{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RMS3VONJ6QWDUTAGNEN6O3G36K","short_pith_number":"pith:RMS3VONJ","schema_version":"1.0","canonical_sha256":"8b25bab9a9f42c3a4c06691be76cdbf2a8a99491f4e97b39a928d8e2e23e59be","source":{"kind":"arxiv","id":"2605.15608","version":1},"attestation_state":"computed","paper":{"title":"Transformer-like Inference from Optimal Control","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Aditya Kudre, Heng-Sheng Chang, Prashant G. Mehta","submitted_at":"2026-05-15T04:42:19Z","abstract_excerpt":"Decoder-only transformers compute the conditional probability of the next token from a sequence of past observations. This paper derives, from first principles, inference architectures that solve the same prediction problem - and in doing so, recovers transformer-like layer operations as a consequence of optimal control theory. The framework is developed for two model classes: a nonlinear model of discrete-valued processes, directly motivated by the transformer, and a linear Gaussian model as a tractable baseline. For both model classes, the prediction objective is reformulated as an optimal c"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T04:42:19Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"b2102e332eeb19e5c03e226187e02e91d4b736c0ae67bf9bd9d773a87b20c5ef","abstract_canon_sha256":"7767bd23be719c7d667558b1a147289fd458f39f2c3c0009a57be0301cbc416e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:07.877395Z","signature_b64":"UjUyFJoP8xzXFSkHzIKeE+ShuWPXM3n7Nse0kl+hdu9CaBUeohZrT+lcfZEYMZ7CuBl6WE3tO4BcCE0W82moAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b25bab9a9f42c3a4c06691be76cdbf2a8a99491f4e97b39a928d8e2e23e59be","last_reissued_at":"2026-05-20T00:01:07.876126Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:07.876126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformer-like Inference from Optimal Control","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Aditya Kudre, Heng-Sheng Chang, Prashant G. Mehta","submitted_at":"2026-05-15T04:42:19Z","abstract_excerpt":"Decoder-only transformers compute the conditional probability of the next token from a sequence of past observations. This paper derives, from first principles, inference architectures that solve the same prediction problem - and in doing so, recovers transformer-like layer operations as a consequence of optimal control theory. The framework is developed for two model classes: a nonlinear model of discrete-valued processes, directly motivated by the transformer, and a linear Gaussian model as a tractable baseline. For both model classes, the prediction objective is reformulated as an optimal c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15608","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15608/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:34.622018Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.048385Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e662fdb441e76edbfebf80e60351ac71de87873835b95937a9543ff5aa8c155a"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.15608","created_at":"2026-05-20T00:01:07.876259+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15608v1","created_at":"2026-05-20T00:01:07.876259+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15608","created_at":"2026-05-20T00:01:07.876259+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMS3VONJ6QWD","created_at":"2026-05-20T00:01:07.876259+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMS3VONJ6QWDUTAG","created_at":"2026-05-20T00:01:07.876259+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMS3VONJ","created_at":"2026-05-20T00:01:07.876259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K","json":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K.json","graph_json":"https://pith.science/api/pith-number/RMS3VONJ6QWDUTAGNEN6O3G36K/graph.json","events_json":"https://pith.science/api/pith-number/RMS3VONJ6QWDUTAGNEN6O3G36K/events.json","paper":"https://pith.science/paper/RMS3VONJ"},"agent_actions":{"view_html":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K","download_json":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K.json","view_paper":"https://pith.science/paper/RMS3VONJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15608&json=true","fetch_graph":"https://pith.science/api/pith-number/RMS3VONJ6QWDUTAGNEN6O3G36K/graph.json","fetch_events":"https://pith.science/api/pith-number/RMS3VONJ6QWDUTAGNEN6O3G36K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K/action/storage_attestation","attest_author":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K/action/author_attestation","sign_citation":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K/action/citation_signature","submit_replication":"https://pith.science/pith/RMS3VONJ6QWDUTAGNEN6O3G36K/action/replication_record"}},"created_at":"2026-05-20T00:01:07.876259+00:00","updated_at":"2026-05-20T00:01:07.876259+00:00"}