{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KPLVVR6N64GFA2KJYP24UIOZIE","short_pith_number":"pith:KPLVVR6N","schema_version":"1.0","canonical_sha256":"53d75ac7cdf70c506949c3f5ca21d9412d51a417e23ffe2493699189de2eff19","source":{"kind":"arxiv","id":"2410.12583","version":1},"attestation_state":"computed","paper":{"title":"STRUX: An LLM for Decision-Making with Structured Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Liu, Hassan Foroosh, Wei Jin, Yebowen Hu, Yiming Lu","submitted_at":"2024-10-16T14:01:22Z","abstract_excerpt":"Countless decisions shape our daily lives, and it is paramount to understand the how and why behind these choices. In this paper, we introduce a new LLM decision-making framework called STRUX, which enhances LLM decision-making by providing structured explanations. These include favorable and adverse facts related to the decision, along with their respective strengths. STRUX begins by distilling lengthy information into a concise table of key facts. It then employs a series of self-reflection steps to determine which of these facts are pivotal, categorizing them as either favorable or adverse "},"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":"2410.12583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T14:01:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b9b562ab8d73adae0c6ff5ce9d897d21a9bd5b2da315f56c86168610733e96a","abstract_canon_sha256":"b4648e9bb211e4c3090fc620eaf5d747419931562d47df142f2183eeb597990e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:31.098891Z","signature_b64":"6nGFBCdNDi5Gd9BRZOUJJT8CRp2PnS1Yl677yhDrDcIvYUFt2+cI0mWZKcnYyy34xzg5yJSyLTWpBoLPUWVnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53d75ac7cdf70c506949c3f5ca21d9412d51a417e23ffe2493699189de2eff19","last_reissued_at":"2026-07-05T09:21:31.098491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:31.098491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STRUX: An LLM for Decision-Making with Structured Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Liu, Hassan Foroosh, Wei Jin, Yebowen Hu, Yiming Lu","submitted_at":"2024-10-16T14:01:22Z","abstract_excerpt":"Countless decisions shape our daily lives, and it is paramount to understand the how and why behind these choices. In this paper, we introduce a new LLM decision-making framework called STRUX, which enhances LLM decision-making by providing structured explanations. These include favorable and adverse facts related to the decision, along with their respective strengths. STRUX begins by distilling lengthy information into a concise table of key facts. It then employs a series of self-reflection steps to determine which of these facts are pivotal, categorizing them as either favorable or adverse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12583","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/2410.12583/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":"2410.12583","created_at":"2026-07-05T09:21:31.098547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12583v1","created_at":"2026-07-05T09:21:31.098547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12583","created_at":"2026-07-05T09:21:31.098547+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPLVVR6N64GF","created_at":"2026-07-05T09:21:31.098547+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPLVVR6N64GFA2KJ","created_at":"2026-07-05T09:21:31.098547+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPLVVR6N","created_at":"2026-07-05T09:21:31.098547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08496","citing_title":"LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE","json":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE.json","graph_json":"https://pith.science/api/pith-number/KPLVVR6N64GFA2KJYP24UIOZIE/graph.json","events_json":"https://pith.science/api/pith-number/KPLVVR6N64GFA2KJYP24UIOZIE/events.json","paper":"https://pith.science/paper/KPLVVR6N"},"agent_actions":{"view_html":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE","download_json":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE.json","view_paper":"https://pith.science/paper/KPLVVR6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12583&json=true","fetch_graph":"https://pith.science/api/pith-number/KPLVVR6N64GFA2KJYP24UIOZIE/graph.json","fetch_events":"https://pith.science/api/pith-number/KPLVVR6N64GFA2KJYP24UIOZIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE/action/storage_attestation","attest_author":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE/action/author_attestation","sign_citation":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE/action/citation_signature","submit_replication":"https://pith.science/pith/KPLVVR6N64GFA2KJYP24UIOZIE/action/replication_record"}},"created_at":"2026-07-05T09:21:31.098547+00:00","updated_at":"2026-07-05T09:21:31.098547+00:00"}