{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4OV4EMIZ5SSLTQE7V3RXYBEF5P","short_pith_number":"pith:4OV4EMIZ","schema_version":"1.0","canonical_sha256":"e3abc23119eca4b9c09faee37c0485ebceb83516127a97943c880714c43fd5d2","source":{"kind":"arxiv","id":"2311.00694","version":2},"attestation_state":"computed","paper":{"title":"Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Hao Su, Mingu Lee, Reza Pourreza, Roland Memisevic, Tongzhou Mu, Xuanlin Li, Yunhao Fang, Zhan Ling","submitted_at":"2023-11-01T17:52:15Z","abstract_excerpt":"Large Language Models (LLMs) have achieved tremendous progress, yet they still often struggle with challenging reasoning problems. Current approaches address this challenge by sampling or searching detailed and low-level reasoning chains. However, these methods are still limited in their exploration capabilities, making it challenging for correct solutions to stand out in the huge solution space. In this work, we unleash LLMs' creative potential for exploring multiple diverse problem solving strategies by framing an LLM as a hierarchical policy via in-context learning. This policy comprises of"},"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":"2311.00694","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-01T17:52:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2275fa7ac1590b480c669d2f7c96a18e1a326b3c899eb01c3d120d111d575044","abstract_canon_sha256":"0163d4d945430e3d05a5df381871673abb51822e27761be64866575d7f5ba313"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:54.728779Z","signature_b64":"BHeYKIj4pXk3nhBy8isHNyxG+Ek2clFeXJFVc0ji66iaeAxlyeIPzFPaf2MDJG81k1/QA0JSp0K3EWceqyAgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3abc23119eca4b9c09faee37c0485ebceb83516127a97943c880714c43fd5d2","last_reissued_at":"2026-07-05T07:20:54.728307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:54.728307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Creative Mind: Language Model As Hierarchical Policy For Improved Exploration on Challenging Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Hao Su, Mingu Lee, Reza Pourreza, Roland Memisevic, Tongzhou Mu, Xuanlin Li, Yunhao Fang, Zhan Ling","submitted_at":"2023-11-01T17:52:15Z","abstract_excerpt":"Large Language Models (LLMs) have achieved tremendous progress, yet they still often struggle with challenging reasoning problems. Current approaches address this challenge by sampling or searching detailed and low-level reasoning chains. However, these methods are still limited in their exploration capabilities, making it challenging for correct solutions to stand out in the huge solution space. In this work, we unleash LLMs' creative potential for exploring multiple diverse problem solving strategies by framing an LLM as a hierarchical policy via in-context learning. This policy comprises of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00694","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/2311.00694/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":"2311.00694","created_at":"2026-07-05T07:20:54.728384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00694v2","created_at":"2026-07-05T07:20:54.728384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00694","created_at":"2026-07-05T07:20:54.728384+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OV4EMIZ5SSL","created_at":"2026-07-05T07:20:54.728384+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OV4EMIZ5SSLTQE7","created_at":"2026-07-05T07:20:54.728384+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OV4EMIZ","created_at":"2026-07-05T07:20:54.728384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15147","citing_title":"A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P","json":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P.json","graph_json":"https://pith.science/api/pith-number/4OV4EMIZ5SSLTQE7V3RXYBEF5P/graph.json","events_json":"https://pith.science/api/pith-number/4OV4EMIZ5SSLTQE7V3RXYBEF5P/events.json","paper":"https://pith.science/paper/4OV4EMIZ"},"agent_actions":{"view_html":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P","download_json":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P.json","view_paper":"https://pith.science/paper/4OV4EMIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00694&json=true","fetch_graph":"https://pith.science/api/pith-number/4OV4EMIZ5SSLTQE7V3RXYBEF5P/graph.json","fetch_events":"https://pith.science/api/pith-number/4OV4EMIZ5SSLTQE7V3RXYBEF5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P/action/storage_attestation","attest_author":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P/action/author_attestation","sign_citation":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P/action/citation_signature","submit_replication":"https://pith.science/pith/4OV4EMIZ5SSLTQE7V3RXYBEF5P/action/replication_record"}},"created_at":"2026-07-05T07:20:54.728384+00:00","updated_at":"2026-07-05T07:20:54.728384+00:00"}