{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CWEWFPWSPIBYIHXLHI7AWRVNBX","short_pith_number":"pith:CWEWFPWS","schema_version":"1.0","canonical_sha256":"158962bed27a03841eeb3a3e0b46ad0df15fa784417731e25755b9e6737d2c55","source":{"kind":"arxiv","id":"2501.02152","version":1},"attestation_state":"computed","paper":{"title":"Table as Thought: Exploring Structured Thoughts in LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Haofei Yu, Jiaxuan You, Naihao Deng, Zhenjie Sun","submitted_at":"2025-01-04T00:58:06Z","abstract_excerpt":"Large language models' reasoning abilities benefit from methods that organize their thought processes, such as chain-of-thought prompting, which employs a sequential structure to guide the reasoning process step-by-step. However, existing approaches focus primarily on organizing the sequence of thoughts, leaving structure in individual thought steps underexplored. To address this gap, we propose Table as Thought, a framework inspired by cognitive neuroscience theories on human thought. Table as Thought organizes reasoning within a tabular schema, where rows represent sequential thought steps a"},"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":"2501.02152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-04T00:58:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"fe5c6cd52e4e95363efabf6315d5f62c6a61801e50e188bfe805a4ec3cefba6d","abstract_canon_sha256":"f7673a96a659c97fee442a3c9bb852840c2e390c7d775ad3ff24d5f892456338"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:02.957321Z","signature_b64":"RFYAEB3I0oPP80tF14UO4CRwKzDqHke9C0mISvYdrwPKYnJOj+3r2ZkzUBUqxDZ5WOQsXI9oUE2W93AmwRILCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158962bed27a03841eeb3a3e0b46ad0df15fa784417731e25755b9e6737d2c55","last_reissued_at":"2026-07-05T09:57:02.956722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:02.956722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Table as Thought: Exploring Structured Thoughts in LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Haofei Yu, Jiaxuan You, Naihao Deng, Zhenjie Sun","submitted_at":"2025-01-04T00:58:06Z","abstract_excerpt":"Large language models' reasoning abilities benefit from methods that organize their thought processes, such as chain-of-thought prompting, which employs a sequential structure to guide the reasoning process step-by-step. However, existing approaches focus primarily on organizing the sequence of thoughts, leaving structure in individual thought steps underexplored. To address this gap, we propose Table as Thought, a framework inspired by cognitive neuroscience theories on human thought. Table as Thought organizes reasoning within a tabular schema, where rows represent sequential thought steps a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02152","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/2501.02152/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":"2501.02152","created_at":"2026-07-05T09:57:02.956835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.02152v1","created_at":"2026-07-05T09:57:02.956835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02152","created_at":"2026-07-05T09:57:02.956835+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWEWFPWSPIBY","created_at":"2026-07-05T09:57:02.956835+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWEWFPWSPIBYIHXL","created_at":"2026-07-05T09:57:02.956835+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWEWFPWS","created_at":"2026-07-05T09:57:02.956835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14930","citing_title":"IE as Cache: Information Extraction Enhanced Agentic Reasoning","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX","json":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX.json","graph_json":"https://pith.science/api/pith-number/CWEWFPWSPIBYIHXLHI7AWRVNBX/graph.json","events_json":"https://pith.science/api/pith-number/CWEWFPWSPIBYIHXLHI7AWRVNBX/events.json","paper":"https://pith.science/paper/CWEWFPWS"},"agent_actions":{"view_html":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX","download_json":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX.json","view_paper":"https://pith.science/paper/CWEWFPWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.02152&json=true","fetch_graph":"https://pith.science/api/pith-number/CWEWFPWSPIBYIHXLHI7AWRVNBX/graph.json","fetch_events":"https://pith.science/api/pith-number/CWEWFPWSPIBYIHXLHI7AWRVNBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX/action/storage_attestation","attest_author":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX/action/author_attestation","sign_citation":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX/action/citation_signature","submit_replication":"https://pith.science/pith/CWEWFPWSPIBYIHXLHI7AWRVNBX/action/replication_record"}},"created_at":"2026-07-05T09:57:02.956835+00:00","updated_at":"2026-07-05T09:57:02.956835+00:00"}