{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z26TOWZTDBLTZU7QPUYY3TF5LJ","short_pith_number":"pith:Z26TOWZT","schema_version":"1.0","canonical_sha256":"cebd375b3318573cd3f07d318dccbd5a5baaa58951456f0e7abd88febaefd350","source":{"kind":"arxiv","id":"2410.06634","version":1},"attestation_state":"computed","paper":{"title":"Tree of Problems: Improving structured problem solving with compositionality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armel Zebaze, Beno\\^it Sagot, Rachel Bawden","submitted_at":"2024-10-09T07:35:46Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance across multiple tasks through in-context learning. For complex reasoning tasks that require step-by-step thinking, Chain-of-Thought (CoT) prompting has given impressive results, especially when combined with self-consistency. Nonetheless, some tasks remain particularly difficult for LLMs to solve. Tree of Thoughts (ToT) and Graph of Thoughts (GoT) emerged as alternatives, dividing the complex problem into paths of subproblems. In this paper, we propose Tree of Problems (ToP), a simpler version of ToT, which we hypothesise ca"},"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":"2410.06634","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-09T07:35:46Z","cross_cats_sorted":[],"title_canon_sha256":"e1f5def046bfd81ed0aac47b6f38f079b830591335c9e180b4064fae072e6e59","abstract_canon_sha256":"ca39d398708c0dbc852add098fb416aefe8878fcf3e2fa2f04e8c1d6f49b1d41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:05.088221Z","signature_b64":"GtCOL9X9lXMLMemQByLvgXtPTwHSRKNaP1P0gq9ZDdsZg/7CI6PARAZTOekiY6DQPWi2nFt/ktWK8ytSKyqRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cebd375b3318573cd3f07d318dccbd5a5baaa58951456f0e7abd88febaefd350","last_reissued_at":"2026-07-05T09:18:05.087815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:05.087815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tree of Problems: Improving structured problem solving with compositionality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armel Zebaze, Beno\\^it Sagot, Rachel Bawden","submitted_at":"2024-10-09T07:35:46Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable performance across multiple tasks through in-context learning. For complex reasoning tasks that require step-by-step thinking, Chain-of-Thought (CoT) prompting has given impressive results, especially when combined with self-consistency. Nonetheless, some tasks remain particularly difficult for LLMs to solve. Tree of Thoughts (ToT) and Graph of Thoughts (GoT) emerged as alternatives, dividing the complex problem into paths of subproblems. In this paper, we propose Tree of Problems (ToP), a simpler version of ToT, which we hypothesise ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06634","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/2410.06634/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":"2410.06634","created_at":"2026-07-05T09:18:05.087864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06634v1","created_at":"2026-07-05T09:18:05.087864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06634","created_at":"2026-07-05T09:18:05.087864+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z26TOWZTDBLT","created_at":"2026-07-05T09:18:05.087864+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z26TOWZTDBLTZU7Q","created_at":"2026-07-05T09:18:05.087864+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z26TOWZT","created_at":"2026-07-05T09:18:05.087864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13416","citing_title":"STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ","json":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ.json","graph_json":"https://pith.science/api/pith-number/Z26TOWZTDBLTZU7QPUYY3TF5LJ/graph.json","events_json":"https://pith.science/api/pith-number/Z26TOWZTDBLTZU7QPUYY3TF5LJ/events.json","paper":"https://pith.science/paper/Z26TOWZT"},"agent_actions":{"view_html":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ","download_json":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ.json","view_paper":"https://pith.science/paper/Z26TOWZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06634&json=true","fetch_graph":"https://pith.science/api/pith-number/Z26TOWZTDBLTZU7QPUYY3TF5LJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z26TOWZTDBLTZU7QPUYY3TF5LJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ/action/storage_attestation","attest_author":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ/action/author_attestation","sign_citation":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ/action/citation_signature","submit_replication":"https://pith.science/pith/Z26TOWZTDBLTZU7QPUYY3TF5LJ/action/replication_record"}},"created_at":"2026-07-05T09:18:05.087864+00:00","updated_at":"2026-07-05T09:18:05.087864+00:00"}