Claim LD07-HQ-C14 (v1.0)
LLMs can support codebook-driven and deductive qualitative coding in researcher-supervised workflows, reducing coding burden without establishing autonomous interpretive validity.
Research opportunities this claim motivates
What this claim leaves open for research. Each is a hypothesis about a gap, not a finding.
- How do research ethics boards judge synthetic participants and AI-interpreted data?Supervised, codebook-driven LLM coding is the defensible use boards are likely to see.
Provenance and status
- Claim type
- FACT + INTERPRETATION (as printed: “FACT + INTERPRETATION”)
- Publication status
- ELIGIBLE (AUGMENTATION) (as printed: “ELIGIBLE WITH AUGMENTATION QUALIFIER”)
- Verification state
- CONTENT_VERIFIED_PRIMARY (SOURCE_SPECIFIC) (as printed: “CLEARED WITH QUALIFIER”; verified by: UNKNOWN)
- Does not license
- Autonomous reflexive interpretation; independent discovery of latent themes
- Source (field 6, as printed)
- Than et al., Sociological Methods & Research 2025; PLOS Digital Health 2026 thematic-analysis comparison
- Source type (field 7)
- PEER_REVIEWED_JOURNAL_ARTICLE (as printed: “Peer-reviewed journal studies”)
- Institutional position
- Independent academic
- Maturity (claim evidence / publication maturity)
- EMERGING (as printed: “EMERGING”)
- Recorded date
- 2026-09-25
- Currentness / correction
- This is the current version. No correction or concern relation is recorded on its Sources.
Version
Current version v1.0, resolved through the explicit current pointer CLAIM--LD07-HQ-C14.
Pinned Sources (field 6, version-specific)
- “Than et al., Sociological Methods & Research 2025” → SRC-LD07-THAN-FUTURE-OF-CODING-2025--v1.0 — Than, Fan, Law, Nelson & McCall, “Updating ‘The Future of Coding’: Qualitative Coding with Generative Large Language Models,” Sociological Methods & Research 54(3):849–888 (2025); class PEER_REVIEWED_JOURNAL_ARTICLE (explicit public provenance pin)
- “PLOS Digital Health 2026 thematic-analysis comparison” → SRC-LD07-PLOS-THEMATIC-ANALYSIS-2026--v1.0 — “Large language models for thematic analysis in healthcare research: A blinded mixed-methods comparison with human analysts,” PLOS Digital Health 2026; class PEER_REVIEWED_JOURNAL_ARTICLE (explicit public provenance pin)
Read the originals
- SRC-LD07-THAN-FUTURE-OF-CODING-2025: open the original
- SRC-LD07-PLOS-THEMATIC-ANALYSIS-2026: open the original
All 25 canonical Claim fields (raw values and normalized values)
| # | Canonical field | Canonical value (verbatim) | Normalized (Claim Value Vocabulary v1.0.2) |
|---|---|---|---|
| 1 | CLAIM ID | LD07-HQ-C14 | — |
| 2 | PUBLIC-FACING CLAIM | LLMs can support codebook-driven and deductive qualitative coding in researcher-supervised workflows, reducing coding burden without establishing autonomous interpretive validity. | — |
| 3 | CLAIM TYPE | FACT + INTERPRETATION | base_types: FACT, INTERPRETATION |
| 4 | RESEARCH STRAND | E — Retrieval/synthesis/qualitative interpretation | — |
| 5 | MATURITY | EMERGING | states: EMERGING |
| 6 | SOURCE | Than et al., Sociological Methods & Research 2025; PLOS Digital Health 2026 thematic-analysis comparison | source_ids: SRC-LD07-THAN-FUTURE-OF-CODING-2025, SRC-LD07-PLOS-THEMATIC-ANALYSIS-2026 |
| 7 | SOURCE TYPE | Peer-reviewed journal studies | classes: PEER_REVIEWED_JOURNAL_ARTICLE |
| 8 | INSTITUTIONAL POSITION | Independent academic | — |
| 9 | SCOPE | US newsweekly inequality coding; one healthcare focus-group transcript | — |
| 10 | DESIGN | LLM vs hand coding / blinded human comparison; codebook-driven deductive and inductive arms | — |
| 11 | SAMPLE / DATASET | 1,253 news articles; one focus-group transcript/6,200 binary coding values | — |
| 12 | MODEL / TOOL / VERSION | GPT-4 + Llama/Gemma models; ChatGPT-5, Claude 4 Sonnet, QualiGPT | — |
| 13 | COMPARATOR | Hand-coded corpus; blinded human analysts + expert consensus | — |
| 14 | MAIN RESULT | Strong bounded deductive performance; researcher–LLM–researcher workflow; inductive performance more variable | — |
| 15 | INFERENTIAL TARGET | Qualitative coding augmentation | — |
| 16 | DOES NOT LICENSE | Autonomous reflexive interpretation; independent discovery of latent themes | — |
| 17 | VERIFICATION STATE | CLEARED WITH QUALIFIER | state: CONTENT_VERIFIED_PRIMARY · qualifiers: SOURCE_SPECIFIC · verified_by: UNKNOWN |
| 18 | LIMITATIONS | Limited domains; one PLOS transcript; codebook-specific | — |
| 19 | CONTRADICTORY / SUPPORTING SOURCES | Liu et al. shows agreement ≠ independent quality | — |
| 20 | GEOGRAPHY / LANGUAGE | US/English; health and media domains | — |
| 21 | DISTRIBUTIONAL LEDGER | Interpretation of marginal/latent meaning requires human review | — |
| 22 | R01 / FIELD-MAP LINKS | D3, D9, R-2 | — |
| 23 | WHAT WOULD CHANGE THIS CLAIM? | Multi-site independent replication of unattended inductive interpretation | — |
| 24 | PUBLICATION STATUS | ELIGIBLE WITH AUGMENTATION QUALIFIER | state: ELIGIBLE · qualifiers: AUGMENTATION |
| 25 | RECORDED DATE | 2026-09-25 | — |
Field 22 references resolved against Field Map v0.2: D3 (DOMAIN); D9 (DOMAIN); R-2 (LENS)
Cited by Living Debate versions
Research-of-record provenance
Materialized by sociolens-materializer 0.6.0 at 2026-09-28T20:00:00.000Z; normalization contract SocioLens — Claim Value Vocabulary v1.0.2 — Pre-Spike Materialization Contract (v1.0.2). Content seal SHA-256 9179db1757b40ab0bded84f86a05e0bbca88be7c265c483d8183ef4ea9656c8d.
Frozen Drive-derived inputs
- R03 — LD-07 Canonical Claim Ledger v1.0 — LOCKED (v1.0) — Drive ID
1xVz_LrQAA8EA1tPhVWIrDgOUU3Zidlg9; revision: NOT_EXPOSED_BY_DRIVE_TEXT_EXPORT; Drive modified 2026-09-29T04:31:14.120Z; block “ENTRY 14 — LD07-HQ-C14” SHA-256f567de8b346f5ee159f09d094547ea212ba96d3091dc1b5cbae0cd7aac73d962; SocioLens — Programme Status & Authority Register v0.6 status “CURRENT.”; frozen fixturefixtures/frozen/r03-ld07-claim-ledger-v1.0-canonical.
Builder decisions (not Drive data)
- VERSION = v1.0 — basis: Claim version taken from the canonical ledger artifact version (R03 — LD-07 Canonical Claim Ledger v1.0); Implementation Architecture Selection §5
- CURRENT_POINTER = true — basis: SocioLens — Programme Status & Authority Register v0.6 status for "R03 — LD-07 Canonical Claim Ledger v1.0 — LOCKED": "CURRENT."
- FIELD_17_CONTEXT_QUALIFIERS = SOURCE_SPECIFIC — basis: R03 — HQ Cross-Batch Synthesis & Adjudication (v0.1, Drive 1V-HOVaPFwF8BTf60-LGPsJXf59V3kRlQ)
- FIELD_6_SOURCE_REFERENCE = SRC-LD07-THAN-FUTURE-OF-CODING-2025--v1.0 — basis: field 6 of ENTRY 14 — LD07-HQ-C14 cites "Than et al., Sociological Methods & Research 2025"; the frozen field-6 segment of this ClaimVersion's ledger block; Drive-derived identity authority (Issue #39 Source inventory): Batch 04 §7; ledger C14; KEY EVIDENCE.
- FIELD_6_SOURCE_REFERENCE = SRC-LD07-PLOS-THEMATIC-ANALYSIS-2026--v1.0 — basis: field 6 of ENTRY 14 — LD07-HQ-C14 cites "PLOS Digital Health 2026 thematic-analysis comparison"; the frozen field-6 segment of this ClaimVersion's ledger block; Drive-derived identity authority (Issue #39 Source inventory): Batch 04 §8; ledger C14/C15; KEY EVIDENCE.
- SOURCE_PROVENANCE_PIN = SRC-LD07-THAN-FUTURE-OF-CODING-2025--v1.0 — basis: Issue #5 proof rendering (Architecture Proof Protocol v0.1 AP-08 / Amendment v1.2 §6): explicit version-pinned public provenance of this ClaimVersion — the pinned field-6 Source record "Than et al., Sociological Methods & Research 2025"; Drive-derived identity authority (Issue #39 Source inventory): Batch 04 §7; ledger C14; KEY EVIDENCE.
- SOURCE_PROVENANCE_PIN = SRC-LD07-PLOS-THEMATIC-ANALYSIS-2026--v1.0 — basis: Issue #5 proof rendering (Architecture Proof Protocol v0.1 AP-08 / Amendment v1.2 §6): explicit version-pinned public provenance of this ClaimVersion — the pinned field-6 Source record "PLOS Digital Health 2026 thematic-analysis comparison"; Drive-derived identity authority (Issue #39 Source inventory): Batch 04 §8; ledger C14/C15; KEY EVIDENCE.