{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BXFDN5DF6VJDSN42JLBVYN2IGO","short_pith_number":"pith:BXFDN5DF","schema_version":"1.0","canonical_sha256":"0dca36f465f55239379a4ac35c374833a05d69ca95b905d45b98fb25931ba955","source":{"kind":"arxiv","id":"2512.03818","version":2},"attestation_state":"computed","paper":{"title":"Improving Alignment Between Human and Machine Codes: An Empirical Assessment of Prompt Engineering for Construct Identification in Psychology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brittney Hernandez, Claudia Ventura, Kylie L. Anglin, Stephanie Milan","submitted_at":"2025-12-03T14:07:42Z","abstract_excerpt":"Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the prompt. While literature on prompt engineering is expanding, few studies focus on classification tasks, and even fewer address domains like psychology, where constructs have precise, theory-driven definitions that may not be well represented in pre-training data. We present an empirical framework for optimizing LLM performance for identifying constructs in texts "},"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":"2512.03818","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-03T14:07:42Z","cross_cats_sorted":[],"title_canon_sha256":"e71fda1898d0a40918e43d28c1b0729208be2caddecd6206861392da57bde2e3","abstract_canon_sha256":"7cc168a1ac1bc0add7482a7b839f5982dd612297106a66ee157dbd430575a623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:16.796843Z","signature_b64":"kHaqevVECbNrvFXqZ4PMixqbAHfF8252IkZ3fTSMHTweWwcdGpNMpo2SiBmidBImuDZ4AmyY5y/65NruzuafAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dca36f465f55239379a4ac35c374833a05d69ca95b905d45b98fb25931ba955","last_reissued_at":"2026-06-19T16:12:16.796391Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:16.796391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Alignment Between Human and Machine Codes: An Empirical Assessment of Prompt Engineering for Construct Identification in Psychology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brittney Hernandez, Claudia Ventura, Kylie L. Anglin, Stephanie Milan","submitted_at":"2025-12-03T14:07:42Z","abstract_excerpt":"Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the prompt. While literature on prompt engineering is expanding, few studies focus on classification tasks, and even fewer address domains like psychology, where constructs have precise, theory-driven definitions that may not be well represented in pre-training data. We present an empirical framework for optimizing LLM performance for identifying constructs in texts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.03818","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/2512.03818/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":"2512.03818","created_at":"2026-06-19T16:12:16.796449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.03818v2","created_at":"2026-06-19T16:12:16.796449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.03818","created_at":"2026-06-19T16:12:16.796449+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXFDN5DF6VJD","created_at":"2026-06-19T16:12:16.796449+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXFDN5DF6VJDSN42","created_at":"2026-06-19T16:12:16.796449+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXFDN5DF","created_at":"2026-06-19T16:12:16.796449+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/BXFDN5DF6VJDSN42JLBVYN2IGO","json":"https://pith.science/pith/BXFDN5DF6VJDSN42JLBVYN2IGO.json","graph_json":"https://pith.science/api/pith-number/BXFDN5DF6VJDSN42JLBVYN2IGO/graph.json","events_json":"https://pith.science/api/pith-number/BXFDN5DF6VJDSN42JLBVYN2IGO/events.json","paper":"https://pith.science/paper/BXFDN5DF"},"agent_actions":{"view_html":"https://pith.science/pith/BXFDN5DF6VJDSN42JLBVYN2IGO","download_json":"https://pith.science/pith/BXFDN5DF6VJDSN42JLBVYN2IGO.json","view_paper":"https://pith.science/paper/BXFDN5DF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.03818&json=true","fetch_graph":"https://pith.science/api/pith-number/BXFDN5DF6VJDSN42JLBVYN2IGO/graph.json","fetch_events":"https://pith.science/api/pith-number/BXFDN5DF6VJDSN42JLBVYN2IGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXFDN5DF6VJDSN42JLBVYN2IGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXFDN5DF6VJDSN42JLBVYN2IGO/action/storage_attestation","attest_author":"https://pith.science/pith/BXFDN5DF6VJDSN42JLBVYN2IGO/action/author_attestation","sign_citation":"https://pith.science/pith/BXFDN5DF6VJDSN42JLBVYN2IGO/action/citation_signature","submit_replication":"https://pith.science/pith/BXFDN5DF6VJDSN42JLBVYN2IGO/action/replication_record"}},"created_at":"2026-06-19T16:12:16.796449+00:00","updated_at":"2026-06-19T16:12:16.796449+00:00"}