{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:P4OP2HGTIZ4QKN6B2DA3PQKZQH","short_pith_number":"pith:P4OP2HGT","canonical_record":{"source":{"id":"1806.05355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T03:59:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"885bc6d58f91c928b936fae4dce8db17d2f5d8c9cdd0319b8e861b3efc6aacdc","abstract_canon_sha256":"f1acf250f82796e7fcd0db4b148012101d0bc01bed6b891db7cf59e799fba48f"},"schema_version":"1.0"},"canonical_sha256":"7f1cfd1cd346790537c1d0c1b7c15981d962948c92cc962ba3d8cb0b945e12dd","source":{"kind":"arxiv","id":"1806.05355","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05355","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05355v1","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05355","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"P4OP2HGTIZ4Q","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"P4OP2HGTIZ4QKN6B","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"P4OP2HGT","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:P4OP2HGTIZ4QKN6B2DA3PQKZQH","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05355","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T03:59:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"885bc6d58f91c928b936fae4dce8db17d2f5d8c9cdd0319b8e861b3efc6aacdc","abstract_canon_sha256":"f1acf250f82796e7fcd0db4b148012101d0bc01bed6b891db7cf59e799fba48f"},"schema_version":"1.0"},"canonical_sha256":"7f1cfd1cd346790537c1d0c1b7c15981d962948c92cc962ba3d8cb0b945e12dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:16.248914Z","signature_b64":"LQhJk1JMXJtKtOo3sVmTkddB8xhQc3jJuayfx1siTyOwN6dNVveeT2zadIa+RT2X6EbkkvnbvryLkVUyNMl8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f1cfd1cd346790537c1d0c1b7c15981d962948c92cc962ba3d8cb0b945e12dd","last_reissued_at":"2026-05-18T00:13:16.248255Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:16.248255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05355","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":"2026-05-18T00:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KCEGvhLi0Fqtbm08ZRSAjQt122GiI9fJo5tZyRhVRXtvjF6IF69tNEBNeVOZM3WSD0pL16bCGlMvHcas5GWfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:15:20.903902Z"},"content_sha256":"af3b96c761766977a4560a8a23ddcc16d72fa02ad409330ba45cf6fbbf47aed8","schema_version":"1.0","event_id":"sha256:af3b96c761766977a4560a8a23ddcc16d72fa02ad409330ba45cf6fbbf47aed8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:P4OP2HGTIZ4QKN6B2DA3PQKZQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Neural Network Compression and Pruning Using Hard Clustering and L1 Regularization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Nicholas Ruozzi, Vibhav Gogate, Yibo Yang","submitted_at":"2018-06-14T03:59:37Z","abstract_excerpt":"We propose a simple and easy to implement neural network compression algorithm that achieves results competitive with more complicated state-of-the-art methods. The key idea is to modify the original optimization problem by adding K independent Gaussian priors (corresponding to the k-means objective) over the network parameters to achieve parameter quantization, as well as an L1 penalty to achieve pruning. Unlike many existing quantization-based methods, our method uses hard clustering assignments of network parameters, which adds minimal change or overhead to standard network training. We als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05355","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":"2026-05-18T00:13:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mhnis5/eJUrA4Z1vFuUHen+uFSLPMOEzSn6KT99ieiofWhD3fgu87NUz1umWFAaffOKbGeqQvKEur/LdKiNsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:15:20.904248Z"},"content_sha256":"b909cd5e330b766a2b972a0e4b63e33481c0ab29c9d145da9f4fa254a56520a8","schema_version":"1.0","event_id":"sha256:b909cd5e330b766a2b972a0e4b63e33481c0ab29c9d145da9f4fa254a56520a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4OP2HGTIZ4QKN6B2DA3PQKZQH/bundle.json","state_url":"https://pith.science/pith/P4OP2HGTIZ4QKN6B2DA3PQKZQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4OP2HGTIZ4QKN6B2DA3PQKZQH/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":"2026-06-02T23:15:20Z","links":{"resolver":"https://pith.science/pith/P4OP2HGTIZ4QKN6B2DA3PQKZQH","bundle":"https://pith.science/pith/P4OP2HGTIZ4QKN6B2DA3PQKZQH/bundle.json","state":"https://pith.science/pith/P4OP2HGTIZ4QKN6B2DA3PQKZQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4OP2HGTIZ4QKN6B2DA3PQKZQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:P4OP2HGTIZ4QKN6B2DA3PQKZQH","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":"f1acf250f82796e7fcd0db4b148012101d0bc01bed6b891db7cf59e799fba48f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T03:59:37Z","title_canon_sha256":"885bc6d58f91c928b936fae4dce8db17d2f5d8c9cdd0319b8e861b3efc6aacdc"},"schema_version":"1.0","source":{"id":"1806.05355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05355","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05355v1","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05355","created_at":"2026-05-18T00:13:16Z"},{"alias_kind":"pith_short_12","alias_value":"P4OP2HGTIZ4Q","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"P4OP2HGTIZ4QKN6B","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"P4OP2HGT","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:b909cd5e330b766a2b972a0e4b63e33481c0ab29c9d145da9f4fa254a56520a8","target":"graph","created_at":"2026-05-18T00:13:16Z","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 propose a simple and easy to implement neural network compression algorithm that achieves results competitive with more complicated state-of-the-art methods. The key idea is to modify the original optimization problem by adding K independent Gaussian priors (corresponding to the k-means objective) over the network parameters to achieve parameter quantization, as well as an L1 penalty to achieve pruning. Unlike many existing quantization-based methods, our method uses hard clustering assignments of network parameters, which adds minimal change or overhead to standard network training. We als","authors_text":"Nicholas Ruozzi, Vibhav Gogate, Yibo Yang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T03:59:37Z","title":"Scalable Neural Network Compression and Pruning Using Hard Clustering and L1 Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05355","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:af3b96c761766977a4560a8a23ddcc16d72fa02ad409330ba45cf6fbbf47aed8","target":"record","created_at":"2026-05-18T00:13:16Z","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":"f1acf250f82796e7fcd0db4b148012101d0bc01bed6b891db7cf59e799fba48f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2018-06-14T03:59:37Z","title_canon_sha256":"885bc6d58f91c928b936fae4dce8db17d2f5d8c9cdd0319b8e861b3efc6aacdc"},"schema_version":"1.0","source":{"id":"1806.05355","kind":"arxiv","version":1}},"canonical_sha256":"7f1cfd1cd346790537c1d0c1b7c15981d962948c92cc962ba3d8cb0b945e12dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f1cfd1cd346790537c1d0c1b7c15981d962948c92cc962ba3d8cb0b945e12dd","first_computed_at":"2026-05-18T00:13:16.248255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:16.248255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LQhJk1JMXJtKtOo3sVmTkddB8xhQc3jJuayfx1siTyOwN6dNVveeT2zadIa+RT2X6EbkkvnbvryLkVUyNMl8Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:16.248914Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af3b96c761766977a4560a8a23ddcc16d72fa02ad409330ba45cf6fbbf47aed8","sha256:b909cd5e330b766a2b972a0e4b63e33481c0ab29c9d145da9f4fa254a56520a8"],"state_sha256":"522d5ccde468ff1be6a241759a54df1d3a423de4bca76b120a2b206a2e3ac33f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ntMu4XuYjs8VE1Qh4IBzQ/gt9K+1BTA3IyJQNbs+pN2cZfk7oXeJgWMYx95jRYgyCWBd/ukEjGQ1XCEy4jJBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:15:20.906194Z","bundle_sha256":"572bbd15084a43a85937bc9cf1250bb24aac729ba2cb47fff44982a6f8967490"}}