{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZCPRGNHRE5HV2X6OKC3NRSGBRU","short_pith_number":"pith:ZCPRGNHR","schema_version":"1.0","canonical_sha256":"c89f1334f1274f5d5fce50b6d8c8c18d266b7daeb7aa1dffc780fd58c2df3a3e","source":{"kind":"arxiv","id":"2412.10139","version":2},"attestation_state":"computed","paper":{"title":"TACOMORE: Exploring a replicable prompting protocol for LLM-assisted corpus analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingru Li, Han Wang, Nicholas Groom","submitted_at":"2024-12-13T13:41:24Z","abstract_excerpt":"As corpus linguistics continues to scale, researchers are facing a growing methodological bottleneck: while computational tools can easily count billions of words, the qualitative interpretation of these data remains a slow and labor-intensive human task. Large Language Models (LLMs) offer a promising way to automate this process, yet their integration into the field is often hindered by concerns over black-box unpredictability and a lack of replicability. This study introduces TACOMORE, a structured prompting framework designed to transform ad-hoc AI interactions into a standardized linguisti"},"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":"2412.10139","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T13:41:24Z","cross_cats_sorted":[],"title_canon_sha256":"e543eeecbadd2203f800fcb7e4cad906dd989c4eaa1d803d95b89b7a1d9de061","abstract_canon_sha256":"407aa98e0a55223b32f14a33fe3fe0643fa43894dbeac22daadc4a1343180ac9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:29.101948Z","signature_b64":"NPorsvx40eOEpkxZwDhmL1kLQ/N2iUX4/4h1YeRAdQ2B29lKunyuTgUagAfDPo3pnpa0FPz1F2zN4B1Q1WcKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c89f1334f1274f5d5fce50b6d8c8c18d266b7daeb7aa1dffc780fd58c2df3a3e","last_reissued_at":"2026-06-19T16:10:29.101567Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:29.101567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TACOMORE: Exploring a replicable prompting protocol for LLM-assisted corpus analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingru Li, Han Wang, Nicholas Groom","submitted_at":"2024-12-13T13:41:24Z","abstract_excerpt":"As corpus linguistics continues to scale, researchers are facing a growing methodological bottleneck: while computational tools can easily count billions of words, the qualitative interpretation of these data remains a slow and labor-intensive human task. Large Language Models (LLMs) offer a promising way to automate this process, yet their integration into the field is often hindered by concerns over black-box unpredictability and a lack of replicability. This study introduces TACOMORE, a structured prompting framework designed to transform ad-hoc AI interactions into a standardized linguisti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10139","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/2412.10139/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":"2412.10139","created_at":"2026-06-19T16:10:29.101621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10139v2","created_at":"2026-06-19T16:10:29.101621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10139","created_at":"2026-06-19T16:10:29.101621+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCPRGNHRE5HV","created_at":"2026-06-19T16:10:29.101621+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCPRGNHRE5HV2X6O","created_at":"2026-06-19T16:10:29.101621+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCPRGNHR","created_at":"2026-06-19T16:10:29.101621+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/ZCPRGNHRE5HV2X6OKC3NRSGBRU","json":"https://pith.science/pith/ZCPRGNHRE5HV2X6OKC3NRSGBRU.json","graph_json":"https://pith.science/api/pith-number/ZCPRGNHRE5HV2X6OKC3NRSGBRU/graph.json","events_json":"https://pith.science/api/pith-number/ZCPRGNHRE5HV2X6OKC3NRSGBRU/events.json","paper":"https://pith.science/paper/ZCPRGNHR"},"agent_actions":{"view_html":"https://pith.science/pith/ZCPRGNHRE5HV2X6OKC3NRSGBRU","download_json":"https://pith.science/pith/ZCPRGNHRE5HV2X6OKC3NRSGBRU.json","view_paper":"https://pith.science/paper/ZCPRGNHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10139&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCPRGNHRE5HV2X6OKC3NRSGBRU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCPRGNHRE5HV2X6OKC3NRSGBRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCPRGNHRE5HV2X6OKC3NRSGBRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCPRGNHRE5HV2X6OKC3NRSGBRU/action/storage_attestation","attest_author":"https://pith.science/pith/ZCPRGNHRE5HV2X6OKC3NRSGBRU/action/author_attestation","sign_citation":"https://pith.science/pith/ZCPRGNHRE5HV2X6OKC3NRSGBRU/action/citation_signature","submit_replication":"https://pith.science/pith/ZCPRGNHRE5HV2X6OKC3NRSGBRU/action/replication_record"}},"created_at":"2026-06-19T16:10:29.101621+00:00","updated_at":"2026-06-19T16:10:29.101621+00:00"}