{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V7TZ57Q5PXVQ6DOY6DMTXWF4M5","short_pith_number":"pith:V7TZ57Q5","schema_version":"1.0","canonical_sha256":"afe79efe1d7deb0f0dd8f0d93bd8bc67693061d45c7b5c064a98f8563dcfcb9b","source":{"kind":"arxiv","id":"2404.05662","version":5},"attestation_state":"computed","paper":{"title":"BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haojie Hao, Haotong Qin, Jiakai Wang, Jinyang Guo, Michele Magno, Mingyuan Zhang, Xianglong Liu, Xingyu Zheng, Xudong Ma, Zixiang Zhao","submitted_at":"2024-04-08T16:46:25Z","abstract_excerpt":"With the advancement of diffusion models (DMs) and the substantially increased computational requirements, quantization emerges as a practical solution to obtain compact and efficient low-bit DMs. However, the highly discrete representation leads to severe accuracy degradation, hindering the quantization of diffusion models to ultra-low bit-widths. This paper proposes a novel weight binarization approach for DMs, namely BinaryDM, pushing binarized DMs to be accurate and efficient by improving the representation and optimization. From the representation perspective, we present an Evolvable-Basi"},"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":"2404.05662","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T16:46:25Z","cross_cats_sorted":[],"title_canon_sha256":"902499b76e53913677c832afa44de33c5567a32f10b160a24e190f9772e9b6a1","abstract_canon_sha256":"2f237b79c51bf96de22c56cdf1b05858a6edf2558da2a7ee7d969439d1097a4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:40.931542Z","signature_b64":"ssjiTxtV/u2bb8m0hlY0RADeC/NWvVE/Ly8o2SgLVjT2JXV8ihoICwtQ9p2OBGmRAB7sOeZxUJDTtjCR6kVTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afe79efe1d7deb0f0dd8f0d93bd8bc67693061d45c7b5c064a98f8563dcfcb9b","last_reissued_at":"2026-07-05T10:07:40.931056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:40.931056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haojie Hao, Haotong Qin, Jiakai Wang, Jinyang Guo, Michele Magno, Mingyuan Zhang, Xianglong Liu, Xingyu Zheng, Xudong Ma, Zixiang Zhao","submitted_at":"2024-04-08T16:46:25Z","abstract_excerpt":"With the advancement of diffusion models (DMs) and the substantially increased computational requirements, quantization emerges as a practical solution to obtain compact and efficient low-bit DMs. However, the highly discrete representation leads to severe accuracy degradation, hindering the quantization of diffusion models to ultra-low bit-widths. This paper proposes a novel weight binarization approach for DMs, namely BinaryDM, pushing binarized DMs to be accurate and efficient by improving the representation and optimization. From the representation perspective, we present an Evolvable-Basi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05662","kind":"arxiv","version":5},"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/2404.05662/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":"2404.05662","created_at":"2026-07-05T10:07:40.931115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05662v5","created_at":"2026-07-05T10:07:40.931115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05662","created_at":"2026-07-05T10:07:40.931115+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7TZ57Q5PXVQ","created_at":"2026-07-05T10:07:40.931115+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7TZ57Q5PXVQ6DOY","created_at":"2026-07-05T10:07:40.931115+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7TZ57Q5","created_at":"2026-07-05T10:07:40.931115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04290","citing_title":"MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5","json":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5.json","graph_json":"https://pith.science/api/pith-number/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/graph.json","events_json":"https://pith.science/api/pith-number/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/events.json","paper":"https://pith.science/paper/V7TZ57Q5"},"agent_actions":{"view_html":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5","download_json":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5.json","view_paper":"https://pith.science/paper/V7TZ57Q5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05662&json=true","fetch_graph":"https://pith.science/api/pith-number/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/graph.json","fetch_events":"https://pith.science/api/pith-number/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/action/storage_attestation","attest_author":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/action/author_attestation","sign_citation":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/action/citation_signature","submit_replication":"https://pith.science/pith/V7TZ57Q5PXVQ6DOY6DMTXWF4M5/action/replication_record"}},"created_at":"2026-07-05T10:07:40.931115+00:00","updated_at":"2026-07-05T10:07:40.931115+00:00"}