{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WCEQ5AXWOSUPHVSGJZGPUIXRWN","short_pith_number":"pith:WCEQ5AXW","schema_version":"1.0","canonical_sha256":"b0890e82f674a8f3d6464e4cfa22f1b36312f6554b3a27d92838bb3bc05430bf","source":{"kind":"arxiv","id":"2505.20465","version":1},"attestation_state":"computed","paper":{"title":"Learning with Expected Signatures: Theory and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Almut E. D. Veraart, Lorenzo Lucchese, Mikko S. Pakkanen","submitted_at":"2025-05-26T19:01:20Z","abstract_excerpt":"The expected signature maps a collection of data streams to a lower dimensional representation, with a remarkable property: the resulting feature tensor can fully characterize the data generating distribution. This \"model-free\" embedding has been successfully leveraged to build multiple domain-agnostic machine learning (ML) algorithms for time series and sequential data. The convergence results proved in this paper bridge the gap between the expected signature's empirical discrete-time estimator and its theoretical continuous-time value, allowing for a more complete probabilistic interpretatio"},"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":"2505.20465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-26T19:01:20Z","cross_cats_sorted":["cs.LG","math.PR","math.ST","stat.TH"],"title_canon_sha256":"e41288ba5a047d7fd0844d5ba7eb02ebbc1a2a3e076a39888df00d2861cd45b6","abstract_canon_sha256":"323b5ebbedfcbe144176f5744968f0ce34b86bcc5e4fbbbb8cf721d2991d658a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:22.983194Z","signature_b64":"y5myIkOqZzpSYnAoV79siEviR90gk5OEwjpJAVE6NDQgeisWAiVs/f3x4KXg3Y7Y1CvpYHNTOVuIRH+Yd4aaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0890e82f674a8f3d6464e4cfa22f1b36312f6554b3a27d92838bb3bc05430bf","last_reissued_at":"2026-07-05T11:11:22.982602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:22.982602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Expected Signatures: Theory and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Almut E. D. Veraart, Lorenzo Lucchese, Mikko S. Pakkanen","submitted_at":"2025-05-26T19:01:20Z","abstract_excerpt":"The expected signature maps a collection of data streams to a lower dimensional representation, with a remarkable property: the resulting feature tensor can fully characterize the data generating distribution. This \"model-free\" embedding has been successfully leveraged to build multiple domain-agnostic machine learning (ML) algorithms for time series and sequential data. The convergence results proved in this paper bridge the gap between the expected signature's empirical discrete-time estimator and its theoretical continuous-time value, allowing for a more complete probabilistic interpretatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20465","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/2505.20465/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":"2505.20465","created_at":"2026-07-05T11:11:22.982664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20465v1","created_at":"2026-07-05T11:11:22.982664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20465","created_at":"2026-07-05T11:11:22.982664+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCEQ5AXWOSUP","created_at":"2026-07-05T11:11:22.982664+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCEQ5AXWOSUPHVSG","created_at":"2026-07-05T11:11:22.982664+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCEQ5AXW","created_at":"2026-07-05T11:11:22.982664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05008","citing_title":"Generative Path-Law Jump-Diffusion: Sequential MMD-Gradient Flows and Generalisation Bounds in Marcus-Signature RKHS","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04662","citing_title":"Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN","json":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN.json","graph_json":"https://pith.science/api/pith-number/WCEQ5AXWOSUPHVSGJZGPUIXRWN/graph.json","events_json":"https://pith.science/api/pith-number/WCEQ5AXWOSUPHVSGJZGPUIXRWN/events.json","paper":"https://pith.science/paper/WCEQ5AXW"},"agent_actions":{"view_html":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN","download_json":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN.json","view_paper":"https://pith.science/paper/WCEQ5AXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20465&json=true","fetch_graph":"https://pith.science/api/pith-number/WCEQ5AXWOSUPHVSGJZGPUIXRWN/graph.json","fetch_events":"https://pith.science/api/pith-number/WCEQ5AXWOSUPHVSGJZGPUIXRWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN/action/storage_attestation","attest_author":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN/action/author_attestation","sign_citation":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN/action/citation_signature","submit_replication":"https://pith.science/pith/WCEQ5AXWOSUPHVSGJZGPUIXRWN/action/replication_record"}},"created_at":"2026-07-05T11:11:22.982664+00:00","updated_at":"2026-07-05T11:11:22.982664+00:00"}