{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E36FLXMMR4MT7HQCUH5VVAT6ZW","short_pith_number":"pith:E36FLXMM","schema_version":"1.0","canonical_sha256":"26fc55dd8c8f193f9e02a1fb5a827ecdaecc8a5827fa922cf4b85549271e311a","source":{"kind":"arxiv","id":"2307.02973","version":2},"attestation_state":"computed","paper":{"title":"Pruning vs Quantization: Which is Better?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Kuzmin, Arash Behboodi, Markus Nagel, Mart van Baalen, Tijmen Blankevoort","submitted_at":"2023-07-06T13:18:44Z","abstract_excerpt":"Neural network pruning and quantization techniques are almost as old as neural networks themselves. However, to date only ad-hoc comparisons between the two have been published. In this paper, we set out to answer the question on which is better: neural network quantization or pruning? By answering this question, we hope to inform design decisions made on neural network hardware going forward. We provide an extensive comparison between the two techniques for compressing deep neural networks. First, we give an analytical comparison of expected quantization and pruning error for general data dis"},"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":"2307.02973","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-06T13:18:44Z","cross_cats_sorted":[],"title_canon_sha256":"e7a96688108dbe3c3c9490a4d75991aa7b2f2d8e48684fb74fd6abd8dc70d219","abstract_canon_sha256":"f8409401a54580a7590d816839b7d6db21d4ff2732501e207d94ed2f7d2ab6f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:47.316815Z","signature_b64":"ZwMFPFuyiDJMUqRsRVhFFhgP4KqlAQT91uv7tBhOD15wm3eqc06sXQ9upsryIhnprQnMbvzKkrDrEkK7U/sNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26fc55dd8c8f193f9e02a1fb5a827ecdaecc8a5827fa922cf4b85549271e311a","last_reissued_at":"2026-07-05T07:45:47.316071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:47.316071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pruning vs Quantization: Which is Better?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrey Kuzmin, Arash Behboodi, Markus Nagel, Mart van Baalen, Tijmen Blankevoort","submitted_at":"2023-07-06T13:18:44Z","abstract_excerpt":"Neural network pruning and quantization techniques are almost as old as neural networks themselves. However, to date only ad-hoc comparisons between the two have been published. In this paper, we set out to answer the question on which is better: neural network quantization or pruning? By answering this question, we hope to inform design decisions made on neural network hardware going forward. We provide an extensive comparison between the two techniques for compressing deep neural networks. First, we give an analytical comparison of expected quantization and pruning error for general data dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02973","kind":"arxiv","version":2},"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/2307.02973/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":"2307.02973","created_at":"2026-07-05T07:45:47.316154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02973v2","created_at":"2026-07-05T07:45:47.316154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02973","created_at":"2026-07-05T07:45:47.316154+00:00"},{"alias_kind":"pith_short_12","alias_value":"E36FLXMMR4MT","created_at":"2026-07-05T07:45:47.316154+00:00"},{"alias_kind":"pith_short_16","alias_value":"E36FLXMMR4MT7HQC","created_at":"2026-07-05T07:45:47.316154+00:00"},{"alias_kind":"pith_short_8","alias_value":"E36FLXMM","created_at":"2026-07-05T07:45:47.316154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07046","citing_title":"Voltron: Enabling Elastic Multi-Device Execution of LLM Inference for Empowered Edge Intelligence","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW","json":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW.json","graph_json":"https://pith.science/api/pith-number/E36FLXMMR4MT7HQCUH5VVAT6ZW/graph.json","events_json":"https://pith.science/api/pith-number/E36FLXMMR4MT7HQCUH5VVAT6ZW/events.json","paper":"https://pith.science/paper/E36FLXMM"},"agent_actions":{"view_html":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW","download_json":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW.json","view_paper":"https://pith.science/paper/E36FLXMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02973&json=true","fetch_graph":"https://pith.science/api/pith-number/E36FLXMMR4MT7HQCUH5VVAT6ZW/graph.json","fetch_events":"https://pith.science/api/pith-number/E36FLXMMR4MT7HQCUH5VVAT6ZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW/action/storage_attestation","attest_author":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW/action/author_attestation","sign_citation":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW/action/citation_signature","submit_replication":"https://pith.science/pith/E36FLXMMR4MT7HQCUH5VVAT6ZW/action/replication_record"}},"created_at":"2026-07-05T07:45:47.316154+00:00","updated_at":"2026-07-05T07:45:47.316154+00:00"}