{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W4IR4MBTBMUWWYAXTBFUZ2HB6U","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":"eb6020d0726981b16ff239e7e31ba480e99a33899000e260380bcfd035e15702","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T14:08:04Z","title_canon_sha256":"3ed5e6d2089dceeea7e8d5bbce54c79c32935ba95f43fceef3bcc9593e015b46"},"schema_version":"1.0","source":{"id":"2406.01345","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01345","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01345v2","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01345","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"W4IR4MBTBMUW","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"pith_short_16","alias_value":"W4IR4MBTBMUWWYAX","created_at":"2026-07-05T09:52:12Z"},{"alias_kind":"pith_short_8","alias_value":"W4IR4MBT","created_at":"2026-07-05T09:52:12Z"}],"graph_snapshots":[{"event_id":"sha256:720651ed245386f855dc500c6fc84c7c0939c21fa04b16ec434032025b7fb93d","target":"graph","created_at":"2026-07-05T09:52:12Z","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/2406.01345/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern neural networks are often massively overparameterized leading to high compute costs during training and at inference. One effective method to improve both the compute and energy efficiency of neural networks while maintaining good performance is structured pruning, where full network structures (e.g.~neurons or convolutional filters) that have limited impact on the model output are removed. In this work, we propose Bayesian Model Reduction for Structured pruning (BMRS), a fully end-to-end Bayesian method of structured pruning. BMRS is based on two recent methods: Bayesian structured pru","authors_text":"Christian Igel, Dustin Wright, Raghavendra Selvan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T14:08:04Z","title":"BMRS: Bayesian Model Reduction for Structured Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01345","kind":"arxiv","version":2},"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":"sha256:008e4bbfffa5326ad78313c84e4b72ffdb3e3686222079507d57c91ad102837f","target":"record","created_at":"2026-07-05T09:52:12Z","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":"eb6020d0726981b16ff239e7e31ba480e99a33899000e260380bcfd035e15702","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T14:08:04Z","title_canon_sha256":"3ed5e6d2089dceeea7e8d5bbce54c79c32935ba95f43fceef3bcc9593e015b46"},"schema_version":"1.0","source":{"id":"2406.01345","kind":"arxiv","version":2}},"canonical_sha256":"b7111e30330b296b6017984b4ce8e1f532eefcba5a30e570b19e2a7e53b52b7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7111e30330b296b6017984b4ce8e1f532eefcba5a30e570b19e2a7e53b52b7c","first_computed_at":"2026-07-05T09:52:12.095974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:12.095974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RjYwB75paeFSHDNYG8oqVXylhNn9pwtNyigq0HlB5NGZC8hCco67IRQvUByvCodCykSxGFo+p76XatQ4HetBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:12.096416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01345","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:008e4bbfffa5326ad78313c84e4b72ffdb3e3686222079507d57c91ad102837f","sha256:720651ed245386f855dc500c6fc84c7c0939c21fa04b16ec434032025b7fb93d"],"state_sha256":"46bf832788a3b5938d92e2f445f2dcd65b5e46783bc7bbd766ae675d74aa9223"}