{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IHISWYQCDX3AW7DNRHQZK5NALI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"69994ef78f3668bb453d130808d1814ba49890654a02411e8e259c10ac989516","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T01:53:24Z","title_canon_sha256":"c0fa6e41fc52eb6f7ce49d45d88857c5b72e56bb313e43a88c6cc9944f183f15"},"schema_version":"1.0","source":{"id":"2403.19913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19913","created_at":"2026-07-05T08:53:21Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19913v2","created_at":"2026-07-05T08:53:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19913","created_at":"2026-07-05T08:53:21Z"},{"alias_kind":"pith_short_12","alias_value":"IHISWYQCDX3A","created_at":"2026-07-05T08:53:21Z"},{"alias_kind":"pith_short_16","alias_value":"IHISWYQCDX3AW7DN","created_at":"2026-07-05T08:53:21Z"},{"alias_kind":"pith_short_8","alias_value":"IHISWYQC","created_at":"2026-07-05T08:53:21Z"}],"graph_snapshots":[{"event_id":"sha256:800406832e45f6c2fd9f2cf7e5dffe74cb16bf54cb89e2e18ffbfd840002f0c3","target":"graph","created_at":"2026-07-05T08:53:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.19913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Hongyuan Mei, Jiading Fang, Jing Li, Kangrui Wang, Matthew R. Walter, Mo Yu, Peng Ding, Peng Li, Xiaochen Zhou","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T01:53:24Z","title":"MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19913","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5045672da7b2e93142fa7662f39dad7dd0c063d07dc672a04f0eb0346a821a46","target":"record","created_at":"2026-07-05T08:53:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"69994ef78f3668bb453d130808d1814ba49890654a02411e8e259c10ac989516","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T01:53:24Z","title_canon_sha256":"c0fa6e41fc52eb6f7ce49d45d88857c5b72e56bb313e43a88c6cc9944f183f15"},"schema_version":"1.0","source":{"id":"2403.19913","kind":"arxiv","version":2}},"canonical_sha256":"41d12b62021df60b7c6d89e19575a05a37feb4c5ba84c556becbcfee8c510769","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41d12b62021df60b7c6d89e19575a05a37feb4c5ba84c556becbcfee8c510769","first_computed_at":"2026-07-05T08:53:21.250469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:21.250469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NcUsHcftb9l0IN3tgpwfm36MpnsYwBGKiFl/CUvbMorz37M0FwS8h+SHMmTaX7X35w9ch6c5E5+qu2YGx3CcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:21.250948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5045672da7b2e93142fa7662f39dad7dd0c063d07dc672a04f0eb0346a821a46","sha256:800406832e45f6c2fd9f2cf7e5dffe74cb16bf54cb89e2e18ffbfd840002f0c3"],"state_sha256":"26607cc0ba4e59bc7b416716e2db3e79d43b1b7c2cd6e541948f8dff1a6c6f04"}