{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IXBX75LGTHMA2HWIPOEXZZD2CT","short_pith_number":"pith:IXBX75LG","canonical_record":{"source":{"id":"2402.15978","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T03:48:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b858d55d75dc711ef573bf55673418536bfcee7fae93d669c228058a883e5979","abstract_canon_sha256":"dbdbeb4c44bfbed79619845b40bdffad06e61e550bb37fe1fdebc7f8304741c1"},"schema_version":"1.0"},"canonical_sha256":"45c37ff56699d80d1ec87b897ce47a14e80bea6b2416c073ab14eec3a1850ee1","source":{"kind":"arxiv","id":"2402.15978","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15978","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15978v2","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15978","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"IXBX75LGTHMA","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"IXBX75LGTHMA2HWI","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"IXBX75LG","created_at":"2026-07-05T09:30:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IXBX75LGTHMA2HWIPOEXZZD2CT","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15978","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T03:48:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b858d55d75dc711ef573bf55673418536bfcee7fae93d669c228058a883e5979","abstract_canon_sha256":"dbdbeb4c44bfbed79619845b40bdffad06e61e550bb37fe1fdebc7f8304741c1"},"schema_version":"1.0"},"canonical_sha256":"45c37ff56699d80d1ec87b897ce47a14e80bea6b2416c073ab14eec3a1850ee1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:59.668836Z","signature_b64":"2h9lAnBCdODDP8YhocwXIpng8wSM32xnJql1MSbAc9ykS/88YC1dooxY1f21b0dZ1r4r1s/2hAXJrYeNDz1iDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45c37ff56699d80d1ec87b897ce47a14e80bea6b2416c073ab14eec3a1850ee1","last_reissued_at":"2026-07-05T09:30:59.668265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:59.668265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15978","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iKj+mZxyAr9cNoJj7FwGpEY/Qin+emCxF/bkUss2PAU4ns0ftZ1njS9kOAh+BP0nrnwPeG4w70cUlz2+MHz9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T22:19:02.657591Z"},"content_sha256":"8894ee17ab23d1b9b56952b1c1c058285457a9b152de9ae608963150a8dbd7cd","schema_version":"1.0","event_id":"sha256:8894ee17ab23d1b9b56952b1c1c058285457a9b152de9ae608963150a8dbd7cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IXBX75LGTHMA2HWIPOEXZZD2CT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Immer, Betrand Charpentier, Rayen Dhahri, Stephan G\\\"unnemann, Vincent Fortuin","submitted_at":"2024-02-25T03:48:13Z","abstract_excerpt":"Neural network sparsification is a promising avenue to save computational time and memory costs, especially in an age where many successful AI models are becoming too large to na\\\"ively deploy on consumer hardware. While much work has focused on different weight pruning criteria, the overall sparsifiability of the network, i.e., its capacity to be pruned without quality loss, has often been overlooked. We present Sparsifiability via the Marginal likelihood (SpaM), a pruning framework that highlights the effectiveness of using the Bayesian marginal likelihood in conjunction with sparsity-induci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15978","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/2402.15978/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Am322bHQzWUn42VVE2ch1L38aCJESNfH2kAxZKGCQYIcyJTS14L4IYvU8/9rBqE6TT6VguBP/cqxsjWSY/SRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T22:19:02.658012Z"},"content_sha256":"098b3e9b913c5aa6eb4547b2be67cf71b2cdc7c3405e846e36574fbf280b08ef","schema_version":"1.0","event_id":"sha256:098b3e9b913c5aa6eb4547b2be67cf71b2cdc7c3405e846e36574fbf280b08ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXBX75LGTHMA2HWIPOEXZZD2CT/bundle.json","state_url":"https://pith.science/pith/IXBX75LGTHMA2HWIPOEXZZD2CT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXBX75LGTHMA2HWIPOEXZZD2CT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T22:19:02Z","links":{"resolver":"https://pith.science/pith/IXBX75LGTHMA2HWIPOEXZZD2CT","bundle":"https://pith.science/pith/IXBX75LGTHMA2HWIPOEXZZD2CT/bundle.json","state":"https://pith.science/pith/IXBX75LGTHMA2HWIPOEXZZD2CT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXBX75LGTHMA2HWIPOEXZZD2CT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IXBX75LGTHMA2HWIPOEXZZD2CT","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":"dbdbeb4c44bfbed79619845b40bdffad06e61e550bb37fe1fdebc7f8304741c1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T03:48:13Z","title_canon_sha256":"b858d55d75dc711ef573bf55673418536bfcee7fae93d669c228058a883e5979"},"schema_version":"1.0","source":{"id":"2402.15978","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15978","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15978v2","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15978","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"IXBX75LGTHMA","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"IXBX75LGTHMA2HWI","created_at":"2026-07-05T09:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"IXBX75LG","created_at":"2026-07-05T09:30:59Z"}],"graph_snapshots":[{"event_id":"sha256:098b3e9b913c5aa6eb4547b2be67cf71b2cdc7c3405e846e36574fbf280b08ef","target":"graph","created_at":"2026-07-05T09:30:59Z","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/2402.15978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural network sparsification is a promising avenue to save computational time and memory costs, especially in an age where many successful AI models are becoming too large to na\\\"ively deploy on consumer hardware. While much work has focused on different weight pruning criteria, the overall sparsifiability of the network, i.e., its capacity to be pruned without quality loss, has often been overlooked. We present Sparsifiability via the Marginal likelihood (SpaM), a pruning framework that highlights the effectiveness of using the Bayesian marginal likelihood in conjunction with sparsity-induci","authors_text":"Alexander Immer, Betrand Charpentier, Rayen Dhahri, Stephan G\\\"unnemann, Vincent Fortuin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T03:48:13Z","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15978","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":"sha256:8894ee17ab23d1b9b56952b1c1c058285457a9b152de9ae608963150a8dbd7cd","target":"record","created_at":"2026-07-05T09:30:59Z","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":"dbdbeb4c44bfbed79619845b40bdffad06e61e550bb37fe1fdebc7f8304741c1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-25T03:48:13Z","title_canon_sha256":"b858d55d75dc711ef573bf55673418536bfcee7fae93d669c228058a883e5979"},"schema_version":"1.0","source":{"id":"2402.15978","kind":"arxiv","version":2}},"canonical_sha256":"45c37ff56699d80d1ec87b897ce47a14e80bea6b2416c073ab14eec3a1850ee1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45c37ff56699d80d1ec87b897ce47a14e80bea6b2416c073ab14eec3a1850ee1","first_computed_at":"2026-07-05T09:30:59.668265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:59.668265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2h9lAnBCdODDP8YhocwXIpng8wSM32xnJql1MSbAc9ykS/88YC1dooxY1f21b0dZ1r4r1s/2hAXJrYeNDz1iDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:59.668836Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15978","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8894ee17ab23d1b9b56952b1c1c058285457a9b152de9ae608963150a8dbd7cd","sha256:098b3e9b913c5aa6eb4547b2be67cf71b2cdc7c3405e846e36574fbf280b08ef"],"state_sha256":"7d28c4d14935abd1424b0cfb839de3676006265b872e489e8e9d8241654f0790"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMcHHhdDAZu7W4VerAId4e5efFmtJX11OTOav6mKAe+7ZvF38Tt6Nr0lvtYDnMy4fzV1jDB7rhufRk1Y1roTCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T22:19:02.659948Z","bundle_sha256":"4ec15a8328d07df648126762c0338339356b38f214920eabe7f4cba0ef924a61"}}