{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:55PYPEXRS6KNBF2W7C47O7CFFH","short_pith_number":"pith:55PYPEXR","schema_version":"1.0","canonical_sha256":"ef5f8792f19794d09756f8b9f77c4529c670fc75c220657668beb23e04120868","source":{"kind":"arxiv","id":"2004.05531","version":1},"attestation_state":"computed","paper":{"title":"A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Caiwen Ding, Fei Sun, Makan Fardad, Minghai Qin, Shanglin Zhou, Tianyun Zhang, Xiaolong Ma, Yanzhi Wang, Yen-Kuang Chen, Zheng Zhan","submitted_at":"2020-04-12T02:59:06Z","abstract_excerpt":"To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based pruning and dynamic regularization-based pruning. However, the former method currently suffers either complex workloads or accuracy degradation, while the latter one takes a long time to tune the parameters to achieve the desired pruning rate without accuracy loss. In this paper, we propose a unified DNN weight pruning framework with dynamically updated regularization terms bo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2004.05531","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-12T02:59:06Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"ca2f6891ee3a98326ab2f407061c5437365b50b3ee22e504a188ff12cc15a6cf","abstract_canon_sha256":"e9ed99011d59234697db9e07f70f769454cdc1b500248c5c1a1b5d197a583733"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:38.135570Z","signature_b64":"OtV2mBzhcrstNBo6rcdxWncY7ZhWPAwdw5Swc850ETpsir+yCeP841deo/owAhylIUENIU32DI1jbypbIM34AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef5f8792f19794d09756f8b9f77c4529c670fc75c220657668beb23e04120868","last_reissued_at":"2026-07-05T00:54:38.135139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:38.135139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Caiwen Ding, Fei Sun, Makan Fardad, Minghai Qin, Shanglin Zhou, Tianyun Zhang, Xiaolong Ma, Yanzhi Wang, Yen-Kuang Chen, Zheng Zhan","submitted_at":"2020-04-12T02:59:06Z","abstract_excerpt":"To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based pruning and dynamic regularization-based pruning. However, the former method currently suffers either complex workloads or accuracy degradation, while the latter one takes a long time to tune the parameters to achieve the desired pruning rate without accuracy loss. In this paper, we propose a unified DNN weight pruning framework with dynamically updated regularization terms bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05531","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.05531/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.05531","created_at":"2026-07-05T00:54:38.135194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05531v1","created_at":"2026-07-05T00:54:38.135194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05531","created_at":"2026-07-05T00:54:38.135194+00:00"},{"alias_kind":"pith_short_12","alias_value":"55PYPEXRS6KN","created_at":"2026-07-05T00:54:38.135194+00:00"},{"alias_kind":"pith_short_16","alias_value":"55PYPEXRS6KNBF2W","created_at":"2026-07-05T00:54:38.135194+00:00"},{"alias_kind":"pith_short_8","alias_value":"55PYPEXR","created_at":"2026-07-05T00:54:38.135194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH","json":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH.json","graph_json":"https://pith.science/api/pith-number/55PYPEXRS6KNBF2W7C47O7CFFH/graph.json","events_json":"https://pith.science/api/pith-number/55PYPEXRS6KNBF2W7C47O7CFFH/events.json","paper":"https://pith.science/paper/55PYPEXR"},"agent_actions":{"view_html":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH","download_json":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH.json","view_paper":"https://pith.science/paper/55PYPEXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05531&json=true","fetch_graph":"https://pith.science/api/pith-number/55PYPEXRS6KNBF2W7C47O7CFFH/graph.json","fetch_events":"https://pith.science/api/pith-number/55PYPEXRS6KNBF2W7C47O7CFFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH/action/storage_attestation","attest_author":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH/action/author_attestation","sign_citation":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH/action/citation_signature","submit_replication":"https://pith.science/pith/55PYPEXRS6KNBF2W7C47O7CFFH/action/replication_record"}},"created_at":"2026-07-05T00:54:38.135194+00:00","updated_at":"2026-07-05T00:54:38.135194+00:00"}