{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6QDFC2Y4U7PG646RJLUYHTFPOH","short_pith_number":"pith:6QDFC2Y4","schema_version":"1.0","canonical_sha256":"f406516b1ca7de6f73d14ae983ccaf71ffa71e1ba8407e18af9cc750415bf815","source":{"kind":"arxiv","id":"2605.17660","version":1},"attestation_state":"computed","paper":{"title":"Training Infinitely Deep and Wide Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Gradient flow in the conditional Wasserstein metric converges to global minima for infinitely deep and wide transformers when the initial loss is small enough and the attention NTK is injective.","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Gabriel Peyr\\'e, Maarten V. de Hoop, Rapha\\\"el Barboni, Takashi Furuya","submitted_at":"2026-05-17T21:30:13Z","abstract_excerpt":"Transformers have become the dominant architecture in modern machine learning, yet the theoretical understanding of their training dynamics remains limited. This paper develops a rigorous mathematical framework for analyzing gradient-based training of transformers in the mean-field regime, where both the depth (number of layers) and width (number of attention heads) tend to infinity. While ResNet training can be understood as controlling a neural ODE, transformer training corresponds to controlling a neural PDE, due to the coupling of multiple token distributions through the attention mechanis"},"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":"2605.17660","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-17T21:30:13Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"8e2ad1d8fba0ed6441fbfa822016d407e90e873fd5e608931be87cddd501d7fe","abstract_canon_sha256":"62f80cc2f7e1bf01bdc441db144ff1c58a541f85b00010ed393581da69da6f36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:51.430686Z","signature_b64":"FGEIH978NuJOSsL0pIxgfoNyopx9bbnRmz/S2VJU2qGSxOaQm6VgM6SYacN0byvKWa+ZlO5DUnsTrSWO0YZPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f406516b1ca7de6f73d14ae983ccaf71ffa71e1ba8407e18af9cc750415bf815","last_reissued_at":"2026-05-20T00:04:51.429856Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:51.429856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Infinitely Deep and Wide Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Gradient flow in the conditional Wasserstein metric converges to global minima for infinitely deep and wide transformers when the initial loss is small enough and the attention NTK is injective.","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Gabriel Peyr\\'e, Maarten V. de Hoop, Rapha\\\"el Barboni, Takashi Furuya","submitted_at":"2026-05-17T21:30:13Z","abstract_excerpt":"Transformers have become the dominant architecture in modern machine learning, yet the theoretical understanding of their training dynamics remains limited. This paper develops a rigorous mathematical framework for analyzing gradient-based training of transformers in the mean-field regime, where both the depth (number of layers) and width (number of attention heads) tend to infinity. While ResNet training can be understood as controlling a neural ODE, transformer training corresponds to controlling a neural PDE, due to the coupling of multiple token distributions through the attention mechanis"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Under the NTK injectivity assumption (linear independence of log-sum-exp functions modulo affine functions), gradient flow in the conditional Wasserstein metric converges to global minima whenever the initial loss is sufficiently small.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The mean-field limit and the NTK injectivity condition remain valid approximations for the finite but large transformers that are actually trained; this premise enters when the convergence theorem is stated after the injectivity characterization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Develops a mean-field neural PDE model for transformer training, proves forward-pass well-posedness via function-space ODEs, derives conditional Wasserstein gradients, and shows global convergence of gradient flow under an NTK injectivity condition equivalent to linear independence of log-sum-exp fu","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Gradient flow in the conditional Wasserstein metric converges to global minima for infinitely deep and wide transformers when the initial loss is small enough and the attention NTK is injective.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0ef8e9c083ae82fb032841b05de678609a723a0bae106e4075ad4349d14ce7f2"},"source":{"id":"2605.17660","kind":"arxiv","version":1},"verdict":{"id":"3204ae40-3192-4bd1-b78a-c06e6933c0b5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T22:08:22.341277Z","strongest_claim":"Under the NTK injectivity assumption (linear independence of log-sum-exp functions modulo affine functions), gradient flow in the conditional Wasserstein metric converges to global minima whenever the initial loss is sufficiently small.","one_line_summary":"Develops a mean-field neural PDE model for transformer training, proves forward-pass well-posedness via function-space ODEs, derives conditional Wasserstein gradients, and shows global convergence of gradient flow under an NTK injectivity condition equivalent to linear independence of log-sum-exp fu","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The mean-field limit and the NTK injectivity condition remain valid approximations for the finite but large transformers that are actually trained; this premise enters when the convergence theorem is stated after the injectivity characterization.","pith_extraction_headline":"Gradient flow in the conditional Wasserstein metric converges to global minima for infinitely deep and wide transformers when the initial loss is small enough and the attention NTK is injective."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17660/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T22:31:19.483169Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T22:22:11.642152Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:20:57.559089Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:44.270375Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.541285Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.458298Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"bac2ec79408c39f98fce8a078365c1009a4553dbe1fa1e5d7a30ef8a506dd882"},"references":{"count":53,"sample":[{"doi":"","year":2023,"title":"Transformers learn to imple- ment preconditioned gradient descent for in-context learning","work_id":"42670431-9028-4b66-889a-652920100a66","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"What learning algorithm is in-context learning? investigations with linear models","work_id":"f67e4fac-adc7-43d4-b334-b8b9d73e40ac","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"A convergence theory for deep learning via over-parameterization","work_id":"00507d70-4223-4a3a-9734-7857dbf05620","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2008,"title":"Transport equation and Cauchy problem for non-smooth vector fields","work_id":"89b697c2-19c1-4aea-9f8b-ee3e65fac016","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2062,"title":"A user’s guide to optimal transport","work_id":"68f196ac-7a64-491a-a457-3a7adbbd7ede","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":53,"snapshot_sha256":"c623850a99f2bf16a3b1bd791d3031a39a3fc798de23afad680d4b9fdfef9187","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9f10c5a324cfd2b25af36ad09efb6164574e418af8cd7ff37bf1f8d1b6d2aee2"},"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":"2605.17660","created_at":"2026-05-20T00:04:51.429985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17660v1","created_at":"2026-05-20T00:04:51.429985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17660","created_at":"2026-05-20T00:04:51.429985+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QDFC2Y4U7PG","created_at":"2026-05-20T00:04:51.429985+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QDFC2Y4U7PG646R","created_at":"2026-05-20T00:04:51.429985+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QDFC2Y4","created_at":"2026-05-20T00:04:51.429985+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/6QDFC2Y4U7PG646RJLUYHTFPOH","json":"https://pith.science/pith/6QDFC2Y4U7PG646RJLUYHTFPOH.json","graph_json":"https://pith.science/api/pith-number/6QDFC2Y4U7PG646RJLUYHTFPOH/graph.json","events_json":"https://pith.science/api/pith-number/6QDFC2Y4U7PG646RJLUYHTFPOH/events.json","paper":"https://pith.science/paper/6QDFC2Y4"},"agent_actions":{"view_html":"https://pith.science/pith/6QDFC2Y4U7PG646RJLUYHTFPOH","download_json":"https://pith.science/pith/6QDFC2Y4U7PG646RJLUYHTFPOH.json","view_paper":"https://pith.science/paper/6QDFC2Y4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17660&json=true","fetch_graph":"https://pith.science/api/pith-number/6QDFC2Y4U7PG646RJLUYHTFPOH/graph.json","fetch_events":"https://pith.science/api/pith-number/6QDFC2Y4U7PG646RJLUYHTFPOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QDFC2Y4U7PG646RJLUYHTFPOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QDFC2Y4U7PG646RJLUYHTFPOH/action/storage_attestation","attest_author":"https://pith.science/pith/6QDFC2Y4U7PG646RJLUYHTFPOH/action/author_attestation","sign_citation":"https://pith.science/pith/6QDFC2Y4U7PG646RJLUYHTFPOH/action/citation_signature","submit_replication":"https://pith.science/pith/6QDFC2Y4U7PG646RJLUYHTFPOH/action/replication_record"}},"created_at":"2026-05-20T00:04:51.429985+00:00","updated_at":"2026-05-20T00:04:51.429985+00:00"}