{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AUGOL3RKSLE222EEGTX47MMWBP","short_pith_number":"pith:AUGOL3RK","schema_version":"1.0","canonical_sha256":"050ce5ee2a92c9ad688434efcfb1960be7700c2e961586b79ed2f61d38920f8d","source":{"kind":"arxiv","id":"2512.11784","version":2},"attestation_state":"computed","paper":{"title":"Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Claire Boyer, Etienne Boursier","submitted_at":"2025-12-12T18:54:52Z","abstract_excerpt":"Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax attention under both finite and infinite prompts. For i.i.d. Gaussian inputs, we lean on the fact that the softmax operator converges in the infinite-prompt limit to a linear operator acting on the underlying input-token measure. Building on this insight, we establish non-asymptotic concentration bounds for the output and gradient of softmax attention, quantifying"},"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":"2512.11784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-12T18:54:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"afcbd8bd8836373493d5c2202625850cb506944f0e11e1ce0f25d27bca0ae76c","abstract_canon_sha256":"5080abe99dc1944bf11c54c37a7848d220da607852c70d69ea03c57daea32793"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:33.532086Z","signature_b64":"lDf4+Kiqsq9P6Oh/stXw0K7jPE1DvoWLmHFMtWPlDUA+9e/UgxVpN9ADNKRKpj0gec7h5W4rdtx2tXWwXqUrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"050ce5ee2a92c9ad688434efcfb1960be7700c2e961586b79ed2f61d38920f8d","last_reissued_at":"2026-06-19T16:10:33.531622Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:33.531622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Softmax as Linear Attention in the Large-Prompt Regime: a Measure-based Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Claire Boyer, Etienne Boursier","submitted_at":"2025-12-12T18:54:52Z","abstract_excerpt":"Softmax attention is a central component of transformer architectures, yet its nonlinear structure poses significant challenges for theoretical analysis. We develop a unified, measure-based framework for studying single-layer softmax attention under both finite and infinite prompts. For i.i.d. Gaussian inputs, we lean on the fact that the softmax operator converges in the infinite-prompt limit to a linear operator acting on the underlying input-token measure. Building on this insight, we establish non-asymptotic concentration bounds for the output and gradient of softmax attention, quantifying"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.11784","kind":"arxiv","version":2},"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/2512.11784/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":"2512.11784","created_at":"2026-06-19T16:10:33.531681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.11784v2","created_at":"2026-06-19T16:10:33.531681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.11784","created_at":"2026-06-19T16:10:33.531681+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUGOL3RKSLE2","created_at":"2026-06-19T16:10:33.531681+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUGOL3RKSLE222EE","created_at":"2026-06-19T16:10:33.531681+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUGOL3RK","created_at":"2026-06-19T16:10:33.531681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16747","citing_title":"Propagation of Chaos in Contextual Flow Maps","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP","json":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP.json","graph_json":"https://pith.science/api/pith-number/AUGOL3RKSLE222EEGTX47MMWBP/graph.json","events_json":"https://pith.science/api/pith-number/AUGOL3RKSLE222EEGTX47MMWBP/events.json","paper":"https://pith.science/paper/AUGOL3RK"},"agent_actions":{"view_html":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP","download_json":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP.json","view_paper":"https://pith.science/paper/AUGOL3RK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.11784&json=true","fetch_graph":"https://pith.science/api/pith-number/AUGOL3RKSLE222EEGTX47MMWBP/graph.json","fetch_events":"https://pith.science/api/pith-number/AUGOL3RKSLE222EEGTX47MMWBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP/action/storage_attestation","attest_author":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP/action/author_attestation","sign_citation":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP/action/citation_signature","submit_replication":"https://pith.science/pith/AUGOL3RKSLE222EEGTX47MMWBP/action/replication_record"}},"created_at":"2026-06-19T16:10:33.531681+00:00","updated_at":"2026-06-19T16:10:33.531681+00:00"}