{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EQPWZLFYTEJPSCE75LFXI3C4PW","short_pith_number":"pith:EQPWZLFY","schema_version":"1.0","canonical_sha256":"241f6cacb89912f9089feacb746c5c7da5ffde49c0f3e67575209907c914f213","source":{"kind":"arxiv","id":"2504.13792","version":2},"attestation_state":"computed","paper":{"title":"Binary and Ternary Quantization Can Enhance Feature Discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mingrui Chen, Weiyu Li, Weizhi Lu","submitted_at":"2025-04-18T16:44:12Z","abstract_excerpt":"Quantization is widely applied in machine learning to reduce computational and storage costs for both data and models. Considering that classification tasks are fundamental to the field, it is crucial to investigate how quantization impacts classification performance. Traditional research has focused on quantization errors, assuming that larger errors generally lead to lower classification accuracy. However, this assumption lacks a solid theoretical foundation and often contradicts empirical observations. For example, despite introducing significant errors, $\\{0,1\\}$-binary and $\\{0, \\pm1\\}$-t"},"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":"2504.13792","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-18T16:44:12Z","cross_cats_sorted":[],"title_canon_sha256":"7fc4566b86254d11181072bdbcb3d4641af549143b38daa7af5cc04ce4225140","abstract_canon_sha256":"b11a7776471c2e7247f1f01bd7df383af990efa45d8f09de80bc5506b48f7318"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:34.654245Z","signature_b64":"QbECD32i2l2mLcuia50HiULSf+c//I+YVj4YGCQ1CGJuKTtjdtI/CY3T/0XYJLzPmBM8KHtO3w8QyrhaVy8pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"241f6cacb89912f9089feacb746c5c7da5ffde49c0f3e67575209907c914f213","last_reissued_at":"2026-07-05T11:35:34.653800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:34.653800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Binary and Ternary Quantization Can Enhance Feature Discrimination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mingrui Chen, Weiyu Li, Weizhi Lu","submitted_at":"2025-04-18T16:44:12Z","abstract_excerpt":"Quantization is widely applied in machine learning to reduce computational and storage costs for both data and models. Considering that classification tasks are fundamental to the field, it is crucial to investigate how quantization impacts classification performance. Traditional research has focused on quantization errors, assuming that larger errors generally lead to lower classification accuracy. However, this assumption lacks a solid theoretical foundation and often contradicts empirical observations. For example, despite introducing significant errors, $\\{0,1\\}$-binary and $\\{0, \\pm1\\}$-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13792","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/2504.13792/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":"2504.13792","created_at":"2026-07-05T11:35:34.653857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13792v2","created_at":"2026-07-05T11:35:34.653857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13792","created_at":"2026-07-05T11:35:34.653857+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQPWZLFYTEJP","created_at":"2026-07-05T11:35:34.653857+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQPWZLFYTEJPSCE7","created_at":"2026-07-05T11:35:34.653857+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQPWZLFY","created_at":"2026-07-05T11:35:34.653857+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/EQPWZLFYTEJPSCE75LFXI3C4PW","json":"https://pith.science/pith/EQPWZLFYTEJPSCE75LFXI3C4PW.json","graph_json":"https://pith.science/api/pith-number/EQPWZLFYTEJPSCE75LFXI3C4PW/graph.json","events_json":"https://pith.science/api/pith-number/EQPWZLFYTEJPSCE75LFXI3C4PW/events.json","paper":"https://pith.science/paper/EQPWZLFY"},"agent_actions":{"view_html":"https://pith.science/pith/EQPWZLFYTEJPSCE75LFXI3C4PW","download_json":"https://pith.science/pith/EQPWZLFYTEJPSCE75LFXI3C4PW.json","view_paper":"https://pith.science/paper/EQPWZLFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13792&json=true","fetch_graph":"https://pith.science/api/pith-number/EQPWZLFYTEJPSCE75LFXI3C4PW/graph.json","fetch_events":"https://pith.science/api/pith-number/EQPWZLFYTEJPSCE75LFXI3C4PW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQPWZLFYTEJPSCE75LFXI3C4PW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQPWZLFYTEJPSCE75LFXI3C4PW/action/storage_attestation","attest_author":"https://pith.science/pith/EQPWZLFYTEJPSCE75LFXI3C4PW/action/author_attestation","sign_citation":"https://pith.science/pith/EQPWZLFYTEJPSCE75LFXI3C4PW/action/citation_signature","submit_replication":"https://pith.science/pith/EQPWZLFYTEJPSCE75LFXI3C4PW/action/replication_record"}},"created_at":"2026-07-05T11:35:34.653857+00:00","updated_at":"2026-07-05T11:35:34.653857+00:00"}