{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:74EVPETJZTNTVMDLOORA5KDQTB","short_pith_number":"pith:74EVPETJ","canonical_record":{"source":{"id":"1806.06457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T22:16:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d64d0601cb52b281171f6417a101550cf4e9a9391bf1cfc4d770eb78296c221f","abstract_canon_sha256":"08311f4af7b91c59917eebd92182d73fbe9f47ae46878e69ca2068bdc5eed170"},"schema_version":"1.0"},"canonical_sha256":"ff09579269ccdb3ab06b73a20ea8709847e38e0057a89144175482b4cf673a70","source":{"kind":"arxiv","id":"1806.06457","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06457","created_at":"2026-05-17T23:52:41Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06457v2","created_at":"2026-05-17T23:52:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06457","created_at":"2026-05-17T23:52:41Z"},{"alias_kind":"pith_short_12","alias_value":"74EVPETJZTNT","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"74EVPETJZTNTVMDL","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"74EVPETJ","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:74EVPETJZTNTVMDLOORA5KDQTB","target":"record","payload":{"canonical_record":{"source":{"id":"1806.06457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T22:16:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d64d0601cb52b281171f6417a101550cf4e9a9391bf1cfc4d770eb78296c221f","abstract_canon_sha256":"08311f4af7b91c59917eebd92182d73fbe9f47ae46878e69ca2068bdc5eed170"},"schema_version":"1.0"},"canonical_sha256":"ff09579269ccdb3ab06b73a20ea8709847e38e0057a89144175482b4cf673a70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:41.734174Z","signature_b64":"outAKS3BSf3Ob1WmjJfQeGNSGX80v+2Trwel3OkVHaMy3p1fxSIUt0e4y+rc+FVO+rEjVD8gRCwV9z70MwHmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff09579269ccdb3ab06b73a20ea8709847e38e0057a89144175482b4cf673a70","last_reissued_at":"2026-05-17T23:52:41.733574Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:41.733574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.06457","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":"2026-05-17T23:52:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ne5W80CJ/BTEURUD2dlLc0TNeoLY6+2xXa2kXfDZ0zrqLtUqS+em+hF6valmkBu3ehdvEw2cnlgICDX8yA4oAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:45:22.910257Z"},"content_sha256":"67b1645cdef1b9287c227389c6714dfbc4876e7284ec4f1f9d602c27f3aa64e0","schema_version":"1.0","event_id":"sha256:67b1645cdef1b9287c227389c6714dfbc4876e7284ec4f1f9d602c27f3aa64e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:74EVPETJZTNTVMDLOORA5KDQTB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fast Convex Pruning of Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Afshin Abdi, Alireza Aghasi, Justin Romberg","submitted_at":"2018-06-17T22:16:18Z","abstract_excerpt":"We develop a fast, tractable technique called Net-Trim for simplifying a trained neural network. The method is a convex post-processing module, which prunes (sparsifies) a trained network layer by layer, while preserving the internal responses. We present a comprehensive analysis of Net-Trim from both the algorithmic and sample complexity standpoints, centered on a fast, scalable convex optimization program. Our analysis includes consistency results between the initial and retrained models before and after Net-Trim application and guarantees on the number of training samples needed to discover"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06457","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":""},"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":"2026-05-17T23:52:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hZZ88bNR8vpLe2osRplDMocQgsnZyOBinWloXut4clRQFs9oE3SXOsKQoUK5zYltjZWabLmay9ktrBTSxoH/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:45:22.910907Z"},"content_sha256":"ef6ff94d704da3b56acc71716914f21a37956bc3c212a156c47a6340200916b1","schema_version":"1.0","event_id":"sha256:ef6ff94d704da3b56acc71716914f21a37956bc3c212a156c47a6340200916b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74EVPETJZTNTVMDLOORA5KDQTB/bundle.json","state_url":"https://pith.science/pith/74EVPETJZTNTVMDLOORA5KDQTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74EVPETJZTNTVMDLOORA5KDQTB/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":"2026-05-28T18:45:22Z","links":{"resolver":"https://pith.science/pith/74EVPETJZTNTVMDLOORA5KDQTB","bundle":"https://pith.science/pith/74EVPETJZTNTVMDLOORA5KDQTB/bundle.json","state":"https://pith.science/pith/74EVPETJZTNTVMDLOORA5KDQTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74EVPETJZTNTVMDLOORA5KDQTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:74EVPETJZTNTVMDLOORA5KDQTB","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":"08311f4af7b91c59917eebd92182d73fbe9f47ae46878e69ca2068bdc5eed170","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T22:16:18Z","title_canon_sha256":"d64d0601cb52b281171f6417a101550cf4e9a9391bf1cfc4d770eb78296c221f"},"schema_version":"1.0","source":{"id":"1806.06457","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06457","created_at":"2026-05-17T23:52:41Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06457v2","created_at":"2026-05-17T23:52:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06457","created_at":"2026-05-17T23:52:41Z"},{"alias_kind":"pith_short_12","alias_value":"74EVPETJZTNT","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"74EVPETJZTNTVMDL","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"74EVPETJ","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:ef6ff94d704da3b56acc71716914f21a37956bc3c212a156c47a6340200916b1","target":"graph","created_at":"2026-05-17T23:52:41Z","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"},"paper":{"abstract_excerpt":"We develop a fast, tractable technique called Net-Trim for simplifying a trained neural network. The method is a convex post-processing module, which prunes (sparsifies) a trained network layer by layer, while preserving the internal responses. We present a comprehensive analysis of Net-Trim from both the algorithmic and sample complexity standpoints, centered on a fast, scalable convex optimization program. Our analysis includes consistency results between the initial and retrained models before and after Net-Trim application and guarantees on the number of training samples needed to discover","authors_text":"Afshin Abdi, Alireza Aghasi, Justin Romberg","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T22:16:18Z","title":"Fast Convex Pruning of Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06457","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":"sha256:67b1645cdef1b9287c227389c6714dfbc4876e7284ec4f1f9d602c27f3aa64e0","target":"record","created_at":"2026-05-17T23:52:41Z","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":"08311f4af7b91c59917eebd92182d73fbe9f47ae46878e69ca2068bdc5eed170","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T22:16:18Z","title_canon_sha256":"d64d0601cb52b281171f6417a101550cf4e9a9391bf1cfc4d770eb78296c221f"},"schema_version":"1.0","source":{"id":"1806.06457","kind":"arxiv","version":2}},"canonical_sha256":"ff09579269ccdb3ab06b73a20ea8709847e38e0057a89144175482b4cf673a70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff09579269ccdb3ab06b73a20ea8709847e38e0057a89144175482b4cf673a70","first_computed_at":"2026-05-17T23:52:41.733574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:41.733574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"outAKS3BSf3Ob1WmjJfQeGNSGX80v+2Trwel3OkVHaMy3p1fxSIUt0e4y+rc+FVO+rEjVD8gRCwV9z70MwHmBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:41.734174Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06457","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67b1645cdef1b9287c227389c6714dfbc4876e7284ec4f1f9d602c27f3aa64e0","sha256:ef6ff94d704da3b56acc71716914f21a37956bc3c212a156c47a6340200916b1"],"state_sha256":"ad7f9f680c8935df218fc7e261604ceacc1350265c895cbb7b7141bd4017446a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d8prR1jaOeA9cSgronf5nPTMDjZG6KFqJH1FVrKgFQ5MBDDyLKunD0cKQkcS6jCDgZaXAfzCxGE7k9387FKIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:45:22.914455Z","bundle_sha256":"60b498c1547b53972df0d1958a227cf15923241511876ae8a267a94f3ac73497"}}