{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SSSJ2GYDR54K7APVHTENCTDNQ2","short_pith_number":"pith:SSSJ2GYD","schema_version":"1.0","canonical_sha256":"94a49d1b038f78af81f53cc8d14c6d8683c71b55a1aa72037850fd462cdf9845","source":{"kind":"arxiv","id":"2411.13918","version":4},"attestation_state":"computed","paper":{"title":"Quantization without Tears","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Yu, Jianxin Wu, Jie Shao, Junjie Zhou, Ke Zhu, Minghao Fu","submitted_at":"2024-11-21T08:13:24Z","abstract_excerpt":"Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration technique, reduces storage costs and enables potential inference acceleration by discretizing network weights and activations into a finite set of integer values. However, current quantization methods are often complex and sensitive, requiring extensive task-specific hyperparameters, where even a single misconfiguration can impair model performance, limitin"},"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":"2411.13918","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T08:13:24Z","cross_cats_sorted":[],"title_canon_sha256":"766cf91f85599d2454d70f56ef18323f56b1507289a278c70b1611e46c6a601e","abstract_canon_sha256":"b51d29a129cffa6b9450089720afec3fec0d2c9ea84d3fe646e77d9b10afeea7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:17.621223Z","signature_b64":"kCmH1tfKxwT5k1/Hg2RysiCnoBHT9Ee4gEKd4gkS4XH4fcZSS46l4Ao2QUaa1H2h7YdfSQ+V5AEODODWYHizDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94a49d1b038f78af81f53cc8d14c6d8683c71b55a1aa72037850fd462cdf9845","last_reissued_at":"2026-07-05T11:33:17.620814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:17.620814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantization without Tears","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Yu, Jianxin Wu, Jie Shao, Junjie Zhou, Ke Zhu, Minghao Fu","submitted_at":"2024-11-21T08:13:24Z","abstract_excerpt":"Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration technique, reduces storage costs and enables potential inference acceleration by discretizing network weights and activations into a finite set of integer values. However, current quantization methods are often complex and sensitive, requiring extensive task-specific hyperparameters, where even a single misconfiguration can impair model performance, limitin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13918","kind":"arxiv","version":4},"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/2411.13918/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":"2411.13918","created_at":"2026-07-05T11:33:17.620870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13918v4","created_at":"2026-07-05T11:33:17.620870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13918","created_at":"2026-07-05T11:33:17.620870+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSSJ2GYDR54K","created_at":"2026-07-05T11:33:17.620870+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSSJ2GYDR54K7APV","created_at":"2026-07-05T11:33:17.620870+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSSJ2GYD","created_at":"2026-07-05T11:33:17.620870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11784","citing_title":"GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2","json":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2.json","graph_json":"https://pith.science/api/pith-number/SSSJ2GYDR54K7APVHTENCTDNQ2/graph.json","events_json":"https://pith.science/api/pith-number/SSSJ2GYDR54K7APVHTENCTDNQ2/events.json","paper":"https://pith.science/paper/SSSJ2GYD"},"agent_actions":{"view_html":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2","download_json":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2.json","view_paper":"https://pith.science/paper/SSSJ2GYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13918&json=true","fetch_graph":"https://pith.science/api/pith-number/SSSJ2GYDR54K7APVHTENCTDNQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/SSSJ2GYDR54K7APVHTENCTDNQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2/action/storage_attestation","attest_author":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2/action/author_attestation","sign_citation":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2/action/citation_signature","submit_replication":"https://pith.science/pith/SSSJ2GYDR54K7APVHTENCTDNQ2/action/replication_record"}},"created_at":"2026-07-05T11:33:17.620870+00:00","updated_at":"2026-07-05T11:33:17.620870+00:00"}