{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LZYAJBCPFS7HVRPUU43IURIQJN","short_pith_number":"pith:LZYAJBCP","schema_version":"1.0","canonical_sha256":"5e7004844f2cbe7ac5f4a7368a45104b79d7cee5e667c1ff1b90a63ec4da02fb","source":{"kind":"arxiv","id":"2411.04551","version":3},"attestation_state":"computed","paper":{"title":"Measure-to-measure interpolation using Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Borjan Geshkovski, Dom\\`enec Ruiz-Balet, Philippe Rigollet","submitted_at":"2024-11-07T09:18:39Z","abstract_excerpt":"Transformers are deep neural network architectures that underpin the recent successes of large language models. Unlike more classical architectures that can be viewed as point-to-point maps, a Transformer acts as a measure-to-measure map implemented as specific interacting particle system on the unit sphere: the input is the empirical measure of tokens in a prompt and its evolution is governed by the continuity equation. In fact, Transformers are not limited to empirical measures and can in principle process any input measure. As the nature of data processed by Transformers is expanding rapidl"},"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":"2411.04551","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-11-07T09:18:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6d2df0b199c78d57e8ca7829b46d2b8e2432e374fbfa739fb354d9b2bcbc316d","abstract_canon_sha256":"e7e7ff079ae8f674ae058c525e8a7d84355f7d6d9546856c9208f80e4da2f83d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:23.929464Z","signature_b64":"G8oXl/ZfGMxRm1jxasuHdzobiMVb5fdNyWsC/Odd+i5k2l6L4nP8TmPBrw/FYZ3LmdMNMDXfitjaGZg0coKKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e7004844f2cbe7ac5f4a7368a45104b79d7cee5e667c1ff1b90a63ec4da02fb","last_reissued_at":"2026-07-28T01:23:23.928581Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:23.928581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measure-to-measure interpolation using Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Borjan Geshkovski, Dom\\`enec Ruiz-Balet, Philippe Rigollet","submitted_at":"2024-11-07T09:18:39Z","abstract_excerpt":"Transformers are deep neural network architectures that underpin the recent successes of large language models. Unlike more classical architectures that can be viewed as point-to-point maps, a Transformer acts as a measure-to-measure map implemented as specific interacting particle system on the unit sphere: the input is the empirical measure of tokens in a prompt and its evolution is governed by the continuity equation. In fact, Transformers are not limited to empirical measures and can in principle process any input measure. As the nature of data processed by Transformers is expanding rapidl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04551","kind":"arxiv","version":3},"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/2411.04551/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":"2411.04551","created_at":"2026-07-28T01:23:23.929020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04551v3","created_at":"2026-07-28T01:23:23.929020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04551","created_at":"2026-07-28T01:23:23.929020+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZYAJBCPFS7H","created_at":"2026-07-28T01:23:23.929020+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZYAJBCPFS7HVRPU","created_at":"2026-07-28T01:23:23.929020+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZYAJBCP","created_at":"2026-07-28T01:23:23.929020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"2605.28075","citing_title":"Measure-to-measure Regression with Transformers","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07600","citing_title":"Reachability and asymptotics of Gaussian Transformer dynamics","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2502.02270","citing_title":"Exact Sequence Interpolation with Transformers","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15608","citing_title":"Transformer-like Inference from Optimal Control","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18870","citing_title":"Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16747","citing_title":"Propagation of Chaos in Contextual Flow Maps","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21366","citing_title":"Perceptrons and localization of attention's mean-field landscape","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08606","citing_title":"Constructive conditional normalizing flows","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26898","citing_title":"Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09213","citing_title":"Kinetic theory for Transformers and the lost-in-the-middle phenomenon","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16653","citing_title":"Continuous transformations of probability measures and their transport representations","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN","json":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN.json","graph_json":"https://pith.science/api/pith-number/LZYAJBCPFS7HVRPUU43IURIQJN/graph.json","events_json":"https://pith.science/api/pith-number/LZYAJBCPFS7HVRPUU43IURIQJN/events.json","paper":"https://pith.science/paper/LZYAJBCP"},"agent_actions":{"view_html":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN","download_json":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN.json","view_paper":"https://pith.science/paper/LZYAJBCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04551&json=true","fetch_graph":"https://pith.science/api/pith-number/LZYAJBCPFS7HVRPUU43IURIQJN/graph.json","fetch_events":"https://pith.science/api/pith-number/LZYAJBCPFS7HVRPUU43IURIQJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN/action/storage_attestation","attest_author":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN/action/author_attestation","sign_citation":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN/action/citation_signature","submit_replication":"https://pith.science/pith/LZYAJBCPFS7HVRPUU43IURIQJN/action/replication_record"}},"created_at":"2026-07-28T01:23:23.929020+00:00","updated_at":"2026-07-28T01:23:23.929020+00:00"}