{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KRTNQISFWAAUWMU2TTEIEIK4HE","short_pith_number":"pith:KRTNQISF","schema_version":"1.0","canonical_sha256":"5466d82245b0014b329a9cc882215c39213de39e0c17b35a920c5cf90f56c975","source":{"kind":"arxiv","id":"2509.03850","version":1},"attestation_state":"computed","paper":{"title":"Data-Augmented Quantization-Aware Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Justin Kur, Kaiqi Zhao","submitted_at":"2025-09-04T03:24:35Z","abstract_excerpt":"Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. Existing KD and QAT works focus on improving the accuracy of quantized models from the network output perspective by designing better KD loss functions or optimizing QAT's forward and backward propagation. However, limited attention has been given to understanding the impact of input transformations, such as data augmentation (DA). The relationship between quantization-aware KD and DA remains unexplored. In this paper, we address the questi"},"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":"2509.03850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-04T03:24:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"183c3f5fb814cf3fd48549da537549f12f1d169ab4df56bbdead5c6256e3d604","abstract_canon_sha256":"4883c258c16c9a5d2b177bbe836522643a4c423d3029aff029bd879a6f72f660"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:47.892421Z","signature_b64":"Nq8sEv6zxmIi1vz02zGwUSfNkV61XV2+84/25Jm0Hvz/TJxIxPW/GPo+ALfrmUEwpHM3LT19fYKS/xXkR/TbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5466d82245b0014b329a9cc882215c39213de39e0c17b35a920c5cf90f56c975","last_reissued_at":"2026-07-05T12:04:47.891964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:47.891964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Augmented Quantization-Aware Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Justin Kur, Kaiqi Zhao","submitted_at":"2025-09-04T03:24:35Z","abstract_excerpt":"Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. Existing KD and QAT works focus on improving the accuracy of quantized models from the network output perspective by designing better KD loss functions or optimizing QAT's forward and backward propagation. However, limited attention has been given to understanding the impact of input transformations, such as data augmentation (DA). The relationship between quantization-aware KD and DA remains unexplored. In this paper, we address the questi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03850","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.03850/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":"2509.03850","created_at":"2026-07-05T12:04:47.892018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03850v1","created_at":"2026-07-05T12:04:47.892018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03850","created_at":"2026-07-05T12:04:47.892018+00:00"},{"alias_kind":"pith_short_12","alias_value":"KRTNQISFWAAU","created_at":"2026-07-05T12:04:47.892018+00:00"},{"alias_kind":"pith_short_16","alias_value":"KRTNQISFWAAUWMU2","created_at":"2026-07-05T12:04:47.892018+00:00"},{"alias_kind":"pith_short_8","alias_value":"KRTNQISF","created_at":"2026-07-05T12:04:47.892018+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/KRTNQISFWAAUWMU2TTEIEIK4HE","json":"https://pith.science/pith/KRTNQISFWAAUWMU2TTEIEIK4HE.json","graph_json":"https://pith.science/api/pith-number/KRTNQISFWAAUWMU2TTEIEIK4HE/graph.json","events_json":"https://pith.science/api/pith-number/KRTNQISFWAAUWMU2TTEIEIK4HE/events.json","paper":"https://pith.science/paper/KRTNQISF"},"agent_actions":{"view_html":"https://pith.science/pith/KRTNQISFWAAUWMU2TTEIEIK4HE","download_json":"https://pith.science/pith/KRTNQISFWAAUWMU2TTEIEIK4HE.json","view_paper":"https://pith.science/paper/KRTNQISF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03850&json=true","fetch_graph":"https://pith.science/api/pith-number/KRTNQISFWAAUWMU2TTEIEIK4HE/graph.json","fetch_events":"https://pith.science/api/pith-number/KRTNQISFWAAUWMU2TTEIEIK4HE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KRTNQISFWAAUWMU2TTEIEIK4HE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KRTNQISFWAAUWMU2TTEIEIK4HE/action/storage_attestation","attest_author":"https://pith.science/pith/KRTNQISFWAAUWMU2TTEIEIK4HE/action/author_attestation","sign_citation":"https://pith.science/pith/KRTNQISFWAAUWMU2TTEIEIK4HE/action/citation_signature","submit_replication":"https://pith.science/pith/KRTNQISFWAAUWMU2TTEIEIK4HE/action/replication_record"}},"created_at":"2026-07-05T12:04:47.892018+00:00","updated_at":"2026-07-05T12:04:47.892018+00:00"}