{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SGZW22SNU6GWUUY2ZGMRDQT6K2","short_pith_number":"pith:SGZW22SN","canonical_record":{"source":{"id":"2405.20324","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:57:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"71c8c841e55f4e0d183a6e653ecf96e464abfd45f7453aac9f1c4bad1cb6565c","abstract_canon_sha256":"b06ce9a45a1a2cd0284c73d1e71730279716ef663a97f43d4d607027da9055b2"},"schema_version":"1.0"},"canonical_sha256":"91b36d6a4da78d6a531ac99911c27e5698385f648998fd5bdec1cdd1746a7445","source":{"kind":"arxiv","id":"2405.20324","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20324","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20324v2","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20324","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"SGZW22SNU6GW","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"SGZW22SNU6GWUUY2","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"SGZW22SN","created_at":"2026-07-05T10:16:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SGZW22SNU6GWUUY2ZGMRDQT6K2","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20324","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:57:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"71c8c841e55f4e0d183a6e653ecf96e464abfd45f7453aac9f1c4bad1cb6565c","abstract_canon_sha256":"b06ce9a45a1a2cd0284c73d1e71730279716ef663a97f43d4d607027da9055b2"},"schema_version":"1.0"},"canonical_sha256":"91b36d6a4da78d6a531ac99911c27e5698385f648998fd5bdec1cdd1746a7445","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:09.375793Z","signature_b64":"a1+8Ln1DXWA1sbJHnPQcx0Y/r4N9Atcj5ZKzm4VeGM6ozk1gWFSxC97U+5DSFe+SEXxvjiG/LnnPC83yWS1OBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91b36d6a4da78d6a531ac99911c27e5698385f648998fd5bdec1cdd1746a7445","last_reissued_at":"2026-07-05T10:16:09.375306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:09.375306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20324","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"opWw+SDdLj3JXZzK6uvYO+JdN4U49fF/RaqGBhEOaQM5yki53evv8mZwJw/DbwWiC4Vm45BPPLTiHYGJCEqYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:19:46.770804Z"},"content_sha256":"442144e65c515509eb040a13a3d597db5471039c92e893a4e68bc16e8e990382","schema_version":"1.0","event_id":"sha256:442144e65c515509eb040a13a3d597db5471039c92e893a4e68bc16e8e990382"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SGZW22SNU6GWUUY2ZGMRDQT6K2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't drop your samples! Coherence-aware training benefits Conditional diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"David Picard, Nicolas Dufour, Vicky Kalogeiton, Victor Besnier","submitted_at":"2024-05-30T17:57:26Z","abstract_excerpt":"Conditional diffusion models are powerful generative models that can leverage various types of conditional information, such as class labels, segmentation masks, or text captions. However, in many real-world scenarios, conditional information may be noisy or unreliable due to human annotation errors or weak alignment. In this paper, we propose the Coherence-Aware Diffusion (CAD), a novel method that integrates coherence in conditional information into diffusion models, allowing them to learn from noisy annotations without discarding data. We assume that each data point has an associated cohere"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20324","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/2405.20324/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":"2026-07-05T10:16:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"200bYXiBKgq7/R8VZmocMW+TcZSSv16K6xsO+7CNFjmyKx4Et3k7nmVh5hJaBBpXCGza+yF3HjwcTRt8JoLGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T15:19:46.771454Z"},"content_sha256":"a8d5dbd64a277bfd5930183f9da495a50e05e069ec396d2e2220fdf9e7e39e7c","schema_version":"1.0","event_id":"sha256:a8d5dbd64a277bfd5930183f9da495a50e05e069ec396d2e2220fdf9e7e39e7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGZW22SNU6GWUUY2ZGMRDQT6K2/bundle.json","state_url":"https://pith.science/pith/SGZW22SNU6GWUUY2ZGMRDQT6K2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGZW22SNU6GWUUY2ZGMRDQT6K2/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":"2026-08-14T15:19:46Z","links":{"resolver":"https://pith.science/pith/SGZW22SNU6GWUUY2ZGMRDQT6K2","bundle":"https://pith.science/pith/SGZW22SNU6GWUUY2ZGMRDQT6K2/bundle.json","state":"https://pith.science/pith/SGZW22SNU6GWUUY2ZGMRDQT6K2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGZW22SNU6GWUUY2ZGMRDQT6K2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SGZW22SNU6GWUUY2ZGMRDQT6K2","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":"b06ce9a45a1a2cd0284c73d1e71730279716ef663a97f43d4d607027da9055b2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:57:26Z","title_canon_sha256":"71c8c841e55f4e0d183a6e653ecf96e464abfd45f7453aac9f1c4bad1cb6565c"},"schema_version":"1.0","source":{"id":"2405.20324","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20324","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20324v2","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20324","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"SGZW22SNU6GW","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"SGZW22SNU6GWUUY2","created_at":"2026-07-05T10:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"SGZW22SN","created_at":"2026-07-05T10:16:09Z"}],"graph_snapshots":[{"event_id":"sha256:a8d5dbd64a277bfd5930183f9da495a50e05e069ec396d2e2220fdf9e7e39e7c","target":"graph","created_at":"2026-07-05T10:16:09Z","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/2405.20324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conditional diffusion models are powerful generative models that can leverage various types of conditional information, such as class labels, segmentation masks, or text captions. However, in many real-world scenarios, conditional information may be noisy or unreliable due to human annotation errors or weak alignment. In this paper, we propose the Coherence-Aware Diffusion (CAD), a novel method that integrates coherence in conditional information into diffusion models, allowing them to learn from noisy annotations without discarding data. We assume that each data point has an associated cohere","authors_text":"David Picard, Nicolas Dufour, Vicky Kalogeiton, Victor Besnier","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:57:26Z","title":"Don't drop your samples! Coherence-aware training benefits Conditional diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20324","kind":"arxiv","version":2},"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":"sha256:442144e65c515509eb040a13a3d597db5471039c92e893a4e68bc16e8e990382","target":"record","created_at":"2026-07-05T10:16:09Z","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":"b06ce9a45a1a2cd0284c73d1e71730279716ef663a97f43d4d607027da9055b2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T17:57:26Z","title_canon_sha256":"71c8c841e55f4e0d183a6e653ecf96e464abfd45f7453aac9f1c4bad1cb6565c"},"schema_version":"1.0","source":{"id":"2405.20324","kind":"arxiv","version":2}},"canonical_sha256":"91b36d6a4da78d6a531ac99911c27e5698385f648998fd5bdec1cdd1746a7445","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91b36d6a4da78d6a531ac99911c27e5698385f648998fd5bdec1cdd1746a7445","first_computed_at":"2026-07-05T10:16:09.375306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:09.375306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a1+8Ln1DXWA1sbJHnPQcx0Y/r4N9Atcj5ZKzm4VeGM6ozk1gWFSxC97U+5DSFe+SEXxvjiG/LnnPC83yWS1OBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:09.375793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20324","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:442144e65c515509eb040a13a3d597db5471039c92e893a4e68bc16e8e990382","sha256:a8d5dbd64a277bfd5930183f9da495a50e05e069ec396d2e2220fdf9e7e39e7c"],"state_sha256":"8b5481b6ce22d30ab1f2871ad4739d4df3581df27fa4bd6cfb5013b81eb486c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLG7FhrWClKkOQbvcECLMqgisM7YGHTjHJ0OOi5+uvVJ3rskx2K2imay52AcjdSVwo97twdvlCpgYzaiBxSGCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T15:19:46.775862Z","bundle_sha256":"803bbb3142ab197720795eb4a9231a9e613bb35e934a703d4f3235dfe04b2696"}}