Watching a claim get smaller
I went to check a claim I liked against the benchmark most likely to have taken it. The claim survived, but smaller — and the smaller version is the one worth building on.
Experiments, writing, and interactive pages I built to understand something. Most of what is here is provisional and says so, and the reading list marks which citations I have actually checked.
| edit-slice | Measure whether weight-level knowledge edits (ROME/MEMIT) leave their own grounds intact and contradictory — the orphan category — and show that this backward failure is worse than the forward propagation these methods were tuned against. | Phase 1 — Design |
| rome-neighbors | When a fact is edited in a language model (e.g. "The Eiffel Tower is in Paris" → "The Eiffel Tower is in Rome"), the logically entailed neighbor facts should also update. They usually don't. | Phase 2 — Implementation |
| claim-graph | Feed real research papers in; get a queryable claim graph out — claims as nodes, typed edges (supports / contradicts / refines), every node carrying provenance back to its source sentence in a real paper. | Phase 5 — LLM edge-typer |
I went to check a claim I liked against the benchmark most likely to have taken it. The claim survived, but smaller — and the smaller version is the one worth building on.
| Bilinear representation mitigates reversal curse and enables consistent model editingThe structured-geometry predictor rome-neighbors adopts. Also bears on edit-slice: "reversal curse" is argument order under another name, so this is the closest published work to that half of the distinction. Read before E-009. | next up |
| STEAM: A Semantic-Level Knowledge Editing Framework for Large Language ModelsLatent-space alignment for editing. Note the correction: this is an editing *method*, not an alignment-based *predictor* of propagation, so the "alignment arm" of the predictor comparison may not have a paper behind it yet. Check before building E-009 around it. | next up |
| The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form AnswersThe nearest existing method — mechanistic similarity predicting alignment at up to 78%. But the construct is short-form versus long-form answer agreement, not factual consistency in general, which makes it easier to differentiate from than the one-line note suggested. Still blocking, since it has to be cited either way. | next up |
| Mind | The Belief ProblemWhat it takes to give up a belief, and why removing one is harder than adding one. Walks expansion and contraction over the same belief set. |
| Mind | The Researcher's StreamHow a line of inquiry actually moves — branching, parking, and coming back — rather than the tidy version that appears in a paper. |
| Economics | One CrateA supply chain told through its data problems. Four stops — measurement, Simpson's paradox, variance, the bullwhip effect — each reproducible from a seeded synthetic dataset. |
| AI | Claim Knowledge Graph Explorer111 papers, 736 typed edges. Nodes are extracted claims rather than papers, so you can ask which claim supported or contradicted which. |
| Medicine | ApoB and the Cardiometabolic CascadeWhy the particle count matters more than the cholesterol number, traced through the cascade it sits in. |
| Medicine | Spine Cracking — What Actually HappensThe mechanics behind the sound, and which of the common explanations survive contact with the evidence. |