{"paper":{"title":"Watts-per-Intelligence Part II: Algorithmic Catalysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Reusable computational structures bound any class-specific speed-up by the algorithmic mutual information between substrate and task descriptor, at a minimum energy cost from Landauer erasure.","cross_cats":["cs.AI","math.IT","physics.comp-ph"],"primary_cat":"cs.IT","authors_text":"Elija Perrier","submitted_at":"2026-04-21T13:36:33Z","abstract_excerpt":"We develop a thermodynamic theory of algorithmic catalysis within the watts per intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that encoding this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We prove that any class-specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that installing this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for a catalyst to be energetically favourable.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That reusable computational structures exist which satisfy bounded restoration and structural selectivity constraints for the task class while allowing the mutual information bound to be achieved in practice.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Reusable algorithmic structures (catalysts) for task classes yield speed-ups upper-bounded by mutual information, with minimum thermodynamic installation costs via Landauer erasure and a lower bound on favorable deployment time.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reusable computational structures bound any class-specific speed-up by the algorithmic mutual information between substrate and task descriptor, at a minimum energy cost from Landauer erasure.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9c8a13e9e5ce9a79826c9bc01670172b0edab80803faf6fbca87e95e152aa828"},"source":{"id":"2604.20897","kind":"arxiv","version":2},"verdict":{"id":"ff564eff-dd2f-4eb7-8fd9-4422a8654ba8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T01:25:04.870553Z","strongest_claim":"We prove that any class-specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that installing this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for a catalyst to be energetically favourable.","one_line_summary":"Reusable algorithmic structures (catalysts) for task classes yield speed-ups upper-bounded by mutual information, with minimum thermodynamic installation costs via Landauer erasure and a lower bound on favorable deployment time.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That reusable computational structures exist which satisfy bounded restoration and structural selectivity constraints for the task class while allowing the mutual information bound to be achieved in practice.","pith_extraction_headline":"Reusable computational structures bound any class-specific speed-up by the algorithmic mutual information between substrate and task descriptor, at a minimum energy cost from Landauer erasure."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.20897/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T02:55:42.371579Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"22e38d9894795f0e8ee6f72f7cce30cb3870a40671d38f6849a44fb92828e209"},"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"}