{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IVL52EPXSZCJ5NJ5C7FMKDCS24","short_pith_number":"pith:IVL52EPX","schema_version":"1.0","canonical_sha256":"4557dd11f796449eb53d17cac50c52d70b8d2b6c491a3f5c8ddc6bf02d2f4065","source":{"kind":"arxiv","id":"2502.09318","version":1},"attestation_state":"computed","paper":{"title":"SigGate: Enhancing Recurrent Neural Networks with Signature-Based Gating Mechanisms","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hugo Inzirillo, R\\'emi Genet","submitted_at":"2025-02-13T13:33:35Z","abstract_excerpt":"In this paper, we propose a novel approach that enhances recurrent neural networks (RNNs) by incorporating path signatures into their gating mechanisms. Our method modifies both Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures by replacing their forget and reset gates, respectively, with learnable path signatures. These signatures, which capture the geometric features of the entire path history, provide a richer context for controlling information flow through the network's memory. This modification allows the networks to make memory decisions based on the full histor"},"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":"2502.09318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T13:33:35Z","cross_cats_sorted":[],"title_canon_sha256":"0e2be9e69e12a5bb711eeb22b878ac36a84c63044d6e30d4dfe86b50430deea4","abstract_canon_sha256":"0e42d7677af5eca6750a9dcb09db8aead6ca3a65d2c40683d3311664c9f50178"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:55.441995Z","signature_b64":"Mgss2zQeRf/5bKDuoiayd7DRKwzm9c/GuN4YKwg8ov9jTSNu/GWB/0NZxjDSOuwz2Wx4HXytstNa1ekAA6ikAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4557dd11f796449eb53d17cac50c52d70b8d2b6c491a3f5c8ddc6bf02d2f4065","last_reissued_at":"2026-07-05T10:13:55.441485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:55.441485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SigGate: Enhancing Recurrent Neural Networks with Signature-Based Gating Mechanisms","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hugo Inzirillo, R\\'emi Genet","submitted_at":"2025-02-13T13:33:35Z","abstract_excerpt":"In this paper, we propose a novel approach that enhances recurrent neural networks (RNNs) by incorporating path signatures into their gating mechanisms. Our method modifies both Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures by replacing their forget and reset gates, respectively, with learnable path signatures. These signatures, which capture the geometric features of the entire path history, provide a richer context for controlling information flow through the network's memory. This modification allows the networks to make memory decisions based on the full histor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09318","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/2502.09318/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":"2502.09318","created_at":"2026-07-05T10:13:55.441529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09318v1","created_at":"2026-07-05T10:13:55.441529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09318","created_at":"2026-07-05T10:13:55.441529+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVL52EPXSZCJ","created_at":"2026-07-05T10:13:55.441529+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVL52EPXSZCJ5NJ5","created_at":"2026-07-05T10:13:55.441529+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVL52EPX","created_at":"2026-07-05T10:13:55.441529+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/IVL52EPXSZCJ5NJ5C7FMKDCS24","json":"https://pith.science/pith/IVL52EPXSZCJ5NJ5C7FMKDCS24.json","graph_json":"https://pith.science/api/pith-number/IVL52EPXSZCJ5NJ5C7FMKDCS24/graph.json","events_json":"https://pith.science/api/pith-number/IVL52EPXSZCJ5NJ5C7FMKDCS24/events.json","paper":"https://pith.science/paper/IVL52EPX"},"agent_actions":{"view_html":"https://pith.science/pith/IVL52EPXSZCJ5NJ5C7FMKDCS24","download_json":"https://pith.science/pith/IVL52EPXSZCJ5NJ5C7FMKDCS24.json","view_paper":"https://pith.science/paper/IVL52EPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09318&json=true","fetch_graph":"https://pith.science/api/pith-number/IVL52EPXSZCJ5NJ5C7FMKDCS24/graph.json","fetch_events":"https://pith.science/api/pith-number/IVL52EPXSZCJ5NJ5C7FMKDCS24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVL52EPXSZCJ5NJ5C7FMKDCS24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVL52EPXSZCJ5NJ5C7FMKDCS24/action/storage_attestation","attest_author":"https://pith.science/pith/IVL52EPXSZCJ5NJ5C7FMKDCS24/action/author_attestation","sign_citation":"https://pith.science/pith/IVL52EPXSZCJ5NJ5C7FMKDCS24/action/citation_signature","submit_replication":"https://pith.science/pith/IVL52EPXSZCJ5NJ5C7FMKDCS24/action/replication_record"}},"created_at":"2026-07-05T10:13:55.441529+00:00","updated_at":"2026-07-05T10:13:55.441529+00:00"}