{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QUGDRE72XHZ6M33TY4KU5BRKCV","short_pith_number":"pith:QUGDRE72","canonical_record":{"source":{"id":"2310.06904","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T18:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"cbe91fb9b84a7e8c4dab0a38dc5ad33c08a8eccec5935e32de27028e56a1fdc5","abstract_canon_sha256":"5486ed446e95b021031e0b9620298dc9b818e82942c3cab71771b7bf022a44da"},"schema_version":"1.0"},"canonical_sha256":"850c3893fab9f3e66f73c7154e862a15649a86504b0e3d511c04f3cef8001e11","source":{"kind":"arxiv","id":"2310.06904","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06904","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06904v1","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06904","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"QUGDRE72XHZ6","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"pith_short_16","alias_value":"QUGDRE72XHZ6M33T","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"pith_short_8","alias_value":"QUGDRE72","created_at":"2026-07-05T06:59:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QUGDRE72XHZ6M33TY4KU5BRKCV","target":"record","payload":{"canonical_record":{"source":{"id":"2310.06904","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T18:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"cbe91fb9b84a7e8c4dab0a38dc5ad33c08a8eccec5935e32de27028e56a1fdc5","abstract_canon_sha256":"5486ed446e95b021031e0b9620298dc9b818e82942c3cab71771b7bf022a44da"},"schema_version":"1.0"},"canonical_sha256":"850c3893fab9f3e66f73c7154e862a15649a86504b0e3d511c04f3cef8001e11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:37.960923Z","signature_b64":"uLHibMQP54Cch/AAExNrJYXq/MMl6zuy2axm7MFCpbuvC9JAiY6Ov8+/V80ZuRynd2yAR4fWB2FEnpb6qJt1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"850c3893fab9f3e66f73c7154e862a15649a86504b0e3d511c04f3cef8001e11","last_reissued_at":"2026-07-05T06:59:37.960477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:37.960477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.06904","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":"2026-07-05T06:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cAVDwr8OO9wPgVYBntkjK4cu+c8yJZd3uvYAo5WNBBzmylRkp4c+IQkdkLUJZf351N4HHFTp33e82hpPlKPiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:28:28.607987Z"},"content_sha256":"8e7fcd83b17a0b81d871ba30e90d992734e6d301c3022323642e09e677454256","schema_version":"1.0","event_id":"sha256:8e7fcd83b17a0b81d871ba30e90d992734e6d301c3022323642e09e677454256"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QUGDRE72XHZ6M33TY4KU5BRKCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mitigating stereotypical biases in text to image generative systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anastasis Germanidis, Deepti Ghadiyaram, Parmida Atighehchian, Piero Esposito","submitted_at":"2023-10-10T18:01:52Z","abstract_excerpt":"State-of-the-art generative text-to-image models are known to exhibit social biases and over-represent certain groups like people of perceived lighter skin tones and men in their outcomes. In this work, we propose a method to mitigate such biases and ensure that the outcomes are fair across different groups of people. We do this by finetuning text-to-image models on synthetic data that varies in perceived skin tones and genders constructed from diverse text prompts. These text prompts are constructed from multiplicative combinations of ethnicities, genders, professions, age groups, and so on, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06904","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/2310.06904/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":"2026-07-05T06:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Psxz3N0lu30FwAGHcNDCP7cRmk9t6NqlPJ5c8r/dnyy8ZLGn+8EwuZSsLEFT8IFBdmds8h7illiyOZxIhQ2gCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:28:28.608369Z"},"content_sha256":"b5139d7e656f4e16fc9060ce605799ddda2b8ac0c225f9f56340da74bba2b881","schema_version":"1.0","event_id":"sha256:b5139d7e656f4e16fc9060ce605799ddda2b8ac0c225f9f56340da74bba2b881"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUGDRE72XHZ6M33TY4KU5BRKCV/bundle.json","state_url":"https://pith.science/pith/QUGDRE72XHZ6M33TY4KU5BRKCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUGDRE72XHZ6M33TY4KU5BRKCV/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":"2026-07-06T12:28:28Z","links":{"resolver":"https://pith.science/pith/QUGDRE72XHZ6M33TY4KU5BRKCV","bundle":"https://pith.science/pith/QUGDRE72XHZ6M33TY4KU5BRKCV/bundle.json","state":"https://pith.science/pith/QUGDRE72XHZ6M33TY4KU5BRKCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUGDRE72XHZ6M33TY4KU5BRKCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QUGDRE72XHZ6M33TY4KU5BRKCV","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":"5486ed446e95b021031e0b9620298dc9b818e82942c3cab71771b7bf022a44da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T18:01:52Z","title_canon_sha256":"cbe91fb9b84a7e8c4dab0a38dc5ad33c08a8eccec5935e32de27028e56a1fdc5"},"schema_version":"1.0","source":{"id":"2310.06904","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06904","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06904v1","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06904","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"QUGDRE72XHZ6","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"pith_short_16","alias_value":"QUGDRE72XHZ6M33T","created_at":"2026-07-05T06:59:37Z"},{"alias_kind":"pith_short_8","alias_value":"QUGDRE72","created_at":"2026-07-05T06:59:37Z"}],"graph_snapshots":[{"event_id":"sha256:b5139d7e656f4e16fc9060ce605799ddda2b8ac0c225f9f56340da74bba2b881","target":"graph","created_at":"2026-07-05T06:59:37Z","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/2310.06904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art generative text-to-image models are known to exhibit social biases and over-represent certain groups like people of perceived lighter skin tones and men in their outcomes. In this work, we propose a method to mitigate such biases and ensure that the outcomes are fair across different groups of people. We do this by finetuning text-to-image models on synthetic data that varies in perceived skin tones and genders constructed from diverse text prompts. These text prompts are constructed from multiplicative combinations of ethnicities, genders, professions, age groups, and so on, ","authors_text":"Anastasis Germanidis, Deepti Ghadiyaram, Parmida Atighehchian, Piero Esposito","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T18:01:52Z","title":"Mitigating stereotypical biases in text to image generative systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06904","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":"sha256:8e7fcd83b17a0b81d871ba30e90d992734e6d301c3022323642e09e677454256","target":"record","created_at":"2026-07-05T06:59:37Z","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":"5486ed446e95b021031e0b9620298dc9b818e82942c3cab71771b7bf022a44da","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T18:01:52Z","title_canon_sha256":"cbe91fb9b84a7e8c4dab0a38dc5ad33c08a8eccec5935e32de27028e56a1fdc5"},"schema_version":"1.0","source":{"id":"2310.06904","kind":"arxiv","version":1}},"canonical_sha256":"850c3893fab9f3e66f73c7154e862a15649a86504b0e3d511c04f3cef8001e11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"850c3893fab9f3e66f73c7154e862a15649a86504b0e3d511c04f3cef8001e11","first_computed_at":"2026-07-05T06:59:37.960477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:37.960477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uLHibMQP54Cch/AAExNrJYXq/MMl6zuy2axm7MFCpbuvC9JAiY6Ov8+/V80ZuRynd2yAR4fWB2FEnpb6qJt1Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:37.960923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06904","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e7fcd83b17a0b81d871ba30e90d992734e6d301c3022323642e09e677454256","sha256:b5139d7e656f4e16fc9060ce605799ddda2b8ac0c225f9f56340da74bba2b881"],"state_sha256":"208dcbf5c7e739828e6b1f475be16e5574c255820ee62a9e5023bf4cf4880a7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wyyDe7vJhgmddgI+I6KHeciziaTXYyssjf3pMcY7FYXszXa3chHhVI9oFf8xJwAqKCQThFajrFAhlbWo7ciKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:28:28.610245Z","bundle_sha256":"01c4d42b5fdd20f358e7d2090904640c1abe2c989f2cf1a1ac3b917171a71a1d"}}