{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LJTABIIYEICOS7Z4QKNMPTANL7","short_pith_number":"pith:LJTABIIY","canonical_record":{"source":{"id":"1806.03723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T20:58:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"089f59802718347706a86eb812014313f9307d839b21aa0e7d4662af2e5fed21","abstract_canon_sha256":"f836f5f7c507a0ef29594faa3436c48a2d2bc055c0ffb0c8851929fa596affb1"},"schema_version":"1.0"},"canonical_sha256":"5a6600a1182204e97f3c829ac7cc0d5feb4a8d27da4dab1c8caf3dd94ef1860b","source":{"kind":"arxiv","id":"1806.03723","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03723","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03723v1","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03723","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"LJTABIIYEICO","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LJTABIIYEICOS7Z4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LJTABIIY","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LJTABIIYEICOS7Z4QKNMPTANL7","target":"record","payload":{"canonical_record":{"source":{"id":"1806.03723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T20:58:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"089f59802718347706a86eb812014313f9307d839b21aa0e7d4662af2e5fed21","abstract_canon_sha256":"f836f5f7c507a0ef29594faa3436c48a2d2bc055c0ffb0c8851929fa596affb1"},"schema_version":"1.0"},"canonical_sha256":"5a6600a1182204e97f3c829ac7cc0d5feb4a8d27da4dab1c8caf3dd94ef1860b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:42.237784Z","signature_b64":"BBX398L/cr+4tE6BwoBbckvhlVjU1gWHFLbfNesQbtoOCEIG/RXY5+IW0Nx2lJ3s2hlMkN1pc7ramtEzjfidAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a6600a1182204e97f3c829ac7cc0d5feb4a8d27da4dab1c8caf3dd94ef1860b","last_reissued_at":"2026-05-18T00:13:42.237078Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:42.237078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.03723","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5HodSI8f3hGS0Mo7+fTqilqwDVdF3tBfYfz8EcxZy1BTyd9Gnhm41e4k08cLntL6yuJTNIDegD1GZBPQ821Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:18:10.991433Z"},"content_sha256":"bdfea30fa6d3c45833766559d5d43002ca501a417d94e531bedd237378b8b1c7","schema_version":"1.0","event_id":"sha256:bdfea30fa6d3c45833766559d5d43002ca501a417d94e531bedd237378b8b1c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LJTABIIYEICOS7Z4QKNMPTANL7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smallify: Learning Network Size while Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Guillaume Leclerc, Manasi Vartak, Raul Castro Fernandez, Samuel Madden, Tim Kraska","submitted_at":"2018-06-10T20:58:59Z","abstract_excerpt":"As neural networks become widely deployed in different applications and on different hardware, it has become increasingly important to optimize inference time and model size along with model accuracy. Most current techniques optimize model size, model accuracy and inference time in different stages, resulting in suboptimal results and computational inefficiency. In this work, we propose a new technique called Smallify that optimizes all three of these metrics at the same time. Specifically we present a new method to simultaneously optimize network size and model performance by neuron-level pru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03723","kind":"arxiv","version":1},"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":"2026-05-18T00:13:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fEHGOGaI96gMS1undU1NhecVVqtKR2c3lmnJGKEXStMQCJEdLSjqGNA6+WtZlWcybYkNpFEkFQ0LJLjCwU0KBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:18:10.991769Z"},"content_sha256":"ac08035f167d72181bac1cab563bcfce18f8e447d601f1c64fa6386a2d86c021","schema_version":"1.0","event_id":"sha256:ac08035f167d72181bac1cab563bcfce18f8e447d601f1c64fa6386a2d86c021"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJTABIIYEICOS7Z4QKNMPTANL7/bundle.json","state_url":"https://pith.science/pith/LJTABIIYEICOS7Z4QKNMPTANL7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJTABIIYEICOS7Z4QKNMPTANL7/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":"2026-06-03T18:18:10Z","links":{"resolver":"https://pith.science/pith/LJTABIIYEICOS7Z4QKNMPTANL7","bundle":"https://pith.science/pith/LJTABIIYEICOS7Z4QKNMPTANL7/bundle.json","state":"https://pith.science/pith/LJTABIIYEICOS7Z4QKNMPTANL7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJTABIIYEICOS7Z4QKNMPTANL7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LJTABIIYEICOS7Z4QKNMPTANL7","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":"f836f5f7c507a0ef29594faa3436c48a2d2bc055c0ffb0c8851929fa596affb1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T20:58:59Z","title_canon_sha256":"089f59802718347706a86eb812014313f9307d839b21aa0e7d4662af2e5fed21"},"schema_version":"1.0","source":{"id":"1806.03723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03723","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03723v1","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03723","created_at":"2026-05-18T00:13:42Z"},{"alias_kind":"pith_short_12","alias_value":"LJTABIIYEICO","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LJTABIIYEICOS7Z4","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LJTABIIY","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:ac08035f167d72181bac1cab563bcfce18f8e447d601f1c64fa6386a2d86c021","target":"graph","created_at":"2026-05-18T00:13:42Z","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":"As neural networks become widely deployed in different applications and on different hardware, it has become increasingly important to optimize inference time and model size along with model accuracy. Most current techniques optimize model size, model accuracy and inference time in different stages, resulting in suboptimal results and computational inefficiency. In this work, we propose a new technique called Smallify that optimizes all three of these metrics at the same time. Specifically we present a new method to simultaneously optimize network size and model performance by neuron-level pru","authors_text":"Guillaume Leclerc, Manasi Vartak, Raul Castro Fernandez, Samuel Madden, Tim Kraska","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T20:58:59Z","title":"Smallify: Learning Network Size while Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03723","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:bdfea30fa6d3c45833766559d5d43002ca501a417d94e531bedd237378b8b1c7","target":"record","created_at":"2026-05-18T00:13:42Z","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":"f836f5f7c507a0ef29594faa3436c48a2d2bc055c0ffb0c8851929fa596affb1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-10T20:58:59Z","title_canon_sha256":"089f59802718347706a86eb812014313f9307d839b21aa0e7d4662af2e5fed21"},"schema_version":"1.0","source":{"id":"1806.03723","kind":"arxiv","version":1}},"canonical_sha256":"5a6600a1182204e97f3c829ac7cc0d5feb4a8d27da4dab1c8caf3dd94ef1860b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a6600a1182204e97f3c829ac7cc0d5feb4a8d27da4dab1c8caf3dd94ef1860b","first_computed_at":"2026-05-18T00:13:42.237078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:42.237078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBX398L/cr+4tE6BwoBbckvhlVjU1gWHFLbfNesQbtoOCEIG/RXY5+IW0Nx2lJ3s2hlMkN1pc7ramtEzjfidAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:42.237784Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bdfea30fa6d3c45833766559d5d43002ca501a417d94e531bedd237378b8b1c7","sha256:ac08035f167d72181bac1cab563bcfce18f8e447d601f1c64fa6386a2d86c021"],"state_sha256":"bf80f2a6aa9074ebf692695c56ff267649e0e6483865214895bebe0780acf8d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Bzks64zGD8IUaPzw93yIRaKJ3a1zkOWAk1J8z3qJamA2AgU6diyOyQOTq21y5H3C28B+5X8RcR1FtDJEQ0vBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T18:18:10.993616Z","bundle_sha256":"c15f8ac38910827f8b96cfb5906d84c95f7431e4db95c5ecb33fb814a44163fb"}}