{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ISVVIX4HJPBREG7KQ7YI56YE5I","short_pith_number":"pith:ISVVIX4H","schema_version":"1.0","canonical_sha256":"44ab545f874bc3121bea87f08efb04ea3fd1229b5498552e57b2e3b920226fa0","source":{"kind":"arxiv","id":"2405.13587","version":1},"attestation_state":"computed","paper":{"title":"Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Christian Holberg, Cristopher Salvi","submitted_at":"2024-05-22T12:34:04Z","abstract_excerpt":"We introduce a mathematically rigorous framework based on rough path theory to model stochastic spiking neural networks (SSNNs) as stochastic differential equations with event discontinuities (Event SDEs) and driven by c\\`adl\\`ag rough paths. Our formalism is general enough to allow for potential jumps to be present both in the solution trajectories as well as in the driving noise. We then identify a set of sufficient conditions ensuring the existence of pathwise gradients of solution trajectories and event times with respect to the network's parameters and show how these gradients satisfy a r"},"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":"2405.13587","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-22T12:34:04Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"09cc9515efcc97262e0bc6def2d09c615d5e130cd1168c94c1d087325eb531e3","abstract_canon_sha256":"ffafb90b216a84f09293a9125f1f3a7d884680375381f0dbb08491124a2908c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:04.896111Z","signature_b64":"Fnqm8dYrkPEnDD634oca1XPbgw471mvYz2vZmiEAdZibNel2Q6BJAgiQvNdYbyhLMlissEIyO0we2pmeemOOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44ab545f874bc3121bea87f08efb04ea3fd1229b5498552e57b2e3b920226fa0","last_reissued_at":"2026-07-05T08:22:04.895662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:04.895662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Christian Holberg, Cristopher Salvi","submitted_at":"2024-05-22T12:34:04Z","abstract_excerpt":"We introduce a mathematically rigorous framework based on rough path theory to model stochastic spiking neural networks (SSNNs) as stochastic differential equations with event discontinuities (Event SDEs) and driven by c\\`adl\\`ag rough paths. Our formalism is general enough to allow for potential jumps to be present both in the solution trajectories as well as in the driving noise. We then identify a set of sufficient conditions ensuring the existence of pathwise gradients of solution trajectories and event times with respect to the network's parameters and show how these gradients satisfy a r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13587","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/2405.13587/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":"2405.13587","created_at":"2026-07-05T08:22:04.895722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13587v1","created_at":"2026-07-05T08:22:04.895722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13587","created_at":"2026-07-05T08:22:04.895722+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISVVIX4HJPBR","created_at":"2026-07-05T08:22:04.895722+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISVVIX4HJPBREG7K","created_at":"2026-07-05T08:22:04.895722+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISVVIX4H","created_at":"2026-07-05T08:22:04.895722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09683","citing_title":"Rough kernel hedging","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I","json":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I.json","graph_json":"https://pith.science/api/pith-number/ISVVIX4HJPBREG7KQ7YI56YE5I/graph.json","events_json":"https://pith.science/api/pith-number/ISVVIX4HJPBREG7KQ7YI56YE5I/events.json","paper":"https://pith.science/paper/ISVVIX4H"},"agent_actions":{"view_html":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I","download_json":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I.json","view_paper":"https://pith.science/paper/ISVVIX4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13587&json=true","fetch_graph":"https://pith.science/api/pith-number/ISVVIX4HJPBREG7KQ7YI56YE5I/graph.json","fetch_events":"https://pith.science/api/pith-number/ISVVIX4HJPBREG7KQ7YI56YE5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I/action/storage_attestation","attest_author":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I/action/author_attestation","sign_citation":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I/action/citation_signature","submit_replication":"https://pith.science/pith/ISVVIX4HJPBREG7KQ7YI56YE5I/action/replication_record"}},"created_at":"2026-07-05T08:22:04.895722+00:00","updated_at":"2026-07-05T08:22:04.895722+00:00"}