{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KMWRMIX4PSB3AIB3VOFBNXYWJ3","short_pith_number":"pith:KMWRMIX4","schema_version":"1.0","canonical_sha256":"532d1622fc7c83b0203bab8a16df164ecd6ba0dd7d490a236b2c96f94e2b2f49","source":{"kind":"arxiv","id":"2304.14082","version":3},"attestation_state":"computed","paper":{"title":"JaxPruner: A concise library for sparsity research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Aart Bik, Amir Yazdanbakhsh, Elias Frantar, Gintare Karolina Dziugaite, Han-Byul Kim, Hong-Seok Kim, Johan Obando-Ceron, Jonathan Pilault, Joo Hyung Lee, Milen Ferev, Namhoon Lee, Nicole Mitchell, Pablo Samuel Castro, Sheng-Chun Kao, Shivani Agrawal, Suvinay Subramanian, Trevor Gale, Utku Evci, Wonpyo Park, Woohyun Han, Xingyao Zhang, Xin Wang, Yann Dauphin, Yun Long, Zhonglin Han","submitted_at":"2023-04-27T10:45:30Z","abstract_excerpt":"This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research. JaxPruner aims to accelerate research on sparse neural networks by providing concise implementations of popular pruning and sparse training algorithms with minimal memory and latency overhead. Algorithms implemented in JaxPruner use a common API and work seamlessly with the popular optimization library Optax, which, in turn, enables easy integration with existing JAX based libraries. We demonstrate this ease of integration by providing examples in four different codebase"},"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":"2304.14082","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T10:45:30Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"c85aaa72d6e9b33631f4c61b8f8e60f5cf96ad18a18806be729e4ad8b700fdf7","abstract_canon_sha256":"de73131e9cedfc224af154fc3cd04cf61b3ff2dc00e4c360384bc55f8cbd9cfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:41.189274Z","signature_b64":"12sAboGpkaAUa5LyhoaYd29vaKJ8/QLoLmRe0AHnXA+zBr/dYAbiAYzYHNaYixG4lNDUwU6lLviIOz2Qz+ldCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"532d1622fc7c83b0203bab8a16df164ecd6ba0dd7d490a236b2c96f94e2b2f49","last_reissued_at":"2026-07-05T07:25:41.188827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:41.188827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JaxPruner: A concise library for sparsity research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Aart Bik, Amir Yazdanbakhsh, Elias Frantar, Gintare Karolina Dziugaite, Han-Byul Kim, Hong-Seok Kim, Johan Obando-Ceron, Jonathan Pilault, Joo Hyung Lee, Milen Ferev, Namhoon Lee, Nicole Mitchell, Pablo Samuel Castro, Sheng-Chun Kao, Shivani Agrawal, Suvinay Subramanian, Trevor Gale, Utku Evci, Wonpyo Park, Woohyun Han, Xingyao Zhang, Xin Wang, Yann Dauphin, Yun Long, Zhonglin Han","submitted_at":"2023-04-27T10:45:30Z","abstract_excerpt":"This paper introduces JaxPruner, an open-source JAX-based pruning and sparse training library for machine learning research. JaxPruner aims to accelerate research on sparse neural networks by providing concise implementations of popular pruning and sparse training algorithms with minimal memory and latency overhead. Algorithms implemented in JaxPruner use a common API and work seamlessly with the popular optimization library Optax, which, in turn, enables easy integration with existing JAX based libraries. We demonstrate this ease of integration by providing examples in four different codebase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14082","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.14082/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":"2304.14082","created_at":"2026-07-05T07:25:41.188891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14082v3","created_at":"2026-07-05T07:25:41.188891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14082","created_at":"2026-07-05T07:25:41.188891+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMWRMIX4PSB3","created_at":"2026-07-05T07:25:41.188891+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMWRMIX4PSB3AIB3","created_at":"2026-07-05T07:25:41.188891+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMWRMIX4","created_at":"2026-07-05T07:25:41.188891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01330","citing_title":"Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3","json":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3.json","graph_json":"https://pith.science/api/pith-number/KMWRMIX4PSB3AIB3VOFBNXYWJ3/graph.json","events_json":"https://pith.science/api/pith-number/KMWRMIX4PSB3AIB3VOFBNXYWJ3/events.json","paper":"https://pith.science/paper/KMWRMIX4"},"agent_actions":{"view_html":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3","download_json":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3.json","view_paper":"https://pith.science/paper/KMWRMIX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14082&json=true","fetch_graph":"https://pith.science/api/pith-number/KMWRMIX4PSB3AIB3VOFBNXYWJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/KMWRMIX4PSB3AIB3VOFBNXYWJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3/action/storage_attestation","attest_author":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3/action/author_attestation","sign_citation":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3/action/citation_signature","submit_replication":"https://pith.science/pith/KMWRMIX4PSB3AIB3VOFBNXYWJ3/action/replication_record"}},"created_at":"2026-07-05T07:25:41.188891+00:00","updated_at":"2026-07-05T07:25:41.188891+00:00"}