{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6QAXISV77VWZBRL5PSR3U5TKZX","short_pith_number":"pith:6QAXISV7","schema_version":"1.0","canonical_sha256":"f401744abffd6d90c57d7ca3ba766acdd0071675b46e4f4b20c5c9929aa23f5b","source":{"kind":"arxiv","id":"2607.27975","version":1},"attestation_state":"computed","paper":{"title":"Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ka\\u{g}an Akman, Naci Saldi, Serdar Y\\\"uksel","submitted_at":"2026-07-30T10:22:38Z","abstract_excerpt":"We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-valued formulation of Transformer dynamics, we view data sets as probability laws on pairs of empirical input-output measures, allowing us to interpret the training problem as a finite-horizon Markovian control problem. We then analyze a quantized model, derived by quantizing the state, action, and measure-state spaces, and derive explicit finite-sample generalization bounds using concentration inequalities for empirical laws on finite metric spaces"},"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":"2607.27975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-30T10:22:38Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"d8702611bb09f4aa27ddfce4ad8835600a797de364dc139cbbc480e63d04a911","abstract_canon_sha256":"c01822247087143acd871669041fcf921e06aa999521e7429f4de7edda57b027"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f401744abffd6d90c57d7ca3ba766acdd0071675b46e4f4b20c5c9929aa23f5b","last_reissued_at":"2026-07-31T01:35:09.796210Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:09.796210Z"},"graph_snapshot":{"paper":{"title":"Generalization Bounds on Optimal Control for Transformer Training and Wasserstein Distributional Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Ka\\u{g}an Akman, Naci Saldi, Serdar Y\\\"uksel","submitted_at":"2026-07-30T10:22:38Z","abstract_excerpt":"We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-valued formulation of Transformer dynamics, we view data sets as probability laws on pairs of empirical input-output measures, allowing us to interpret the training problem as a finite-horizon Markovian control problem. We then analyze a quantized model, derived by quantizing the state, action, and measure-state spaces, and derive explicit finite-sample generalization bounds using concentration inequalities for empirical laws on finite metric spaces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27975","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/2607.27975/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2607.27975","created_at":"2026-07-31T01:35:09.799305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27975v1","created_at":"2026-07-31T01:35:09.799305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27975","created_at":"2026-07-31T01:35:09.799305+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QAXISV77VWZ","created_at":"2026-07-31T01:35:09.799305+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QAXISV77VWZBRL5","created_at":"2026-07-31T01:35:09.799305+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QAXISV7","created_at":"2026-07-31T01:35:09.799305+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/6QAXISV77VWZBRL5PSR3U5TKZX","json":"https://pith.science/pith/6QAXISV77VWZBRL5PSR3U5TKZX.json","graph_json":"https://pith.science/api/pith-number/6QAXISV77VWZBRL5PSR3U5TKZX/graph.json","events_json":"https://pith.science/api/pith-number/6QAXISV77VWZBRL5PSR3U5TKZX/events.json","paper":"https://pith.science/paper/6QAXISV7"},"agent_actions":{"view_html":"https://pith.science/pith/6QAXISV77VWZBRL5PSR3U5TKZX","download_json":"https://pith.science/pith/6QAXISV77VWZBRL5PSR3U5TKZX.json","view_paper":"https://pith.science/paper/6QAXISV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27975&json=true","fetch_graph":"https://pith.science/api/pith-number/6QAXISV77VWZBRL5PSR3U5TKZX/graph.json","fetch_events":"https://pith.science/api/pith-number/6QAXISV77VWZBRL5PSR3U5TKZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QAXISV77VWZBRL5PSR3U5TKZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QAXISV77VWZBRL5PSR3U5TKZX/action/storage_attestation","attest_author":"https://pith.science/pith/6QAXISV77VWZBRL5PSR3U5TKZX/action/author_attestation","sign_citation":"https://pith.science/pith/6QAXISV77VWZBRL5PSR3U5TKZX/action/citation_signature","submit_replication":"https://pith.science/pith/6QAXISV77VWZBRL5PSR3U5TKZX/action/replication_record"}},"created_at":"2026-07-31T01:35:09.799305+00:00","updated_at":"2026-07-31T01:35:09.799305+00:00"}