{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H3A5ZPWU23WIWUNPZ7GG3KBJHP","short_pith_number":"pith:H3A5ZPWU","schema_version":"1.0","canonical_sha256":"3ec1dcbed4d6ec8b51afcfcc6da8293bf528d7442942d4ae974f23ef1c084172","source":{"kind":"arxiv","id":"2510.02730","version":2},"attestation_state":"computed","paper":{"title":"Dale meets Langevin: A Multiplicative Denoising Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chandra Sekhar Seelamantula, Madhava Prasath, Nishanth Shetty","submitted_at":"2025-10-03T05:23:33Z","abstract_excerpt":"Exponentiated gradient descent (EGD), a biologically motivated optimisation algorithm that respects Dale's law, produces log-normally distributed synaptic weights at convergence, in alignment with experimental observations in neuroscience. Since the marginal distribution of geometric Brownian motion (GBM) at any fixed time is log-normal, this convergence property reveals a natural connection between EGD and GBM-based stochastic processes. We propose a multiplicative score-based generative model with GBM as a forward noising process and derive its corresponding reverse-time SDE in both the ambi"},"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":"2510.02730","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-03T05:23:33Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"659c8a951e8096361b4a2e04d951be0b084bc2485f7b15823e36b9ee75a6649c","abstract_canon_sha256":"3240d144da4d06cd9baa341fbe9be2c5c3011671ed4209752ce20aa5b9cb50b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:56.822932Z","signature_b64":"SV63eSZdRL8GnXkG3hUrrXwoAPL4lwBjjwx6GL1gRwQzJkfcqs7mkXLeSwFuecLpeMI8fcBGYG+mJX4axjS1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ec1dcbed4d6ec8b51afcfcc6da8293bf528d7442942d4ae974f23ef1c084172","last_reissued_at":"2026-05-26T02:03:56.822292Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:56.822292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dale meets Langevin: A Multiplicative Denoising Diffusion Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chandra Sekhar Seelamantula, Madhava Prasath, Nishanth Shetty","submitted_at":"2025-10-03T05:23:33Z","abstract_excerpt":"Exponentiated gradient descent (EGD), a biologically motivated optimisation algorithm that respects Dale's law, produces log-normally distributed synaptic weights at convergence, in alignment with experimental observations in neuroscience. Since the marginal distribution of geometric Brownian motion (GBM) at any fixed time is log-normal, this convergence property reveals a natural connection between EGD and GBM-based stochastic processes. We propose a multiplicative score-based generative model with GBM as a forward noising process and derive its corresponding reverse-time SDE in both the ambi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02730","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/2510.02730/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":"2510.02730","created_at":"2026-05-26T02:03:56.822427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.02730v2","created_at":"2026-05-26T02:03:56.822427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02730","created_at":"2026-05-26T02:03:56.822427+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3A5ZPWU23WI","created_at":"2026-05-26T02:03:56.822427+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3A5ZPWU23WIWUNP","created_at":"2026-05-26T02:03:56.822427+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3A5ZPWU","created_at":"2026-05-26T02:03:56.822427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.19391","citing_title":"Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP","json":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP.json","graph_json":"https://pith.science/api/pith-number/H3A5ZPWU23WIWUNPZ7GG3KBJHP/graph.json","events_json":"https://pith.science/api/pith-number/H3A5ZPWU23WIWUNPZ7GG3KBJHP/events.json","paper":"https://pith.science/paper/H3A5ZPWU"},"agent_actions":{"view_html":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP","download_json":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP.json","view_paper":"https://pith.science/paper/H3A5ZPWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.02730&json=true","fetch_graph":"https://pith.science/api/pith-number/H3A5ZPWU23WIWUNPZ7GG3KBJHP/graph.json","fetch_events":"https://pith.science/api/pith-number/H3A5ZPWU23WIWUNPZ7GG3KBJHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP/action/storage_attestation","attest_author":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP/action/author_attestation","sign_citation":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP/action/citation_signature","submit_replication":"https://pith.science/pith/H3A5ZPWU23WIWUNPZ7GG3KBJHP/action/replication_record"}},"created_at":"2026-05-26T02:03:56.822427+00:00","updated_at":"2026-05-26T02:03:56.822427+00:00"}