{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZWDJJTG22UPCP2CG2WZ5KZ2KPA","short_pith_number":"pith:ZWDJJTG2","schema_version":"1.0","canonical_sha256":"cd8694ccdad51e27e846d5b3d5674a781074591498fcccc2ca0fe9c0634fdb90","source":{"kind":"arxiv","id":"2502.00333","version":2},"attestation_state":"computed","paper":{"title":"BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaicheng Yang, Kai Liu, Linghe Kong, Wenbo Li, Yong Guo, Yulun Zhang, Zheng Chen, Zhiteng Li","submitted_at":"2025-02-01T06:34:55Z","abstract_excerpt":"While super-resolution (SR) methods based on diffusion models (DM) have demonstrated inspiring performance, their deployment is impeded due to the heavy request of memory and computation. Recent researchers apply two kinds of methods to compress or fasten the DM. One is to compress the DM into 1-bit, aka binarization, alleviating the storage and computation pressure. The other distills the multi-step DM into only one step, significantly speeding up inference process. Nonetheless, it remains impossible to deploy DM to resource-limited edge devices. To address this problem, we propose BiMaCoSR, "},"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":"2502.00333","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-01T06:34:55Z","cross_cats_sorted":[],"title_canon_sha256":"7bc284b45ed46ebc22d2d2bef5869efed614c6dece5b05db63a66689d970490e","abstract_canon_sha256":"c9aac1a14744cc4923322de41fc66209fb290bfcea492cb5afab2b85d1fc92d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:16.237809Z","signature_b64":"Ll1v4HkmRshCAbfPwi09NYIbQikXIEPsjcSLq/yjXRFGRfkut1/1wSN6gMwQeTDVUKL9X0WM5Di3rkBkG29UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd8694ccdad51e27e846d5b3d5674a781074591498fcccc2ca0fe9c0634fdb90","last_reissued_at":"2026-07-05T10:09:16.237372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:16.237372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaicheng Yang, Kai Liu, Linghe Kong, Wenbo Li, Yong Guo, Yulun Zhang, Zheng Chen, Zhiteng Li","submitted_at":"2025-02-01T06:34:55Z","abstract_excerpt":"While super-resolution (SR) methods based on diffusion models (DM) have demonstrated inspiring performance, their deployment is impeded due to the heavy request of memory and computation. Recent researchers apply two kinds of methods to compress or fasten the DM. One is to compress the DM into 1-bit, aka binarization, alleviating the storage and computation pressure. The other distills the multi-step DM into only one step, significantly speeding up inference process. Nonetheless, it remains impossible to deploy DM to resource-limited edge devices. To address this problem, we propose BiMaCoSR, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00333","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/2502.00333/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":"2502.00333","created_at":"2026-07-05T10:09:16.237430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00333v2","created_at":"2026-07-05T10:09:16.237430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00333","created_at":"2026-07-05T10:09:16.237430+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWDJJTG22UPC","created_at":"2026-07-05T10:09:16.237430+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWDJJTG22UPCP2CG","created_at":"2026-07-05T10:09:16.237430+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWDJJTG2","created_at":"2026-07-05T10:09:16.237430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23486","citing_title":"From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13054","citing_title":"TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA","json":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA.json","graph_json":"https://pith.science/api/pith-number/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/graph.json","events_json":"https://pith.science/api/pith-number/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/events.json","paper":"https://pith.science/paper/ZWDJJTG2"},"agent_actions":{"view_html":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA","download_json":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA.json","view_paper":"https://pith.science/paper/ZWDJJTG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00333&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/action/storage_attestation","attest_author":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/action/author_attestation","sign_citation":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/action/citation_signature","submit_replication":"https://pith.science/pith/ZWDJJTG22UPCP2CG2WZ5KZ2KPA/action/replication_record"}},"created_at":"2026-07-05T10:09:16.237430+00:00","updated_at":"2026-07-05T10:09:16.237430+00:00"}