{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BB6Q2GKEKMHGO63UZIEELJZ3DX","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":"5074b7a469d9bfece7f7ff9a54d82e262fb351b4e02e948ebe01c345b1c0062b","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T22:53:10Z","title_canon_sha256":"5846871c1c30cc8275aec4190d70907ebb7ee62687d8cd7517e80a5ceb673750"},"schema_version":"1.0","source":{"id":"2010.15979","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.15979","created_at":"2026-07-05T03:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2010.15979v2","created_at":"2026-07-05T03:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.15979","created_at":"2026-07-05T03:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"BB6Q2GKEKMHG","created_at":"2026-07-05T03:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"BB6Q2GKEKMHGO63U","created_at":"2026-07-05T03:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"BB6Q2GKE","created_at":"2026-07-05T03:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:5bd265bff5c08d23e5f360c3b42a35284b4f5a6b61779495a232127699fa6986","target":"graph","created_at":"2026-07-05T03:05:44Z","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/2010.15979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new computationally efficient method for quantizing the weights of pre- trained neural networks that is general enough to handle both multi-layer perceptrons and convolutional neural networks. Our method deterministically quantizes layers in an iterative fashion with no complicated re-training required. Specifically, we quantize each neuron, or hidden unit, using a greedy path-following algorithm. This simple algorithm is equivalent to running a dynamical system, which we prove is stable for quantizing a single-layer neural network (or, alternatively, for quantizing the first laye","authors_text":"Eric Lybrand, Rayan Saab","cross_cats":["cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T22:53:10Z","title":"A Greedy Algorithm for Quantizing Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.15979","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":"sha256:43eb90012f35f59070c2cba67c24a92b340b66625aa7bb3bb59c7f33216f147c","target":"record","created_at":"2026-07-05T03:05:44Z","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":"5074b7a469d9bfece7f7ff9a54d82e262fb351b4e02e948ebe01c345b1c0062b","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-29T22:53:10Z","title_canon_sha256":"5846871c1c30cc8275aec4190d70907ebb7ee62687d8cd7517e80a5ceb673750"},"schema_version":"1.0","source":{"id":"2010.15979","kind":"arxiv","version":2}},"canonical_sha256":"087d0d1944530e677b74ca0845a73b1dce37ad8b38d7b3bed78022820b566354","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"087d0d1944530e677b74ca0845a73b1dce37ad8b38d7b3bed78022820b566354","first_computed_at":"2026-07-05T03:05:44.862242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:44.862242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ao68eJUvLvESEYVdfImHTBHWcI5sZpPQ39Q0BYzH5vJ+mG7AC+G1pU1K1qNZ0MK90enVGSaO8R9WBn63kI02Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:44.862803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.15979","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43eb90012f35f59070c2cba67c24a92b340b66625aa7bb3bb59c7f33216f147c","sha256:5bd265bff5c08d23e5f360c3b42a35284b4f5a6b61779495a232127699fa6986"],"state_sha256":"2375a874447e96fbd59a01e93d4cff141a65e94f914925ae7b5ddae904e76549"}