{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:NGOKP2BRYKHNOZZNWUF6QJ4RI5","short_pith_number":"pith:NGOKP2BR","canonical_record":{"source":{"id":"1707.01209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-05T04:36:26Z","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"title_canon_sha256":"8b4bc6e865099c3700bd55623d5f146bf85c739494a6b87a778f4c39e221be10","abstract_canon_sha256":"3eb6ea2d6f101d372bd3b0cc5365fc2e9060d586ac44fde0f6b653002386c5a9"},"schema_version":"1.0"},"canonical_sha256":"699ca7e831c28ed7672db50be8279147658227a7edcbb9ea8aae14955a83fc78","source":{"kind":"arxiv","id":"1707.01209","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.01209","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"arxiv_version","alias_value":"1707.01209v1","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.01209","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"pith_short_12","alias_value":"NGOKP2BRYKHN","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"NGOKP2BRYKHNOZZN","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"NGOKP2BR","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:NGOKP2BRYKHNOZZNWUF6QJ4RI5","target":"record","payload":{"canonical_record":{"source":{"id":"1707.01209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-05T04:36:26Z","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"title_canon_sha256":"8b4bc6e865099c3700bd55623d5f146bf85c739494a6b87a778f4c39e221be10","abstract_canon_sha256":"3eb6ea2d6f101d372bd3b0cc5365fc2e9060d586ac44fde0f6b653002386c5a9"},"schema_version":"1.0"},"canonical_sha256":"699ca7e831c28ed7672db50be8279147658227a7edcbb9ea8aae14955a83fc78","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:53.422939Z","signature_b64":"2IcVJ8T4WdeeqKPoJeGXLpPfH5TBtQXAc4XsukyUIbU1mRTDaKgd00pGqty90f5gvjGCTudHXItKNN35Dn6FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"699ca7e831c28ed7672db50be8279147658227a7edcbb9ea8aae14955a83fc78","last_reissued_at":"2026-05-18T00:40:53.422332Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:53.422332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.01209","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":"2026-05-18T00:40:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eg2TJ3O99I2qJ1zohQ9j4420xF7nOgSYBvn3KNTs0XkFcQP3qeQYdxvmE8/nrp42b9CFYwveNCGlAf5oO8x3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T12:20:24.714415Z"},"content_sha256":"184f748b2f6939f724d152c25f7ba987fa1b371e7522c84fe825d0fe8c2fc2d6","schema_version":"1.0","event_id":"sha256:184f748b2f6939f724d152c25f7ba987fa1b371e7522c84fe825d0fe8c2fc2d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:NGOKP2BRYKHNOZZNWUF6QJ4RI5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model compression as constrained optimization, with application to neural nets. Part I: general framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Miguel \\'A. Carreira-Perpi\\~n\\'an","submitted_at":"2017-07-05T04:36:26Z","abstract_excerpt":"Compressing neural nets is an active research problem, given the large size of state-of-the-art nets for tasks such as object recognition, and the computational limits imposed by mobile devices. We give a general formulation of model compression as constrained optimization. This includes many types of compression: quantization, low-rank decomposition, pruning, lossless compression and others. Then, we give a general algorithm to optimize this nonconvex problem based on the augmented Lagrangian and alternating optimization. This results in a \"learning-compression\" algorithm, which alternates a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.01209","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":"2026-05-18T00:40:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FwmNI1A9YkNXhsi3BfHwU/KyjCgX/WK3+27FOVmlW4Bk8c5YQd9GEYhnnUL3P66nxr45I6fh0Qgxs9d2q9BZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T12:20:24.714761Z"},"content_sha256":"d7b8add7432618f17badd466c775ff1ff1e8900b1b33a6be91aa1b7aba1dc832","schema_version":"1.0","event_id":"sha256:d7b8add7432618f17badd466c775ff1ff1e8900b1b33a6be91aa1b7aba1dc832"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NGOKP2BRYKHNOZZNWUF6QJ4RI5/bundle.json","state_url":"https://pith.science/pith/NGOKP2BRYKHNOZZNWUF6QJ4RI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NGOKP2BRYKHNOZZNWUF6QJ4RI5/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":"2026-06-08T12:20:24Z","links":{"resolver":"https://pith.science/pith/NGOKP2BRYKHNOZZNWUF6QJ4RI5","bundle":"https://pith.science/pith/NGOKP2BRYKHNOZZNWUF6QJ4RI5/bundle.json","state":"https://pith.science/pith/NGOKP2BRYKHNOZZNWUF6QJ4RI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NGOKP2BRYKHNOZZNWUF6QJ4RI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:NGOKP2BRYKHNOZZNWUF6QJ4RI5","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":"3eb6ea2d6f101d372bd3b0cc5365fc2e9060d586ac44fde0f6b653002386c5a9","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-05T04:36:26Z","title_canon_sha256":"8b4bc6e865099c3700bd55623d5f146bf85c739494a6b87a778f4c39e221be10"},"schema_version":"1.0","source":{"id":"1707.01209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.01209","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"arxiv_version","alias_value":"1707.01209v1","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.01209","created_at":"2026-05-18T00:40:53Z"},{"alias_kind":"pith_short_12","alias_value":"NGOKP2BRYKHN","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"NGOKP2BRYKHNOZZN","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"NGOKP2BR","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:d7b8add7432618f17badd466c775ff1ff1e8900b1b33a6be91aa1b7aba1dc832","target":"graph","created_at":"2026-05-18T00:40:53Z","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":"Compressing neural nets is an active research problem, given the large size of state-of-the-art nets for tasks such as object recognition, and the computational limits imposed by mobile devices. We give a general formulation of model compression as constrained optimization. This includes many types of compression: quantization, low-rank decomposition, pruning, lossless compression and others. Then, we give a general algorithm to optimize this nonconvex problem based on the augmented Lagrangian and alternating optimization. This results in a \"learning-compression\" algorithm, which alternates a ","authors_text":"Miguel \\'A. Carreira-Perpi\\~n\\'an","cross_cats":["cs.NE","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-05T04:36:26Z","title":"Model compression as constrained optimization, with application to neural nets. Part I: general framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.01209","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":"sha256:184f748b2f6939f724d152c25f7ba987fa1b371e7522c84fe825d0fe8c2fc2d6","target":"record","created_at":"2026-05-18T00:40:53Z","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":"3eb6ea2d6f101d372bd3b0cc5365fc2e9060d586ac44fde0f6b653002386c5a9","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-05T04:36:26Z","title_canon_sha256":"8b4bc6e865099c3700bd55623d5f146bf85c739494a6b87a778f4c39e221be10"},"schema_version":"1.0","source":{"id":"1707.01209","kind":"arxiv","version":1}},"canonical_sha256":"699ca7e831c28ed7672db50be8279147658227a7edcbb9ea8aae14955a83fc78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"699ca7e831c28ed7672db50be8279147658227a7edcbb9ea8aae14955a83fc78","first_computed_at":"2026-05-18T00:40:53.422332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:53.422332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2IcVJ8T4WdeeqKPoJeGXLpPfH5TBtQXAc4XsukyUIbU1mRTDaKgd00pGqty90f5gvjGCTudHXItKNN35Dn6FAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:53.422939Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.01209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:184f748b2f6939f724d152c25f7ba987fa1b371e7522c84fe825d0fe8c2fc2d6","sha256:d7b8add7432618f17badd466c775ff1ff1e8900b1b33a6be91aa1b7aba1dc832"],"state_sha256":"193422c7be8fae21b8b7994dc47eecb423f40d101e015670dfce450516735cfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gtsgPuARzNRM6kEqgnmJNpyetzQho4Sb1D0QVkIvJZzfdfmAi5BVP15I4qPKLhTfEgZenkYFa1DrtX9tyyQxAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T12:20:24.716619Z","bundle_sha256":"26c63eac36ea55bdcaa3e1a9a1d740b6474f66286f17d44f2678fa2e5315299d"}}