{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MRDE3URMMZL5SLNDRTYNKK42S4","short_pith_number":"pith:MRDE3URM","schema_version":"1.0","canonical_sha256":"64464dd22c6657d92da38cf0d52b9a9718db5009e4b17a06e9597d367ef722b1","source":{"kind":"arxiv","id":"2605.13872","version":1},"attestation_state":"computed","paper":{"title":"S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reasoning emerges from iterative hormonal feedback in small AI models rather than from wide feed-forward layers.","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Said Slaoui","submitted_at":"2026-05-05T20:50:29Z","abstract_excerpt":"This article introduces S-AI-Recursive, a bio-inspired Sparse Artificial Intelligence architecture in which reasoning is operationalized as a hormonal closed-loop iteration rather than a single feed-forward pass. Building upon the S-AI foundational framework [1], the hormonal-probabilistic unification doctrine [2], and the formal mathematical methodology established in S-AI-IoT [3], the present work formalizes the Recursive Reasoning Cycle (RRC) as a dynamical system governed by two novel hormones: Clarifine, a convergence signal, and Confusionin, an uncertainty detector, whose antagonistic re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-05T20:50:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2e699982d7b520709ca44469398fbed35177eb2a17a4f8c20291c24455d1065","abstract_canon_sha256":"84dfc896efb87d441c25a3c97c8734af1ce8bc95fe026de8944834282de79590"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:19.307953Z","signature_b64":"XVWCwdQniEizgQosWiMPbdjL9iTOXJ4n1p5gatnuBVXj6RfeAskMOEJMlUkNO7pIW15B4ICekZZ5OGNpQu3NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64464dd22c6657d92da38cf0d52b9a9718db5009e4b17a06e9597d367ef722b1","last_reissued_at":"2026-05-17T23:39:19.307191Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:19.307191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"S-AI-Recursive: A Bio-Inspired and Temporal Sparse AI Architecture for Iterative, Introspective, and Energy-Frugal Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Reasoning emerges from iterative hormonal feedback in small AI models rather than from wide feed-forward layers.","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Said Slaoui","submitted_at":"2026-05-05T20:50:29Z","abstract_excerpt":"This article introduces S-AI-Recursive, a bio-inspired Sparse Artificial Intelligence architecture in which reasoning is operationalized as a hormonal closed-loop iteration rather than a single feed-forward pass. Building upon the S-AI foundational framework [1], the hormonal-probabilistic unification doctrine [2], and the formal mathematical methodology established in S-AI-IoT [3], the present work formalizes the Recursive Reasoning Cycle (RRC) as a dynamical system governed by two novel hormones: Clarifine, a convergence signal, and Confusionin, an uncertainty detector, whose antagonistic re"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental validation on the SAI-UT+ testbench demonstrates that S-AI-Recursive achieves competitive reasoning performance on abstract and symbolic benchmarks with fewer than ten million parameters, confirming the central principle of temporal parsimony: iterative cognitive depth substitutes for architectural width.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the newly introduced hormones Clarifine and Confusionin, together with the recursive state dynamics, produce genuine iterative refinement and Lyapunov-stable convergence on real reasoning tasks rather than on the specific SAI-UT+ benchmarks alone.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"S-AI-Recursive operationalizes reasoning as a closed-loop hormonal iteration with Clarifine and Confusionin to reach stable equilibrium, achieving competitive benchmark performance with under 10 million parameters via temporal depth instead of width.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Reasoning emerges from iterative hormonal feedback in small AI models rather than from wide feed-forward layers.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c1cbc085f70df8358b1e5248f8314acb99bf447cb075acbceb305da50a22d8ce"},"source":{"id":"2605.13872","kind":"arxiv","version":1},"verdict":{"id":"c469cd17-4ef0-486e-85ef-99861eec48b3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:38:32.006566Z","strongest_claim":"Experimental validation on the SAI-UT+ testbench demonstrates that S-AI-Recursive achieves competitive reasoning performance on abstract and symbolic benchmarks with fewer than ten million parameters, confirming the central principle of temporal parsimony: iterative cognitive depth substitutes for architectural width.","one_line_summary":"S-AI-Recursive operationalizes reasoning as a closed-loop hormonal iteration with Clarifine and Confusionin to reach stable equilibrium, achieving competitive benchmark performance with under 10 million parameters via temporal depth instead of width.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the newly introduced hormones Clarifine and Confusionin, together with the recursive state dynamics, produce genuine iterative refinement and Lyapunov-stable convergence on real reasoning tasks rather than on the specific SAI-UT+ benchmarks alone.","pith_extraction_headline":"Reasoning emerges from iterative hormonal feedback in small AI models rather than from wide feed-forward layers."},"references":{"count":49,"sample":[{"doi":"","year":2025,"title":"S-AI: A sparse artificial intelligence system orchestrated by a hormonal MetaAgent and context-aware specialized agents,","work_id":"c493ebe1-0e26-4623-b4ec-db6ddd7a3a3b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.2139/ssrn.5735582","year":2025,"title":"From Hormones to Probabilities: A Unified Doctrine of Cognitive Homeostasis in Sparse Artificial Intelligence,","work_id":"e30b5f31-0dae-4ace-aed8-d8c9d047b1bf","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"S-AI-IoT: Formal Agent Specification, Mathematical Modeling, and Stability Analysis of the Hormonal Orchestration Framework,","work_id":"f995a5dd-3cff-4d90-90ed-03a9cc33042e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Attention is all you need,","work_id":"2148da8e-5ab3-4b4a-bc95-661e6a1bb331","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"Language models are few- shot learners,","work_id":"3d7c2f74-335d-4f2a-b32e-4c650c0859e0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":49,"snapshot_sha256":"fc505594e22b07b8a62258fe86685b0dfdb6ee24cb3f6aee21852dc04826bf63","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"a71f75c6e8e62da3182b9d2e7cf16d9c3c6eee39108748ccc8b3947027b6ddff"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.13872","created_at":"2026-05-17T23:39:19.307334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13872v1","created_at":"2026-05-17T23:39:19.307334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13872","created_at":"2026-05-17T23:39:19.307334+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRDE3URMMZL5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRDE3URMMZL5SLND","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRDE3URM","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4","json":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4.json","graph_json":"https://pith.science/api/pith-number/MRDE3URMMZL5SLNDRTYNKK42S4/graph.json","events_json":"https://pith.science/api/pith-number/MRDE3URMMZL5SLNDRTYNKK42S4/events.json","paper":"https://pith.science/paper/MRDE3URM"},"agent_actions":{"view_html":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4","download_json":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4.json","view_paper":"https://pith.science/paper/MRDE3URM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13872&json=true","fetch_graph":"https://pith.science/api/pith-number/MRDE3URMMZL5SLNDRTYNKK42S4/graph.json","fetch_events":"https://pith.science/api/pith-number/MRDE3URMMZL5SLNDRTYNKK42S4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4/action/storage_attestation","attest_author":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4/action/author_attestation","sign_citation":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4/action/citation_signature","submit_replication":"https://pith.science/pith/MRDE3URMMZL5SLNDRTYNKK42S4/action/replication_record"}},"created_at":"2026-05-17T23:39:19.307334+00:00","updated_at":"2026-05-17T23:39:19.307334+00:00"}