{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2EZHO36OXZ76EMLNFJMBZPBIBU","short_pith_number":"pith:2EZHO36O","schema_version":"1.0","canonical_sha256":"d132776fcebe7fe2316d2a581cbc280d38631af05e7c39e9f542ececd90ec1fa","source":{"kind":"arxiv","id":"2603.04525","version":2},"attestation_state":"computed","paper":{"title":"The Volterra signature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fabian N. Harang, Luca Pelizzari, Paul P. Hager, Samy Tindel","submitted_at":"2026-03-04T19:10:28Z","abstract_excerpt":"Modern approaches for learning from non-Markovian time series, such as recurrent neural networks, neural controlled differential equations or transformers, typically rely on implicit memory mechanisms that can be difficult to interpret or to train over long horizons. We propose the \\emph{Volterra signature} $\\mathrm{VSig}(x;K)$ as a principled, explicit feature representation for history-dependent systems. By developing the input path $x$ weighted by a temporal kernel $K$ into the tensor algebra, we leverage the associated Volterra--Chen identity to derive rigorous learning-theoretic guarantee"},"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":"2603.04525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-03-04T19:10:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cf7edec09590f8230763cdc1f29866149acdad78b79bab612ff7ba858e9fcd17","abstract_canon_sha256":"ac7fccc019885257bfab6ac2d357aa83ab2232e10edfc56b2389a63f1fd37e5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:59.669199Z","signature_b64":"QRyBjxp5wqVchR5kq+EMgrj0WI+KQFRGylgJvr551woWPXmh/MXmkwWJYILdlj7ZIue0PGs9f2H5GcLLiCjXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d132776fcebe7fe2316d2a581cbc280d38631af05e7c39e9f542ececd90ec1fa","last_reissued_at":"2026-05-22T01:03:59.668533Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:59.668533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Volterra signature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Fabian N. Harang, Luca Pelizzari, Paul P. Hager, Samy Tindel","submitted_at":"2026-03-04T19:10:28Z","abstract_excerpt":"Modern approaches for learning from non-Markovian time series, such as recurrent neural networks, neural controlled differential equations or transformers, typically rely on implicit memory mechanisms that can be difficult to interpret or to train over long horizons. We propose the \\emph{Volterra signature} $\\mathrm{VSig}(x;K)$ as a principled, explicit feature representation for history-dependent systems. By developing the input path $x$ weighted by a temporal kernel $K$ into the tensor algebra, we leverage the associated Volterra--Chen identity to derive rigorous learning-theoretic guarantee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04525","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/2603.04525/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":"2603.04525","created_at":"2026-05-22T01:03:59.668631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.04525v2","created_at":"2026-05-22T01:03:59.668631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04525","created_at":"2026-05-22T01:03:59.668631+00:00"},{"alias_kind":"pith_short_12","alias_value":"2EZHO36OXZ76","created_at":"2026-05-22T01:03:59.668631+00:00"},{"alias_kind":"pith_short_16","alias_value":"2EZHO36OXZ76EMLN","created_at":"2026-05-22T01:03:59.668631+00:00"},{"alias_kind":"pith_short_8","alias_value":"2EZHO36O","created_at":"2026-05-22T01:03:59.668631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.18406","citing_title":"Computational aspects of the Volterra Signature","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15285","citing_title":"Universal Approximation of Nonlinear Operators and Their Derivatives","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13147","citing_title":"Adaptive Learning via Off-Model Training and Importance Sampling for Fully Non-Markovian Optimal Stochastic Control. Complete version","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU","json":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU.json","graph_json":"https://pith.science/api/pith-number/2EZHO36OXZ76EMLNFJMBZPBIBU/graph.json","events_json":"https://pith.science/api/pith-number/2EZHO36OXZ76EMLNFJMBZPBIBU/events.json","paper":"https://pith.science/paper/2EZHO36O"},"agent_actions":{"view_html":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU","download_json":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU.json","view_paper":"https://pith.science/paper/2EZHO36O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.04525&json=true","fetch_graph":"https://pith.science/api/pith-number/2EZHO36OXZ76EMLNFJMBZPBIBU/graph.json","fetch_events":"https://pith.science/api/pith-number/2EZHO36OXZ76EMLNFJMBZPBIBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU/action/storage_attestation","attest_author":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU/action/author_attestation","sign_citation":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU/action/citation_signature","submit_replication":"https://pith.science/pith/2EZHO36OXZ76EMLNFJMBZPBIBU/action/replication_record"}},"created_at":"2026-05-22T01:03:59.668631+00:00","updated_at":"2026-05-22T01:03:59.668631+00:00"}