{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V4TGICZYP2VNZRZHOEAPJ6K3RU","short_pith_number":"pith:V4TGICZY","schema_version":"1.0","canonical_sha256":"af26640b387eaadcc7277100f4f95b8d3f9bd7c7ab097ccee19424109de26844","source":{"kind":"arxiv","id":"1905.11478","version":1},"attestation_state":"computed","paper":{"title":"Learning In Practice: Reasoning About Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Annie Cherkaev, Jeff Phillips, Vivek Srikumar, Waiming Tai","submitted_at":"2019-05-27T19:59:14Z","abstract_excerpt":"There is a mismatch between the standard theoretical analyses of statistical machine learning and how learning is used in practice. The foundational assumption supporting the theory is that we can represent features and models using real-valued parameters. In practice, however, we do not use real numbers at any point during training or deployment. Instead, we rely on discrete and finite quantizations of the reals, typically floating points. In this paper, we propose a framework for reasoning about learning under arbitrary quantizations. Using this formalization, we prove the convergence of qua"},"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":"1905.11478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T19:59:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e28635ba9bd6cf99abc8d90d80148c910e8140e0450a2ef6ade8e5f16e2e228b","abstract_canon_sha256":"2c3ddae2809ba2d03a48937241bda030ce1aa3f74d76c36a26c94770eb6fe8e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:53.309588Z","signature_b64":"K8yMul7kWhFpPJ2ZzfDX63mJ+qMQrHA/ryjBMbcguHu5SXN4FwLN6IKIioDeE9uVrMl5oNOsi8jBJXLGTpDxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af26640b387eaadcc7277100f4f95b8d3f9bd7c7ab097ccee19424109de26844","last_reissued_at":"2026-05-17T23:44:53.308805Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:53.308805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning In Practice: Reasoning About Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Annie Cherkaev, Jeff Phillips, Vivek Srikumar, Waiming Tai","submitted_at":"2019-05-27T19:59:14Z","abstract_excerpt":"There is a mismatch between the standard theoretical analyses of statistical machine learning and how learning is used in practice. The foundational assumption supporting the theory is that we can represent features and models using real-valued parameters. In practice, however, we do not use real numbers at any point during training or deployment. Instead, we rely on discrete and finite quantizations of the reals, typically floating points. In this paper, we propose a framework for reasoning about learning under arbitrary quantizations. Using this formalization, we prove the convergence of qua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11478","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":""},"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":"1905.11478","created_at":"2026-05-17T23:44:53.308936+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11478v1","created_at":"2026-05-17T23:44:53.308936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11478","created_at":"2026-05-17T23:44:53.308936+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4TGICZYP2VN","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4TGICZYP2VNZRZH","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4TGICZY","created_at":"2026-05-18T12:33:30.264802+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/V4TGICZYP2VNZRZHOEAPJ6K3RU","json":"https://pith.science/pith/V4TGICZYP2VNZRZHOEAPJ6K3RU.json","graph_json":"https://pith.science/api/pith-number/V4TGICZYP2VNZRZHOEAPJ6K3RU/graph.json","events_json":"https://pith.science/api/pith-number/V4TGICZYP2VNZRZHOEAPJ6K3RU/events.json","paper":"https://pith.science/paper/V4TGICZY"},"agent_actions":{"view_html":"https://pith.science/pith/V4TGICZYP2VNZRZHOEAPJ6K3RU","download_json":"https://pith.science/pith/V4TGICZYP2VNZRZHOEAPJ6K3RU.json","view_paper":"https://pith.science/paper/V4TGICZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11478&json=true","fetch_graph":"https://pith.science/api/pith-number/V4TGICZYP2VNZRZHOEAPJ6K3RU/graph.json","fetch_events":"https://pith.science/api/pith-number/V4TGICZYP2VNZRZHOEAPJ6K3RU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4TGICZYP2VNZRZHOEAPJ6K3RU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4TGICZYP2VNZRZHOEAPJ6K3RU/action/storage_attestation","attest_author":"https://pith.science/pith/V4TGICZYP2VNZRZHOEAPJ6K3RU/action/author_attestation","sign_citation":"https://pith.science/pith/V4TGICZYP2VNZRZHOEAPJ6K3RU/action/citation_signature","submit_replication":"https://pith.science/pith/V4TGICZYP2VNZRZHOEAPJ6K3RU/action/replication_record"}},"created_at":"2026-05-17T23:44:53.308936+00:00","updated_at":"2026-05-17T23:44:53.308936+00:00"}