{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LGUNG3GOYADEHPVTOWOE3PPYTP","short_pith_number":"pith:LGUNG3GO","canonical_record":{"source":{"id":"1910.05422","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-11T21:40:59Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"6953d3510871e55cf45b0c33e2ef13f0378a307e27b75ddf01e6d304b5bd4e89","abstract_canon_sha256":"dabc5d71ee64cfa26b49f931d4f2dee284da6e42b6302f18b839d2d8974a72aa"},"schema_version":"1.0"},"canonical_sha256":"59a8d36ccec00643beb3759c4dbdf89bd660691c386b2dbbe394e005d188aa87","source":{"kind":"arxiv","id":"1910.05422","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05422","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05422v2","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05422","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"pith_short_12","alias_value":"LGUNG3GOYADE","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"pith_short_16","alias_value":"LGUNG3GOYADEHPVT","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"pith_short_8","alias_value":"LGUNG3GO","created_at":"2026-07-05T02:22:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LGUNG3GOYADEHPVTOWOE3PPYTP","target":"record","payload":{"canonical_record":{"source":{"id":"1910.05422","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-11T21:40:59Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"6953d3510871e55cf45b0c33e2ef13f0378a307e27b75ddf01e6d304b5bd4e89","abstract_canon_sha256":"dabc5d71ee64cfa26b49f931d4f2dee284da6e42b6302f18b839d2d8974a72aa"},"schema_version":"1.0"},"canonical_sha256":"59a8d36ccec00643beb3759c4dbdf89bd660691c386b2dbbe394e005d188aa87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:34.460144Z","signature_b64":"HhllXsMlifpfB7htaGHGhAXeh4nDRznjbyqDpowBpDYwFPQZ+YFT9LLZUIWCem5o93wHuZeKgUv+sgktqpdICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59a8d36ccec00643beb3759c4dbdf89bd660691c386b2dbbe394e005d188aa87","last_reissued_at":"2026-07-05T02:22:34.459636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:34.459636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.05422","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":"2026-07-05T02:22:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Zok9zqILpxMI2UqFOccJoPSC8nS2UmlX77B/h12lYmNG5ofP2irFxr/yqSD+TK2lS6qCE5Nq0nMwmhh7IasCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:31:10.359437Z"},"content_sha256":"6bc004a6d82a8016a20dd998e3037fa29d4f0be3b5d14fc2d21210b16ddab5a8","schema_version":"1.0","event_id":"sha256:6bc004a6d82a8016a20dd998e3037fa29d4f0be3b5d14fc2d21210b16ddab5a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LGUNG3GOYADEHPVTOWOE3PPYTP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SiPPing Neural Networks: Sensitivity-informed Provable Pruning of Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cenk Baykal, Dan Feldman, Daniela Rus, Igor Gilitschenski, Lucas Liebenwein","submitted_at":"2019-10-11T21:40:59Z","abstract_excerpt":"We introduce a pruning algorithm that provably sparsifies the parameters of a trained model in a way that approximately preserves the model's predictive accuracy. Our algorithm uses a small batch of input points to construct a data-informed importance sampling distribution over the network's parameters, and adaptively mixes a sampling-based and deterministic pruning procedure to discard redundant weights. Our pruning method is simultaneously computationally efficient, provably accurate, and broadly applicable to various network architectures and data distributions. Our empirical comparisons sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05422","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/1910.05422/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":"2026-07-05T02:22:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Gs851vkkDb/L5uabLSed/VMOVsBNgL5UDDJl5kHs+PRhUfEWtzA3JAg4UoWOILot0j0NaJiWSLe64DeBO8rAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:31:10.359939Z"},"content_sha256":"49f3812f669f39431615720c72657d3a0a67169d77a43f61218156e12455299e","schema_version":"1.0","event_id":"sha256:49f3812f669f39431615720c72657d3a0a67169d77a43f61218156e12455299e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGUNG3GOYADEHPVTOWOE3PPYTP/bundle.json","state_url":"https://pith.science/pith/LGUNG3GOYADEHPVTOWOE3PPYTP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGUNG3GOYADEHPVTOWOE3PPYTP/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":"2026-08-06T09:31:10Z","links":{"resolver":"https://pith.science/pith/LGUNG3GOYADEHPVTOWOE3PPYTP","bundle":"https://pith.science/pith/LGUNG3GOYADEHPVTOWOE3PPYTP/bundle.json","state":"https://pith.science/pith/LGUNG3GOYADEHPVTOWOE3PPYTP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGUNG3GOYADEHPVTOWOE3PPYTP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LGUNG3GOYADEHPVTOWOE3PPYTP","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":"dabc5d71ee64cfa26b49f931d4f2dee284da6e42b6302f18b839d2d8974a72aa","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-11T21:40:59Z","title_canon_sha256":"6953d3510871e55cf45b0c33e2ef13f0378a307e27b75ddf01e6d304b5bd4e89"},"schema_version":"1.0","source":{"id":"1910.05422","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05422","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05422v2","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05422","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"pith_short_12","alias_value":"LGUNG3GOYADE","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"pith_short_16","alias_value":"LGUNG3GOYADEHPVT","created_at":"2026-07-05T02:22:34Z"},{"alias_kind":"pith_short_8","alias_value":"LGUNG3GO","created_at":"2026-07-05T02:22:34Z"}],"graph_snapshots":[{"event_id":"sha256:49f3812f669f39431615720c72657d3a0a67169d77a43f61218156e12455299e","target":"graph","created_at":"2026-07-05T02:22:34Z","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/1910.05422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a pruning algorithm that provably sparsifies the parameters of a trained model in a way that approximately preserves the model's predictive accuracy. Our algorithm uses a small batch of input points to construct a data-informed importance sampling distribution over the network's parameters, and adaptively mixes a sampling-based and deterministic pruning procedure to discard redundant weights. Our pruning method is simultaneously computationally efficient, provably accurate, and broadly applicable to various network architectures and data distributions. Our empirical comparisons sh","authors_text":"Cenk Baykal, Dan Feldman, Daniela Rus, Igor Gilitschenski, Lucas Liebenwein","cross_cats":["cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-11T21:40:59Z","title":"SiPPing Neural Networks: Sensitivity-informed Provable Pruning of Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05422","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":"sha256:6bc004a6d82a8016a20dd998e3037fa29d4f0be3b5d14fc2d21210b16ddab5a8","target":"record","created_at":"2026-07-05T02:22:34Z","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":"dabc5d71ee64cfa26b49f931d4f2dee284da6e42b6302f18b839d2d8974a72aa","cross_cats_sorted":["cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-11T21:40:59Z","title_canon_sha256":"6953d3510871e55cf45b0c33e2ef13f0378a307e27b75ddf01e6d304b5bd4e89"},"schema_version":"1.0","source":{"id":"1910.05422","kind":"arxiv","version":2}},"canonical_sha256":"59a8d36ccec00643beb3759c4dbdf89bd660691c386b2dbbe394e005d188aa87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59a8d36ccec00643beb3759c4dbdf89bd660691c386b2dbbe394e005d188aa87","first_computed_at":"2026-07-05T02:22:34.459636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:22:34.459636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HhllXsMlifpfB7htaGHGhAXeh4nDRznjbyqDpowBpDYwFPQZ+YFT9LLZUIWCem5o93wHuZeKgUv+sgktqpdICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:22:34.460144Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.05422","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bc004a6d82a8016a20dd998e3037fa29d4f0be3b5d14fc2d21210b16ddab5a8","sha256:49f3812f669f39431615720c72657d3a0a67169d77a43f61218156e12455299e"],"state_sha256":"0873187a11dff1844bf9c794bfd462aa806c98dba1fe54ae28c3b8c761d390e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"be6qoz8wSFe4001xgSL5fSE6iX+8ciCHIylNrs5GTDvBA6rWVLGFFiH2SRmY32PrHFkjHTP3Gf1dZ1mCqxtFAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:31:10.363717Z","bundle_sha256":"387306b7dba051a0bffd4052272d3ce369c7e410954cad2039170928a443a739"}}