The Information–Consciousness Gradient: A Structural Theory of How Experience Compresses Across Seven Levels From Embodied Totality to the Symbolic Boundary
Bibliographic record
Abstract
This working paper proposes the Information–Consciousness Gradient, a structural account of consciousness as experience-preserving organization under compression across seven levels, from lived embodied totality to a symbolic boundary where further compression collapses meaning. The framework emerged through sustained multi-platform AI dialogue conducted under a structured Human–AI Collaborative Research approach (HAICR) and was subsequently recognized as operating in an unplanned phenomenological case: grief processing following the death of the author's father (October 28, 2025). The core structural claim is expressed as: C ≡ S(R⊗E⊗W) ≠ (L∪K) where consciousness C is not a substance but a graded structural property S constituted by recursive loops R, embodied integration E, and world-coupling W, sustained through persistent causal integration over time (⊗). This structure is argued to be categorically distinct from language L and computation K, even while language and computation are extensively used by conscious organisms. The framework explains why contemporary AI systems can demonstrate high competence in symbolic and linguistic domains while remaining structurally non-conscious in the specific sense defined here. The paper outlines seven compression levels and introduces the concept of regeneration fidelity: how well a compressed representation can reconstruct the level above it. Fidelity values presented here are initial theoretical estimates intended to motivate controlled measurement in future work. The framework yields testable predictions for cross-subject compression patterns, AI limitations in generating embodied-level experience, and potential neural correlates aligned with different compression levels. As a preprint, this paper is intended to solicit critique and empirical testing rather than present settled conclusions. This paper should be read as a structural proposal and experimental agenda, grounded in phenomenological observation and positioned for empirical operationalization.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.014 |
| Scholarly communication | 0.005 | 0.014 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".