{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7TW4UKQNDAI3BPHPVIJ4JHKYSD","short_pith_number":"pith:7TW4UKQN","canonical_record":{"source":{"id":"2303.09556","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"e7f1c4c9632e3d564b6674179416e6b28954668e3495356146f3563c5e4b49cb","abstract_canon_sha256":"723d584d108d3489651a440a969999f6b0fc67e64ec35d1b20ad1ecbd461fef0"},"schema_version":"1.0"},"canonical_sha256":"fcedca2a0d1811b0bcefaa13c49d5890c59e653c958d13e24a78912f02202ea6","source":{"kind":"arxiv","id":"2303.09556","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09556","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09556v3","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09556","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"pith_short_12","alias_value":"7TW4UKQNDAI3","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"pith_short_16","alias_value":"7TW4UKQNDAI3BPHP","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"pith_short_8","alias_value":"7TW4UKQN","created_at":"2026-07-05T07:54:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7TW4UKQNDAI3BPHPVIJ4JHKYSD","target":"record","payload":{"canonical_record":{"source":{"id":"2303.09556","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"e7f1c4c9632e3d564b6674179416e6b28954668e3495356146f3563c5e4b49cb","abstract_canon_sha256":"723d584d108d3489651a440a969999f6b0fc67e64ec35d1b20ad1ecbd461fef0"},"schema_version":"1.0"},"canonical_sha256":"fcedca2a0d1811b0bcefaa13c49d5890c59e653c958d13e24a78912f02202ea6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:29.896524Z","signature_b64":"U3LwJ8EymZ3cnOHH2ECJTmp2a+Xzu/Q0ibZjPQWV4CXfWSfJtFCE9BPj/EJ84egUsVt8pykq9ja3BtOJL2cxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcedca2a0d1811b0bcefaa13c49d5890c59e653c958d13e24a78912f02202ea6","last_reissued_at":"2026-07-05T07:54:29.896022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:29.896022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.09556","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:54:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hphRBFhKM9KV4T64QM4x9duQih+uj7+GzdV5lo4QfmOzosQmDttTIqBDP4ut0z3AmNEo6K4drzRdRANIZNJKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:01:57.787681Z"},"content_sha256":"0eb8a56fee319c73edd7b7d43d85bd680dc8c6f2f7a4bee833761413623235fa","schema_version":"1.0","event_id":"sha256:0eb8a56fee319c73edd7b7d43d85bd680dc8c6f2f7a4bee833761413623235fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7TW4UKQNDAI3BPHPVIJ4JHKYSD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Chen Li, Dong Chen, Han Hu, Jianmin Bao, Shuyang Gu, Tiankai Hang, Xin Geng","submitted_at":"2023-03-16T17:59:56Z","abstract_excerpt":"Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting optimization directions between timesteps. To address this issue, we treat the diffusion training as a multi-task learning problem, and introduce a simple yet effective approach referred to as Min-SNR-$\\gamma$. This method adapts loss weights of timesteps based on clamped signal-to-noise ratios, which effectively balances the conflicts among timesteps. Our results "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09556","kind":"arxiv","version":3},"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/2303.09556/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:54:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4mrTFyEOaIb576a2rsXibx8T2FCUlAKxgbxWf0n0ifsWH0LWyC1aAVpMjss+FDM8ovsGGkgkNOi0S9626YdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:01:57.788270Z"},"content_sha256":"43e500378444d3247323228cf456629f658595e6be2e8252f3ce371b62f3f121","schema_version":"1.0","event_id":"sha256:43e500378444d3247323228cf456629f658595e6be2e8252f3ce371b62f3f121"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7TW4UKQNDAI3BPHPVIJ4JHKYSD/bundle.json","state_url":"https://pith.science/pith/7TW4UKQNDAI3BPHPVIJ4JHKYSD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7TW4UKQNDAI3BPHPVIJ4JHKYSD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T18:01:57Z","links":{"resolver":"https://pith.science/pith/7TW4UKQNDAI3BPHPVIJ4JHKYSD","bundle":"https://pith.science/pith/7TW4UKQNDAI3BPHPVIJ4JHKYSD/bundle.json","state":"https://pith.science/pith/7TW4UKQNDAI3BPHPVIJ4JHKYSD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7TW4UKQNDAI3BPHPVIJ4JHKYSD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7TW4UKQNDAI3BPHPVIJ4JHKYSD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"723d584d108d3489651a440a969999f6b0fc67e64ec35d1b20ad1ecbd461fef0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T17:59:56Z","title_canon_sha256":"e7f1c4c9632e3d564b6674179416e6b28954668e3495356146f3563c5e4b49cb"},"schema_version":"1.0","source":{"id":"2303.09556","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09556","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09556v3","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09556","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"pith_short_12","alias_value":"7TW4UKQNDAI3","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"pith_short_16","alias_value":"7TW4UKQNDAI3BPHP","created_at":"2026-07-05T07:54:29Z"},{"alias_kind":"pith_short_8","alias_value":"7TW4UKQN","created_at":"2026-07-05T07:54:29Z"}],"graph_snapshots":[{"event_id":"sha256:43e500378444d3247323228cf456629f658595e6be2e8252f3ce371b62f3f121","target":"graph","created_at":"2026-07-05T07:54:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.09556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence. In this paper, we discovered that the slow convergence is partly due to conflicting optimization directions between timesteps. To address this issue, we treat the diffusion training as a multi-task learning problem, and introduce a simple yet effective approach referred to as Min-SNR-$\\gamma$. This method adapts loss weights of timesteps based on clamped signal-to-noise ratios, which effectively balances the conflicts among timesteps. Our results ","authors_text":"Baining Guo, Chen Li, Dong Chen, Han Hu, Jianmin Bao, Shuyang Gu, Tiankai Hang, Xin Geng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T17:59:56Z","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09556","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0eb8a56fee319c73edd7b7d43d85bd680dc8c6f2f7a4bee833761413623235fa","target":"record","created_at":"2026-07-05T07:54:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"723d584d108d3489651a440a969999f6b0fc67e64ec35d1b20ad1ecbd461fef0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T17:59:56Z","title_canon_sha256":"e7f1c4c9632e3d564b6674179416e6b28954668e3495356146f3563c5e4b49cb"},"schema_version":"1.0","source":{"id":"2303.09556","kind":"arxiv","version":3}},"canonical_sha256":"fcedca2a0d1811b0bcefaa13c49d5890c59e653c958d13e24a78912f02202ea6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcedca2a0d1811b0bcefaa13c49d5890c59e653c958d13e24a78912f02202ea6","first_computed_at":"2026-07-05T07:54:29.896022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:29.896022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U3LwJ8EymZ3cnOHH2ECJTmp2a+Xzu/Q0ibZjPQWV4CXfWSfJtFCE9BPj/EJ84egUsVt8pykq9ja3BtOJL2cxCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:29.896524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09556","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eb8a56fee319c73edd7b7d43d85bd680dc8c6f2f7a4bee833761413623235fa","sha256:43e500378444d3247323228cf456629f658595e6be2e8252f3ce371b62f3f121"],"state_sha256":"6cd4c77135493c26c7d5e17fa2cf65bb288bf6cef9f988ffecd798d0acb85db5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q3pUZOBVr1wf4r+a1hX4rwT5PtOCg3tF6nD8/fZjB/rLitT1iLDl0hRdKqcXFdd+evabP+N+dsssLXfgxZD0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:01:57.793274Z","bundle_sha256":"fdf6a21730cc23879bb4b51297e06643ca434e8f62c908f2b7b0f6d09ef5ab8c"}}