{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7DAJ5VMYBAGAUVYJSG4AL2K7BG","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":"cfb3549a98fa844e552bfbeb3ab91b918c9d00a270c994a4f8c07293feeacc7d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:07:50Z","title_canon_sha256":"27e2c2d6108ac3b940995e63b0e56fbd8497f4fe76011857941c8f5a95bbec7e"},"schema_version":"1.0","source":{"id":"2305.10276","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10276","created_at":"2026-07-05T08:51:41Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10276v7","created_at":"2026-07-05T08:51:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10276","created_at":"2026-07-05T08:51:41Z"},{"alias_kind":"pith_short_12","alias_value":"7DAJ5VMYBAGA","created_at":"2026-07-05T08:51:41Z"},{"alias_kind":"pith_short_16","alias_value":"7DAJ5VMYBAGAUVYJ","created_at":"2026-07-05T08:51:41Z"},{"alias_kind":"pith_short_8","alias_value":"7DAJ5VMY","created_at":"2026-07-05T08:51:41Z"}],"graph_snapshots":[{"event_id":"sha256:7cdeb5d3913cdb3251cbe9737a667219575f27f8fce66df70c189976b36c85f4","target":"graph","created_at":"2026-07-05T08:51:41Z","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/2305.10276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we take the initiative to investigate the performance of LLMs on complex planning tasks that require LLMs to understand a virtual spatial environment simulated via natural language and act correspondingly in text. We propose a benchmark named Natural Language Planning and Action (Natala) composed of a set of novel tasks: Brick World, NLVR-based Manipulations, and Natural Language Navigation. We found that current popular LLMs such as ChatGPT still lack abilities in complex planning. This arises a question -- do the LLMs have a good understanding of the environments described in ","authors_text":"Hanxu Hu, Hongyuan Lu, Huajian Zhang, Wai Lam, Yue Zhang, Yun-Ze Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:07:50Z","title":"Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10276","kind":"arxiv","version":7},"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:e18c056eb72390907ac1adc363c83bfd8133e51385b485e614e08803ff033d02","target":"record","created_at":"2026-07-05T08:51:41Z","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":"cfb3549a98fa844e552bfbeb3ab91b918c9d00a270c994a4f8c07293feeacc7d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T15:07:50Z","title_canon_sha256":"27e2c2d6108ac3b940995e63b0e56fbd8497f4fe76011857941c8f5a95bbec7e"},"schema_version":"1.0","source":{"id":"2305.10276","kind":"arxiv","version":7}},"canonical_sha256":"f8c09ed598080c0a570991b805e95f0990be0883e5b3573bd69666127dbbd0f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8c09ed598080c0a570991b805e95f0990be0883e5b3573bd69666127dbbd0f6","first_computed_at":"2026-07-05T08:51:41.732577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:41.732577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N1egkPamVN92s/+zudzRntbrebS8IHxmJx9z6TixT7ay/MwTf7niOrtfzNow7mFZWV53TScHxSheUxXybhCrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:41.733060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10276","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e18c056eb72390907ac1adc363c83bfd8133e51385b485e614e08803ff033d02","sha256:7cdeb5d3913cdb3251cbe9737a667219575f27f8fce66df70c189976b36c85f4"],"state_sha256":"85b37f2660e8b4a704cbed9751ca8244508efb512f94333674139c9c97173975"}