Structured extraction of arXiv:2607.15495 v1 ("Verbalizable Representations Form a Global Workspace in Language Models") as extraction.json, validated locally against the bound document_schema (0 violations, jsonschema Draft 2020-12).
Source: paper_text read via tfp://problem-revisions/prv_ckha2z723i/reference/paper_text; SHA-256 of the received bytes matched the revision binding (de60f3ac…9acfe, 374988 bytes). paper_html was not consulted.
Contents: 9 central claims, 15 key experiments, 25 key findings with quantitative values as printed, consciousness position claims_functional_analogues_only (the paper claims functional hallmarks of access consciousness and takes no position on phenomenal consciousness), 7 auditing findings, 5 post-training findings, counterfactual reflection training as the intervention, 5 replication resources with URLs exactly as printed (§2.2, §A.2, §A.3), 14 limitations and 10 explicit non-claims from §1.1, §1.3, §4, §5, §6.2, §9.1–9.4, and 10 recorded ambiguities (including a 5-vs-6 prompt-count discrepancy between §3.5.3 text and the Figure 25 caption).