{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FEDNJ2TTPNHX6UPTBROXCJK42D","short_pith_number":"pith:FEDNJ2TT","canonical_record":{"source":{"id":"2503.12536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-16T15:02:52Z","cross_cats_sorted":["cs.CV","cs.CY"],"title_canon_sha256":"854347e945c353c1e1d5335af9aba4123b2e1864d2cf9d53b67b5cdc38091464","abstract_canon_sha256":"1f937d9cd86566d6ae4be7228942ddb147dc1d865f2561eed7588de1d96003fc"},"schema_version":"1.0"},"canonical_sha256":"2906d4ea737b4f7f51f30c5d71255cd0cdfd3e7d5297a872031ad4662a98d89a","source":{"kind":"arxiv","id":"2503.12536","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12536","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12536v1","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12536","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_12","alias_value":"FEDNJ2TTPNHX","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_16","alias_value":"FEDNJ2TTPNHX6UPT","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_8","alias_value":"FEDNJ2TT","created_at":"2026-07-05T10:32:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FEDNJ2TTPNHX6UPTBROXCJK42D","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-16T15:02:52Z","cross_cats_sorted":["cs.CV","cs.CY"],"title_canon_sha256":"854347e945c353c1e1d5335af9aba4123b2e1864d2cf9d53b67b5cdc38091464","abstract_canon_sha256":"1f937d9cd86566d6ae4be7228942ddb147dc1d865f2561eed7588de1d96003fc"},"schema_version":"1.0"},"canonical_sha256":"2906d4ea737b4f7f51f30c5d71255cd0cdfd3e7d5297a872031ad4662a98d89a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:15.722422Z","signature_b64":"92nDB6tOiwlVG5vrOv+Fjj8baSSc63YPv4W4cauxepcVL+JOB/b1qjeZHm+VGjZ5Tt+yad1/YY7RARHW+cREDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2906d4ea737b4f7f51f30c5d71255cd0cdfd3e7d5297a872031ad4662a98d89a","last_reissued_at":"2026-07-05T10:32:15.721809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:15.721809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12536","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNbFCe0mvayLwIwX4IL67h6R5bGOC04KXuL2XoqybWJqa//3z/gB9N9j/JM4ddZCLm5sRwhJHMuVEN+4E0NJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:00:09.426275Z"},"content_sha256":"f1f5386ff23393e61cfdb2ca807021012ead20cb9ccf903deefbb449b78c66d1","schema_version":"1.0","event_id":"sha256:f1f5386ff23393e61cfdb2ca807021012ead20cb9ccf903deefbb449b78c66d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FEDNJ2TTPNHX6UPTBROXCJK42D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.CY"],"primary_cat":"cs.LG","authors_text":"Ching Chieh Tsao, Fang-Yi Su, Jung-Hsien Chiang, Lin-Chun Huang","submitted_at":"2025-03-16T15:02:52Z","abstract_excerpt":"Image generative models, particularly diffusion-based models, have surged in popularity due to their remarkable ability to synthesize highly realistic images. However, since these models are data-driven, they inherit biases from the training datasets, frequently leading to disproportionate group representations that exacerbate societal inequities. Traditionally, efforts to debiase these models have relied on predefined sensitive attributes, classifiers trained on such attributes, or large language models to steer outputs toward fairness. However, these approaches face notable drawbacks: predef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12536","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/2503.12536/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":"2026-07-05T10:32:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DX2d9Lz49SrTo5zjNARkWKV2xspD1eXCe6YN+MEtBr8t228RYleWRpJaNvDU8rpIPTstSNcZwlq42fACZvYdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:00:09.426838Z"},"content_sha256":"157f3335ed83f8cf3cbe55dfe1f746e175dcf1fffbeb76433b643fa06b209eb4","schema_version":"1.0","event_id":"sha256:157f3335ed83f8cf3cbe55dfe1f746e175dcf1fffbeb76433b643fa06b209eb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FEDNJ2TTPNHX6UPTBROXCJK42D/bundle.json","state_url":"https://pith.science/pith/FEDNJ2TTPNHX6UPTBROXCJK42D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FEDNJ2TTPNHX6UPTBROXCJK42D/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":"2026-08-08T18:00:09Z","links":{"resolver":"https://pith.science/pith/FEDNJ2TTPNHX6UPTBROXCJK42D","bundle":"https://pith.science/pith/FEDNJ2TTPNHX6UPTBROXCJK42D/bundle.json","state":"https://pith.science/pith/FEDNJ2TTPNHX6UPTBROXCJK42D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FEDNJ2TTPNHX6UPTBROXCJK42D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FEDNJ2TTPNHX6UPTBROXCJK42D","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":"1f937d9cd86566d6ae4be7228942ddb147dc1d865f2561eed7588de1d96003fc","cross_cats_sorted":["cs.CV","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-16T15:02:52Z","title_canon_sha256":"854347e945c353c1e1d5335af9aba4123b2e1864d2cf9d53b67b5cdc38091464"},"schema_version":"1.0","source":{"id":"2503.12536","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12536","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12536v1","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12536","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_12","alias_value":"FEDNJ2TTPNHX","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_16","alias_value":"FEDNJ2TTPNHX6UPT","created_at":"2026-07-05T10:32:15Z"},{"alias_kind":"pith_short_8","alias_value":"FEDNJ2TT","created_at":"2026-07-05T10:32:15Z"}],"graph_snapshots":[{"event_id":"sha256:157f3335ed83f8cf3cbe55dfe1f746e175dcf1fffbeb76433b643fa06b209eb4","target":"graph","created_at":"2026-07-05T10:32:15Z","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/2503.12536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image generative models, particularly diffusion-based models, have surged in popularity due to their remarkable ability to synthesize highly realistic images. However, since these models are data-driven, they inherit biases from the training datasets, frequently leading to disproportionate group representations that exacerbate societal inequities. Traditionally, efforts to debiase these models have relied on predefined sensitive attributes, classifiers trained on such attributes, or large language models to steer outputs toward fairness. However, these approaches face notable drawbacks: predef","authors_text":"Ching Chieh Tsao, Fang-Yi Su, Jung-Hsien Chiang, Lin-Chun Huang","cross_cats":["cs.CV","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-16T15:02:52Z","title":"Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12536","kind":"arxiv","version":1},"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:f1f5386ff23393e61cfdb2ca807021012ead20cb9ccf903deefbb449b78c66d1","target":"record","created_at":"2026-07-05T10:32:15Z","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":"1f937d9cd86566d6ae4be7228942ddb147dc1d865f2561eed7588de1d96003fc","cross_cats_sorted":["cs.CV","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-16T15:02:52Z","title_canon_sha256":"854347e945c353c1e1d5335af9aba4123b2e1864d2cf9d53b67b5cdc38091464"},"schema_version":"1.0","source":{"id":"2503.12536","kind":"arxiv","version":1}},"canonical_sha256":"2906d4ea737b4f7f51f30c5d71255cd0cdfd3e7d5297a872031ad4662a98d89a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2906d4ea737b4f7f51f30c5d71255cd0cdfd3e7d5297a872031ad4662a98d89a","first_computed_at":"2026-07-05T10:32:15.721809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:15.721809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"92nDB6tOiwlVG5vrOv+Fjj8baSSc63YPv4W4cauxepcVL+JOB/b1qjeZHm+VGjZ5Tt+yad1/YY7RARHW+cREDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:15.722422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12536","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1f5386ff23393e61cfdb2ca807021012ead20cb9ccf903deefbb449b78c66d1","sha256:157f3335ed83f8cf3cbe55dfe1f746e175dcf1fffbeb76433b643fa06b209eb4"],"state_sha256":"e784fd1699eedb409556d1c8e3a5d954d01e537e5c1fc32fa4bf79efd83c6bb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zcT4CJf//6fPTc8qvPFSmXGYfQBdmS0qlCyjXb6iJ09VAfLEnYNGhya5yyLUKmJOV5pMVYNzQPhEvS8JnUFNAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:00:09.431350Z","bundle_sha256":"d024e59851b455607b054d92ffdfcd380f68cbccfe450e667d56cd47eb2dff5e"}}