{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ADJZFUP3MVQDKPZEGKPCXNARTG","short_pith_number":"pith:ADJZFUP3","schema_version":"1.0","canonical_sha256":"00d392d1fb6560353f24329e2bb4119981913387e8b4a224d7697926c15bc144","source":{"kind":"arxiv","id":"2501.00603","version":2},"attestation_state":"computed","paper":{"title":"DiC: Rethinking Conv3x3 Designs in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chao Xu, Chengcheng Wang, Hanting Chen, Jing Han, Yuchen Liang, Yuchuan Tian","submitted_at":"2024-12-31T19:00:01Z","abstract_excerpt":"Diffusion models have shown exceptional performance in visual generation tasks. Recently, these models have shifted from traditional U-Shaped CNN-Attention hybrid structures to fully transformer-based isotropic architectures. While these transformers exhibit strong scalability and performance, their reliance on complicated self-attention operation results in slow inference speeds. Contrary to these works, we rethink one of the simplest yet fastest module in deep learning, 3x3 Convolution, to construct a scaled-up purely convolutional diffusion model. We first discover that an Encoder-Decoder H"},"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":"2501.00603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T19:00:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7c6a6e528f06dc8c2f32f63455064cd2a86e8690f5253224f98c16f716379b8a","abstract_canon_sha256":"162e8e28da7d562d616f1a72dac8b3968dcc3191627d96faec4d6e3eb8d0363e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:39.566682Z","signature_b64":"SI6CPPO9Xv9XdWEdXF8Fbkidbu6tFYaFPQ+oByU0j8C0Ji1HvbaBuAIaLG+/2JfRjNVt66LsFB47j0wegG5UCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00d392d1fb6560353f24329e2bb4119981913387e8b4a224d7697926c15bc144","last_reissued_at":"2026-07-05T11:17:39.566200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:39.566200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiC: Rethinking Conv3x3 Designs in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chao Xu, Chengcheng Wang, Hanting Chen, Jing Han, Yuchen Liang, Yuchuan Tian","submitted_at":"2024-12-31T19:00:01Z","abstract_excerpt":"Diffusion models have shown exceptional performance in visual generation tasks. Recently, these models have shifted from traditional U-Shaped CNN-Attention hybrid structures to fully transformer-based isotropic architectures. While these transformers exhibit strong scalability and performance, their reliance on complicated self-attention operation results in slow inference speeds. Contrary to these works, we rethink one of the simplest yet fastest module in deep learning, 3x3 Convolution, to construct a scaled-up purely convolutional diffusion model. We first discover that an Encoder-Decoder H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00603","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/2501.00603/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":"2501.00603","created_at":"2026-07-05T11:17:39.566260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00603v2","created_at":"2026-07-05T11:17:39.566260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00603","created_at":"2026-07-05T11:17:39.566260+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADJZFUP3MVQD","created_at":"2026-07-05T11:17:39.566260+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADJZFUP3MVQDKPZE","created_at":"2026-07-05T11:17:39.566260+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADJZFUP3","created_at":"2026-07-05T11:17:39.566260+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/ADJZFUP3MVQDKPZEGKPCXNARTG","json":"https://pith.science/pith/ADJZFUP3MVQDKPZEGKPCXNARTG.json","graph_json":"https://pith.science/api/pith-number/ADJZFUP3MVQDKPZEGKPCXNARTG/graph.json","events_json":"https://pith.science/api/pith-number/ADJZFUP3MVQDKPZEGKPCXNARTG/events.json","paper":"https://pith.science/paper/ADJZFUP3"},"agent_actions":{"view_html":"https://pith.science/pith/ADJZFUP3MVQDKPZEGKPCXNARTG","download_json":"https://pith.science/pith/ADJZFUP3MVQDKPZEGKPCXNARTG.json","view_paper":"https://pith.science/paper/ADJZFUP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00603&json=true","fetch_graph":"https://pith.science/api/pith-number/ADJZFUP3MVQDKPZEGKPCXNARTG/graph.json","fetch_events":"https://pith.science/api/pith-number/ADJZFUP3MVQDKPZEGKPCXNARTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADJZFUP3MVQDKPZEGKPCXNARTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADJZFUP3MVQDKPZEGKPCXNARTG/action/storage_attestation","attest_author":"https://pith.science/pith/ADJZFUP3MVQDKPZEGKPCXNARTG/action/author_attestation","sign_citation":"https://pith.science/pith/ADJZFUP3MVQDKPZEGKPCXNARTG/action/citation_signature","submit_replication":"https://pith.science/pith/ADJZFUP3MVQDKPZEGKPCXNARTG/action/replication_record"}},"created_at":"2026-07-05T11:17:39.566260+00:00","updated_at":"2026-07-05T11:17:39.566260+00:00"}