchmark to evaluate their capabilities to perform text-based mapping and navigation. Our benchmark includes 53 mazes taken from a suite of textgames: each maze is paired with a walkthrough that visits every location but does not cover all possible paths. The task is question-answering: for each maze, a large language model reads the walkthrough and answers hundreds of mapping and navigation questions such as \"How "},"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":"2403.19913","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T01:53:24Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"c0fa6e41fc52eb6f7ce49d45d88857c5b72e56bb313e43a88c6cc9944f183f15","abstract_canon_sha256":"69994ef78f3668bb453d130808d1814ba49890654a02411e8e259c10ac989516"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:21.250948Z","signature_b64":"NcUsHcftb9l0IN3tgpwfm36MpnsYwBGKiFl/CUvbMorz37M0FwS8h+SHMmTaX7X35w9ch6c5E5+qu2YGx3CcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41d12b62021df60b7c6d89e19575a05a37feb4c5ba84c556becbcfee8c510769","last_reissued_at":"2026-07-05T08:53:21.250469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:21.250469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CL","authors_text":"Hongyuan Mei, Jiading Fang, Jing Li, Kangrui Wang, Matthew R. Walter, Mo Yu, Peng Ding, Peng Li, Xiaochen Zhou","submitted_at":"2024-03-29T01:53:24Z","abstract_excerpt":"Large language models such as ChatGPT and GPT-4 have recently achieved astonishing performance on a variety of natural language processing tasks. In this paper, we propose MANGO, a benchmark to evaluate their capabilities to perform text-based mapping and navigation. Our benchmark includes 53 mazes taken from a suite of textgames: each maze is paired with a walkthrough that visits every location but does not cover all possible paths. The task is question-answering: for each maze, a large language model reads the walkthrough and answers hundreds of mapping and navigation questions such as \"How "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19913","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/2403.19913/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":"2403.19913","created_at":"2026-07-05T08:53:21.250529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19913v2","created_at":"2026-07-05T08:53:21.250529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19913","created_at":"2026-07-05T08:53:21.250529+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHISWYQCDX3A","created_at":"2026-07-05T08:53:21.250529+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHISWYQCDX3AW7DN","created_at":"2026-07-05T08:53:21.250529+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHISWYQC","created_at":"2026-07-05T08:53:21.250529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14847","citing_title":"A Survey of RWKV","ref_index":191,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI","json":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI.json","graph_json":"https://pith.science/api/pith-number/IHISWYQCDX3AW7DNRHQZK5NALI/graph.json","events_json":"https://pith.science/api/pith-number/IHISWYQCDX3AW7DNRHQZK5NALI/events.json","paper":"https://pith.science/paper/IHISWYQC"},"agent_actions":{"view_html":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI","download_json":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI.json","view_paper":"https://pith.science/paper/IHISWYQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19913&json=true","fetch_graph":"https://pith.science/api/pith-number/IHISWYQCDX3AW7DNRHQZK5NALI/graph.json","fetch_events":"https://pith.science/api/pith-number/IHISWYQCDX3AW7DNRHQZK5NALI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI/action/storage_attestation","attest_author":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI/action/author_attestation","sign_citation":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI/action/citation_signature","submit_replication":"https://pith.science/pith/IHISWYQCDX3AW7DNRHQZK5NALI/action/replication_record"}},"created_at":"2026-07-05T08:53:21.250529+00:00","updated_at":"2026-07-05T08:53:21.250529+00:00"}