{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E4APQ2ZVIUM2ISSGBOFOPQV5M7","short_pith_number":"pith:E4APQ2ZV","schema_version":"1.0","canonical_sha256":"2700f86b354519a44a460b8ae7c2bd67ead90c3aa69a0c5f2e81d54c63637f0b","source":{"kind":"arxiv","id":"2310.03270","version":4},"attestation_state":"computed","paper":{"title":"EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Hong Zhou, Jing Liu, Weijia Wu, Yefei He","submitted_at":"2023-10-05T02:51:53Z","abstract_excerpt":"Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrained by substantial computational costs and latency issues. Quantization is a dominant way to compress and accelerate diffusion models, where post-training quantization (PTQ) and quantization-aware training (QAT) are two main approaches, each bearing its own properties. While PTQ exhibits efficiency in terms of both time and data usage, it may lead to diminished performance in low bit-width. On the other hand, QAT can"},"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":"2310.03270","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T02:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"d7a99644f474aedbc2933fbccf401a4101012b7b147a0438f510d3441a89db17","abstract_canon_sha256":"0cd54700c104ed4e8466ce26aaaab4d7dcea0e09e1b6c3b09aa66302face707c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:29.763602Z","signature_b64":"O2wwKi2xO4viah5WJbo8Qw1JpxLUbm0tlxUjc7sc6MoifPvoR+EUxmbs1PWNadfUjYMMmS+5+fpy939FSbCfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2700f86b354519a44a460b8ae7c2bd67ead90c3aa69a0c5f2e81d54c63637f0b","last_reissued_at":"2026-07-05T08:07:29.763117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:29.763117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Hong Zhou, Jing Liu, Weijia Wu, Yefei He","submitted_at":"2023-10-05T02:51:53Z","abstract_excerpt":"Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrained by substantial computational costs and latency issues. Quantization is a dominant way to compress and accelerate diffusion models, where post-training quantization (PTQ) and quantization-aware training (QAT) are two main approaches, each bearing its own properties. While PTQ exhibits efficiency in terms of both time and data usage, it may lead to diminished performance in low bit-width. On the other hand, QAT can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03270","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/2310.03270/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":"2310.03270","created_at":"2026-07-05T08:07:29.763173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03270v4","created_at":"2026-07-05T08:07:29.763173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03270","created_at":"2026-07-05T08:07:29.763173+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4APQ2ZVIUM2","created_at":"2026-07-05T08:07:29.763173+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4APQ2ZVIUM2ISSG","created_at":"2026-07-05T08:07:29.763173+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4APQ2ZV","created_at":"2026-07-05T08:07:29.763173+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2505.02242","citing_title":"Sampling-Aware Quantization for Diffusion Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12668","citing_title":"OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7","json":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7.json","graph_json":"https://pith.science/api/pith-number/E4APQ2ZVIUM2ISSGBOFOPQV5M7/graph.json","events_json":"https://pith.science/api/pith-number/E4APQ2ZVIUM2ISSGBOFOPQV5M7/events.json","paper":"https://pith.science/paper/E4APQ2ZV"},"agent_actions":{"view_html":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7","download_json":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7.json","view_paper":"https://pith.science/paper/E4APQ2ZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03270&json=true","fetch_graph":"https://pith.science/api/pith-number/E4APQ2ZVIUM2ISSGBOFOPQV5M7/graph.json","fetch_events":"https://pith.science/api/pith-number/E4APQ2ZVIUM2ISSGBOFOPQV5M7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7/action/storage_attestation","attest_author":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7/action/author_attestation","sign_citation":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7/action/citation_signature","submit_replication":"https://pith.science/pith/E4APQ2ZVIUM2ISSGBOFOPQV5M7/action/replication_record"}},"created_at":"2026-07-05T08:07:29.763173+00:00","updated_at":"2026-07-05T08:07:29.763173+00:00"}