{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PCU674EPSSMNVPJIJCXA3INR3A","short_pith_number":"pith:PCU674EP","schema_version":"1.0","canonical_sha256":"78a9eff08f9498dabd2848ae0da1b1d80ac301543a7a88c5cba9cf20dc64c353","source":{"kind":"arxiv","id":"2507.01923","version":2},"attestation_state":"computed","paper":{"title":"Decision-Oriented Text Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuan-Ju Wang, Chung-Chi Chen, Yu-Shiang Huang","submitted_at":"2025-07-02T17:32:35Z","abstract_excerpt":"Natural language generation (NLG) is increasingly deployed in high-stakes domains, yet common intrinsic evaluation methods, such as n-gram overlap or sentence plausibility, weakly correlate with actual decision-making efficacy. We propose a decision-oriented framework for evaluating generated text by directly measuring its influence on human and large language model (LLM) decision outcomes. Using market digest texts--including objective morning summaries and subjective closing-bell analyses--as test cases, we assess decision quality based on the financial performance of trades executed by huma"},"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":"2507.01923","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T17:32:35Z","cross_cats_sorted":[],"title_canon_sha256":"b7a1f3d7bd407ab67243743b0f6227bfcf1452b149e82a9500243dfccf84e277","abstract_canon_sha256":"2cfddd8bf288676fbbc48283439850ca82a7413cba3147f95409b8e8c0b809cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:09.377423Z","signature_b64":"hoMY4q3MbWjJeaBvL7WaSZ8XdEYwy4jeYlZarjIu+JzN3oYWvHDKAEyVBiZjloGYhGWZyFG0Mj952IZO+FCSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78a9eff08f9498dabd2848ae0da1b1d80ac301543a7a88c5cba9cf20dc64c353","last_reissued_at":"2026-07-05T11:31:09.376932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:09.376932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decision-Oriented Text Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chuan-Ju Wang, Chung-Chi Chen, Yu-Shiang Huang","submitted_at":"2025-07-02T17:32:35Z","abstract_excerpt":"Natural language generation (NLG) is increasingly deployed in high-stakes domains, yet common intrinsic evaluation methods, such as n-gram overlap or sentence plausibility, weakly correlate with actual decision-making efficacy. We propose a decision-oriented framework for evaluating generated text by directly measuring its influence on human and large language model (LLM) decision outcomes. Using market digest texts--including objective morning summaries and subjective closing-bell analyses--as test cases, we assess decision quality based on the financial performance of trades executed by huma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01923","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/2507.01923/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":"2507.01923","created_at":"2026-07-05T11:31:09.376992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01923v2","created_at":"2026-07-05T11:31:09.376992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01923","created_at":"2026-07-05T11:31:09.376992+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCU674EPSSMN","created_at":"2026-07-05T11:31:09.376992+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCU674EPSSMNVPJI","created_at":"2026-07-05T11:31:09.376992+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCU674EP","created_at":"2026-07-05T11:31:09.376992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A","json":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A.json","graph_json":"https://pith.science/api/pith-number/PCU674EPSSMNVPJIJCXA3INR3A/graph.json","events_json":"https://pith.science/api/pith-number/PCU674EPSSMNVPJIJCXA3INR3A/events.json","paper":"https://pith.science/paper/PCU674EP"},"agent_actions":{"view_html":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A","download_json":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A.json","view_paper":"https://pith.science/paper/PCU674EP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01923&json=true","fetch_graph":"https://pith.science/api/pith-number/PCU674EPSSMNVPJIJCXA3INR3A/graph.json","fetch_events":"https://pith.science/api/pith-number/PCU674EPSSMNVPJIJCXA3INR3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A/action/storage_attestation","attest_author":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A/action/author_attestation","sign_citation":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A/action/citation_signature","submit_replication":"https://pith.science/pith/PCU674EPSSMNVPJIJCXA3INR3A/action/replication_record"}},"created_at":"2026-07-05T11:31:09.376992+00:00","updated_at":"2026-07-05T11:31:09.376992+00:00"}