{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NLJ6XGWJORH3WL2G724KBAHTGW","short_pith_number":"pith:NLJ6XGWJ","canonical_record":{"source":{"id":"1804.03294","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-10T01:14:51Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c561125de6d32e55a1e61f175cabc54187f2b82a8a392765f84a2d437c55d62f","abstract_canon_sha256":"42318f02b61a81e6e66feca41c46cabd5fcd8c772332c25f8debcb91eb576746"},"schema_version":"1.0"},"canonical_sha256":"6ad3eb9ac9744fbb2f46feb8a080f335a9a586d769ee7a2efd620447acd12100","source":{"kind":"arxiv","id":"1804.03294","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03294","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03294v3","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03294","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"NLJ6XGWJORH3","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NLJ6XGWJORH3WL2G","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NLJ6XGWJ","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NLJ6XGWJORH3WL2G724KBAHTGW","target":"record","payload":{"canonical_record":{"source":{"id":"1804.03294","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-10T01:14:51Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c561125de6d32e55a1e61f175cabc54187f2b82a8a392765f84a2d437c55d62f","abstract_canon_sha256":"42318f02b61a81e6e66feca41c46cabd5fcd8c772332c25f8debcb91eb576746"},"schema_version":"1.0"},"canonical_sha256":"6ad3eb9ac9744fbb2f46feb8a080f335a9a586d769ee7a2efd620447acd12100","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:45.053305Z","signature_b64":"xcjVZglGD7qFl3yc1/t2jkD74dxMV5yZBBGzS+l40KOxJNGhN/9piW34SVBw1EUnAEEA2I6aM6iSwjnlFw6pBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ad3eb9ac9744fbb2f46feb8a080f335a9a586d769ee7a2efd620447acd12100","last_reissued_at":"2026-05-18T00:02:45.052905Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:45.052905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.03294","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F9+FoHVXoD2jE/kZHSLGir66DFgZ+0bxOhNV1Zj2uRM80B4IOhQHFMn8nlH3xG2afhEBsnU4HV0h9+FA7gVZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:30:10.674409Z"},"content_sha256":"38fa4d0fb9240b36206f81f51e79057527d0cdb7b01b23e1d03ef31630ed41b4","schema_version":"1.0","event_id":"sha256:38fa4d0fb9240b36206f81f51e79057527d0cdb7b01b23e1d03ef31630ed41b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NLJ6XGWJORH3WL2G724KBAHTGW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Jian Tang, Kaiqi Zhang, Makan Fardad, Shaokai Ye, Tianyun Zhang, Wujie Wen, Yanzhi Wang","submitted_at":"2018-04-10T01:14:51Z","abstract_excerpt":"Weight pruning methods for deep neural networks (DNNs) have been investigated recently, but prior work in this area is mainly heuristic, iterative pruning, thereby lacking guarantees on the weight reduction ratio and convergence time. To mitigate these limitations, we present a systematic weight pruning framework of DNNs using the alternating direction method of multipliers (ADMM). We first formulate the weight pruning problem of DNNs as a nonconvex optimization problem with combinatorial constraints specifying the sparsity requirements, and then adopt the ADMM framework for systematic weight "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03294","kind":"arxiv","version":3},"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":"2026-05-18T00:02:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GqImB5L+KoQFj+QeZbO0KAmPCGJEL58L6AoCHUtdppt88eH548OJ7jgNzcJnkb9Wr/E1X5qhcHAV7+SHslsjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:30:10.675134Z"},"content_sha256":"b95ee8ccc7605d896731c29aa12d3c6a5fe77cc85ce1a5f91cce84b49cb05a74","schema_version":"1.0","event_id":"sha256:b95ee8ccc7605d896731c29aa12d3c6a5fe77cc85ce1a5f91cce84b49cb05a74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLJ6XGWJORH3WL2G724KBAHTGW/bundle.json","state_url":"https://pith.science/pith/NLJ6XGWJORH3WL2G724KBAHTGW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLJ6XGWJORH3WL2G724KBAHTGW/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":"2026-05-27T18:30:10Z","links":{"resolver":"https://pith.science/pith/NLJ6XGWJORH3WL2G724KBAHTGW","bundle":"https://pith.science/pith/NLJ6XGWJORH3WL2G724KBAHTGW/bundle.json","state":"https://pith.science/pith/NLJ6XGWJORH3WL2G724KBAHTGW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLJ6XGWJORH3WL2G724KBAHTGW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NLJ6XGWJORH3WL2G724KBAHTGW","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":"42318f02b61a81e6e66feca41c46cabd5fcd8c772332c25f8debcb91eb576746","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-10T01:14:51Z","title_canon_sha256":"c561125de6d32e55a1e61f175cabc54187f2b82a8a392765f84a2d437c55d62f"},"schema_version":"1.0","source":{"id":"1804.03294","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03294","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03294v3","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03294","created_at":"2026-05-18T00:02:45Z"},{"alias_kind":"pith_short_12","alias_value":"NLJ6XGWJORH3","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NLJ6XGWJORH3WL2G","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NLJ6XGWJ","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:b95ee8ccc7605d896731c29aa12d3c6a5fe77cc85ce1a5f91cce84b49cb05a74","target":"graph","created_at":"2026-05-18T00:02:45Z","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":"Weight pruning methods for deep neural networks (DNNs) have been investigated recently, but prior work in this area is mainly heuristic, iterative pruning, thereby lacking guarantees on the weight reduction ratio and convergence time. To mitigate these limitations, we present a systematic weight pruning framework of DNNs using the alternating direction method of multipliers (ADMM). We first formulate the weight pruning problem of DNNs as a nonconvex optimization problem with combinatorial constraints specifying the sparsity requirements, and then adopt the ADMM framework for systematic weight ","authors_text":"Jian Tang, Kaiqi Zhang, Makan Fardad, Shaokai Ye, Tianyun Zhang, Wujie Wen, Yanzhi Wang","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-10T01:14:51Z","title":"A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03294","kind":"arxiv","version":3},"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":"sha256:38fa4d0fb9240b36206f81f51e79057527d0cdb7b01b23e1d03ef31630ed41b4","target":"record","created_at":"2026-05-18T00:02:45Z","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":"42318f02b61a81e6e66feca41c46cabd5fcd8c772332c25f8debcb91eb576746","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-04-10T01:14:51Z","title_canon_sha256":"c561125de6d32e55a1e61f175cabc54187f2b82a8a392765f84a2d437c55d62f"},"schema_version":"1.0","source":{"id":"1804.03294","kind":"arxiv","version":3}},"canonical_sha256":"6ad3eb9ac9744fbb2f46feb8a080f335a9a586d769ee7a2efd620447acd12100","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ad3eb9ac9744fbb2f46feb8a080f335a9a586d769ee7a2efd620447acd12100","first_computed_at":"2026-05-18T00:02:45.052905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:45.052905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xcjVZglGD7qFl3yc1/t2jkD74dxMV5yZBBGzS+l40KOxJNGhN/9piW34SVBw1EUnAEEA2I6aM6iSwjnlFw6pBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:45.053305Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.03294","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38fa4d0fb9240b36206f81f51e79057527d0cdb7b01b23e1d03ef31630ed41b4","sha256:b95ee8ccc7605d896731c29aa12d3c6a5fe77cc85ce1a5f91cce84b49cb05a74"],"state_sha256":"4bf2fc67b5fc8d19314b1bd27b75143a3073f2ab7621bb252fbd1af2975495c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"owIbK3EaqY48SXBrJ/RdWveosTES8VarfKnYSlY62YxlMcvG/dILpuzNh4KI1BZxQoDi4SlZ4DqhufoQfN8ICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T18:30:10.678590Z","bundle_sha256":"2cd3016714c5b2ec811ab12d15ddbf61cd6fcf2cb5225a480737084d14d48e90"}}