{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TZGWETORBVFSZYBXVRTYLHD4WY","short_pith_number":"pith:TZGWETOR","schema_version":"1.0","canonical_sha256":"9e4d624dd10d4b2ce037ac67859c7cb61fc7deec5984ad887d14a9a77164eab8","source":{"kind":"arxiv","id":"2401.02414","version":1},"attestation_state":"computed","paper":{"title":"Bring Metric Functions into Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfeng Wang, Jie An, Jiebo Luo, Lijuan Wang, Linjie Li, Zhengyuan Yang, Zicheng Liu","submitted_at":"2024-01-04T18:55:01Z","abstract_excerpt":"We introduce a Cascaded Diffusion Model (Cas-DM) that improves a Denoising Diffusion Probabilistic Model (DDPM) by effectively incorporating additional metric functions in training. Metric functions such as the LPIPS loss have been proven highly effective in consistency models derived from the score matching. However, for the diffusion counterparts, the methodology and efficacy of adding extra metric functions remain unclear. One major challenge is the mismatch between the noise predicted by a DDPM at each step and the desired clean image that the metric function works well on. To address this"},"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":"2401.02414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-04T18:55:01Z","cross_cats_sorted":[],"title_canon_sha256":"f1fda597717b12201915744cfef0caa28a15b4331f1dc27b7ba0e01f1541520c","abstract_canon_sha256":"b34efa81b0fa612d6d6da7b6dcd73a85ea7e3d152cb56b713a1d64f6ec0b3328"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:16.378170Z","signature_b64":"rF2/oSF1Ta3VHAlS6PLD1HlID6dF3f2n2k6ej2PSB+cim/N034dFc75F1IPupm4IfbEXob+czliEdK5D1N/uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e4d624dd10d4b2ce037ac67859c7cb61fc7deec5984ad887d14a9a77164eab8","last_reissued_at":"2026-07-05T07:30:16.377742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:16.377742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bring Metric Functions into Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianfeng Wang, Jie An, Jiebo Luo, Lijuan Wang, Linjie Li, Zhengyuan Yang, Zicheng Liu","submitted_at":"2024-01-04T18:55:01Z","abstract_excerpt":"We introduce a Cascaded Diffusion Model (Cas-DM) that improves a Denoising Diffusion Probabilistic Model (DDPM) by effectively incorporating additional metric functions in training. Metric functions such as the LPIPS loss have been proven highly effective in consistency models derived from the score matching. However, for the diffusion counterparts, the methodology and efficacy of adding extra metric functions remain unclear. One major challenge is the mismatch between the noise predicted by a DDPM at each step and the desired clean image that the metric function works well on. To address this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02414","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/2401.02414/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":"2401.02414","created_at":"2026-07-05T07:30:16.377800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.02414v1","created_at":"2026-07-05T07:30:16.377800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02414","created_at":"2026-07-05T07:30:16.377800+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZGWETORBVFS","created_at":"2026-07-05T07:30:16.377800+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZGWETORBVFSZYBX","created_at":"2026-07-05T07:30:16.377800+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZGWETOR","created_at":"2026-07-05T07:30:16.377800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21432","citing_title":"Hume: Introducing System-2 Thinking in Visual-Language-Action Model","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY","json":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY.json","graph_json":"https://pith.science/api/pith-number/TZGWETORBVFSZYBXVRTYLHD4WY/graph.json","events_json":"https://pith.science/api/pith-number/TZGWETORBVFSZYBXVRTYLHD4WY/events.json","paper":"https://pith.science/paper/TZGWETOR"},"agent_actions":{"view_html":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY","download_json":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY.json","view_paper":"https://pith.science/paper/TZGWETOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.02414&json=true","fetch_graph":"https://pith.science/api/pith-number/TZGWETORBVFSZYBXVRTYLHD4WY/graph.json","fetch_events":"https://pith.science/api/pith-number/TZGWETORBVFSZYBXVRTYLHD4WY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY/action/storage_attestation","attest_author":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY/action/author_attestation","sign_citation":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY/action/citation_signature","submit_replication":"https://pith.science/pith/TZGWETORBVFSZYBXVRTYLHD4WY/action/replication_record"}},"created_at":"2026-07-05T07:30:16.377800+00:00","updated_at":"2026-07-05T07:30:16.377800+00:00"}