{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WIEMSXC2Z7HZPTTDLXY55A6F26","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8367976992435a95c3e6d9ef3c166ece339626f8cfa2f0e25c191a65a306748d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T17:37:22Z","title_canon_sha256":"023dcd3a8bae5b3eb0e58bc3e842c4b2edc647424eadf68d9fb21e29a5c96640"},"schema_version":"1.0","source":{"id":"2506.17768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17768","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17768v1","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17768","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_12","alias_value":"WIEMSXC2Z7HZ","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_16","alias_value":"WIEMSXC2Z7HZPTTD","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_8","alias_value":"WIEMSXC2","created_at":"2026-07-05T11:25:22Z"}],"graph_snapshots":[{"event_id":"sha256:83b1646946a53dec35f63f702bd3476ac956aba2825182bd1e73c1c6770787b0","target":"graph","created_at":"2026-07-05T11:25:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.17768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Studies in neuroscience have shown that biological synapses follow a log-normal distribution whose transitioning can be explained by noisy multiplicative dynamics. Biological networks can function stably even under dynamically fluctuating conditions arising due to unreliable synaptic transmissions. Here we ask: Is it possible to design similar multiplicative training in artificial neural networks? To answer this question, we derive a Bayesian learning rule that assumes log-normal posterior distributions over weights which gives rise to a new Log-Normal Multiplicative Dynamics (LMD) algorithm. ","authors_text":"Eren Mehmet K{\\i}ral, Keigo Nishida, Kenichi Bannai, Mohammad Emtiyaz Khan, Thomas M\\\"ollenhoff","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T17:37:22Z","title":"Log-Normal Multiplicative Dynamics for Stable Low-Precision Training of Large Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17768","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:12705093fe410320da5e959dfaa0747a889ae5d9e0282c70eb3bc1df76df7f44","target":"record","created_at":"2026-07-05T11:25:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8367976992435a95c3e6d9ef3c166ece339626f8cfa2f0e25c191a65a306748d","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-21T17:37:22Z","title_canon_sha256":"023dcd3a8bae5b3eb0e58bc3e842c4b2edc647424eadf68d9fb21e29a5c96640"},"schema_version":"1.0","source":{"id":"2506.17768","kind":"arxiv","version":1}},"canonical_sha256":"b208c95c5acfcf97ce635df1de83c5d79600293b74e48bb460fe49445c7c3383","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b208c95c5acfcf97ce635df1de83c5d79600293b74e48bb460fe49445c7c3383","first_computed_at":"2026-07-05T11:25:22.935523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:22.935523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"arR3Rb8tmUl6CzsprBG0x4DVbdf6tseDhEjROgcw9JJMuLyqxJ3xOXeKqy978TYjb2Dm4Xu8vYbCc3HdjUWDBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:22.935875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12705093fe410320da5e959dfaa0747a889ae5d9e0282c70eb3bc1df76df7f44","sha256:83b1646946a53dec35f63f702bd3476ac956aba2825182bd1e73c1c6770787b0"],"state_sha256":"df88742d8e1b6da7e522dc1a71e07ff8e01dc68d8be53f3dc5f386d0615c51b9"}