{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:65VCLIMELH4BDWHKOGV4QAGU4I","short_pith_number":"pith:65VCLIME","schema_version":"1.0","canonical_sha256":"f76a25a18459f811d8ea71abc800d4e2082e52d464261bf4256f9a0ee6a196bb","source":{"kind":"arxiv","id":"2309.17176","version":3},"attestation_state":"computed","paper":{"title":"AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Wanpeng Zhang, Zongqing Lu","submitted_at":"2023-09-29T12:16:19Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant success across various domains. However, their application in complex decision-making tasks frequently necessitates intricate prompt engineering or fine-tuning, leading to challenges in unseen downstream tasks and heavy demands on computational resources. Meanwhile, Reinforcement Learning (RL) has been recognized as effective in decision-making problems but struggles in environments with sparse rewards, such as open-world games. To overcome these challenges, we introduce AdaRefiner, a novel framework designed to enhance the synergy bet"},"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":"2309.17176","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-29T12:16:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"760692457d2712ba86c61fe0de78463b0a39bdcb5ee3a6b9b1f50dd87b2a20cf","abstract_canon_sha256":"8029f3e74bed97f7be2a92bcec0a0015a8b72c99af649d0c84a86bc8d2d67d36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:50.653529Z","signature_b64":"LPBIvP+VUTl5h7mjRq5ccvarg+9r8Qq5ris0VHzBpr76Z2UjPFHzICG9CsIJW2UGLB8/seLhiGIJ5v2ws3FSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f76a25a18459f811d8ea71abc800d4e2082e52d464261bf4256f9a0ee6a196bb","last_reissued_at":"2026-07-05T08:14:50.652942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:50.652942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Wanpeng Zhang, Zongqing Lu","submitted_at":"2023-09-29T12:16:19Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant success across various domains. However, their application in complex decision-making tasks frequently necessitates intricate prompt engineering or fine-tuning, leading to challenges in unseen downstream tasks and heavy demands on computational resources. Meanwhile, Reinforcement Learning (RL) has been recognized as effective in decision-making problems but struggles in environments with sparse rewards, such as open-world games. To overcome these challenges, we introduce AdaRefiner, a novel framework designed to enhance the synergy bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17176","kind":"arxiv","version":3},"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/2309.17176/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":"2309.17176","created_at":"2026-07-05T08:14:50.653033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17176v3","created_at":"2026-07-05T08:14:50.653033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17176","created_at":"2026-07-05T08:14:50.653033+00:00"},{"alias_kind":"pith_short_12","alias_value":"65VCLIMELH4B","created_at":"2026-07-05T08:14:50.653033+00:00"},{"alias_kind":"pith_short_16","alias_value":"65VCLIMELH4BDWHK","created_at":"2026-07-05T08:14:50.653033+00:00"},{"alias_kind":"pith_short_8","alias_value":"65VCLIME","created_at":"2026-07-05T08:14:50.653033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07971","citing_title":"CyberV: Cybernetics for Test-time Scaling in Video Understanding","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I","json":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I.json","graph_json":"https://pith.science/api/pith-number/65VCLIMELH4BDWHKOGV4QAGU4I/graph.json","events_json":"https://pith.science/api/pith-number/65VCLIMELH4BDWHKOGV4QAGU4I/events.json","paper":"https://pith.science/paper/65VCLIME"},"agent_actions":{"view_html":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I","download_json":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I.json","view_paper":"https://pith.science/paper/65VCLIME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17176&json=true","fetch_graph":"https://pith.science/api/pith-number/65VCLIMELH4BDWHKOGV4QAGU4I/graph.json","fetch_events":"https://pith.science/api/pith-number/65VCLIMELH4BDWHKOGV4QAGU4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I/action/storage_attestation","attest_author":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I/action/author_attestation","sign_citation":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I/action/citation_signature","submit_replication":"https://pith.science/pith/65VCLIMELH4BDWHKOGV4QAGU4I/action/replication_record"}},"created_at":"2026-07-05T08:14:50.653033+00:00","updated_at":"2026-07-05T08:14:50.653033+00:00"}