{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EL7A4AVHMPJJTNOGLRXZFEQMTT","short_pith_number":"pith:EL7A4AVH","canonical_record":{"source":{"id":"2306.05500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-03T21:39:07Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"c26f0b21269c30297b42848227db34fdb074a2eba3f13823e7a3bbb970c20d31","abstract_canon_sha256":"b7d139db5151f8add55ed533e250579bab0778eec86a27f01f4bd812b123f4e9"},"schema_version":"1.0"},"canonical_sha256":"22fe0e02a763d299b5c65c6f92920c9cd149671a0bc87a41bf8c01706621bd3a","source":{"kind":"arxiv","id":"2306.05500","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05500","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05500v1","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05500","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"EL7A4AVHMPJJ","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"EL7A4AVHMPJJTNOG","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"EL7A4AVH","created_at":"2026-07-05T06:19:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EL7A4AVHMPJJTNOGLRXZFEQMTT","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-03T21:39:07Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"c26f0b21269c30297b42848227db34fdb074a2eba3f13823e7a3bbb970c20d31","abstract_canon_sha256":"b7d139db5151f8add55ed533e250579bab0778eec86a27f01f4bd812b123f4e9"},"schema_version":"1.0"},"canonical_sha256":"22fe0e02a763d299b5c65c6f92920c9cd149671a0bc87a41bf8c01706621bd3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:06.827404Z","signature_b64":"dGmdbuO4/O/M57vzk1YdNl5QCgPb6L9K4O9XPd1oG6LLjWNf3f/y9+FWZPe2gjoKnPYhWgiMCLj7EosuhmohDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22fe0e02a763d299b5c65c6f92920c9cd149671a0bc87a41bf8c01706621bd3a","last_reissued_at":"2026-07-05T06:19:06.826919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:06.826919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05500","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":"2026-07-05T06:19:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fWa7dx4EOKSD41L3Y4gvIWWY1FCikK4Pg+ZPj05QC94YhBwlSipjbbhl0lBrja2lJM9YnKrmfj1jc9H+nSJPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:00:37.074669Z"},"content_sha256":"909fa75caab9f2308ddc04f3b6493017dc675e4cd345fbac8c1c5ce6a9800dbd","schema_version":"1.0","event_id":"sha256:909fa75caab9f2308ddc04f3b6493017dc675e4cd345fbac8c1c5ce6a9800dbd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EL7A4AVHMPJJTNOGLRXZFEQMTT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word-Level Explanations for Analyzing Bias in Text-to-Image Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Lin, Himabindu Lakkaraju, Lucas Monteiro Paes, Sree Harsha Tanneru, Suraj Srinivas","submitted_at":"2023-06-03T21:39:07Z","abstract_excerpt":"Text-to-image models take a sentence (i.e., prompt) and generate images associated with this input prompt. These models have created award wining-art, videos, and even synthetic datasets. However, text-to-image (T2I) models can generate images that underrepresent minorities based on race and sex. This paper investigates which word in the input prompt is responsible for bias in generated images. We introduce a method for computing scores for each word in the prompt; these scores represent its influence on biases in the model's output. Our method follows the principle of \\emph{explaining by remo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05500","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/2306.05500/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":"2026-07-05T06:19:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T5IxtI57KFw2GV2iG6/y3fN9WhNmv1fsXINzTdM3z/P6er0tWYPxGuzz79GBQlnzWG1TnbTUc6gvbVkUJBX2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:00:37.075189Z"},"content_sha256":"f0fad6d951b8ba3eb63f6819e5c4b6b4ef63945ab147e100db0bd1213e46d1c0","schema_version":"1.0","event_id":"sha256:f0fad6d951b8ba3eb63f6819e5c4b6b4ef63945ab147e100db0bd1213e46d1c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EL7A4AVHMPJJTNOGLRXZFEQMTT/bundle.json","state_url":"https://pith.science/pith/EL7A4AVHMPJJTNOGLRXZFEQMTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EL7A4AVHMPJJTNOGLRXZFEQMTT/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":"2026-08-05T04:00:37Z","links":{"resolver":"https://pith.science/pith/EL7A4AVHMPJJTNOGLRXZFEQMTT","bundle":"https://pith.science/pith/EL7A4AVHMPJJTNOGLRXZFEQMTT/bundle.json","state":"https://pith.science/pith/EL7A4AVHMPJJTNOGLRXZFEQMTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EL7A4AVHMPJJTNOGLRXZFEQMTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EL7A4AVHMPJJTNOGLRXZFEQMTT","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":"b7d139db5151f8add55ed533e250579bab0778eec86a27f01f4bd812b123f4e9","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-03T21:39:07Z","title_canon_sha256":"c26f0b21269c30297b42848227db34fdb074a2eba3f13823e7a3bbb970c20d31"},"schema_version":"1.0","source":{"id":"2306.05500","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05500","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05500v1","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05500","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"pith_short_12","alias_value":"EL7A4AVHMPJJ","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"pith_short_16","alias_value":"EL7A4AVHMPJJTNOG","created_at":"2026-07-05T06:19:06Z"},{"alias_kind":"pith_short_8","alias_value":"EL7A4AVH","created_at":"2026-07-05T06:19:06Z"}],"graph_snapshots":[{"event_id":"sha256:f0fad6d951b8ba3eb63f6819e5c4b6b4ef63945ab147e100db0bd1213e46d1c0","target":"graph","created_at":"2026-07-05T06:19:06Z","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/2306.05500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image models take a sentence (i.e., prompt) and generate images associated with this input prompt. These models have created award wining-art, videos, and even synthetic datasets. However, text-to-image (T2I) models can generate images that underrepresent minorities based on race and sex. This paper investigates which word in the input prompt is responsible for bias in generated images. We introduce a method for computing scores for each word in the prompt; these scores represent its influence on biases in the model's output. Our method follows the principle of \\emph{explaining by remo","authors_text":"Alexander Lin, Himabindu Lakkaraju, Lucas Monteiro Paes, Sree Harsha Tanneru, Suraj Srinivas","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-03T21:39:07Z","title":"Word-Level Explanations for Analyzing Bias in Text-to-Image Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05500","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":"sha256:909fa75caab9f2308ddc04f3b6493017dc675e4cd345fbac8c1c5ce6a9800dbd","target":"record","created_at":"2026-07-05T06:19:06Z","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":"b7d139db5151f8add55ed533e250579bab0778eec86a27f01f4bd812b123f4e9","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-03T21:39:07Z","title_canon_sha256":"c26f0b21269c30297b42848227db34fdb074a2eba3f13823e7a3bbb970c20d31"},"schema_version":"1.0","source":{"id":"2306.05500","kind":"arxiv","version":1}},"canonical_sha256":"22fe0e02a763d299b5c65c6f92920c9cd149671a0bc87a41bf8c01706621bd3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22fe0e02a763d299b5c65c6f92920c9cd149671a0bc87a41bf8c01706621bd3a","first_computed_at":"2026-07-05T06:19:06.826919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:06.826919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dGmdbuO4/O/M57vzk1YdNl5QCgPb6L9K4O9XPd1oG6LLjWNf3f/y9+FWZPe2gjoKnPYhWgiMCLj7EosuhmohDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:06.827404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05500","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:909fa75caab9f2308ddc04f3b6493017dc675e4cd345fbac8c1c5ce6a9800dbd","sha256:f0fad6d951b8ba3eb63f6819e5c4b6b4ef63945ab147e100db0bd1213e46d1c0"],"state_sha256":"54f32dafcf087946fd2ac6b19d92c82150000e7efdf5f2e76529ba46f1bb07d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zCW7e8id3Vk4ngcRDVp6qGwxl5RuUrS9OcSlwHWLNGuOFgKgU2Jq0TWanoLcS/b0LsELSWMMO67XT+QQA5bfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:00:37.079523Z","bundle_sha256":"f7bde33cba4b27bfaa22a11e4406209dc4c03224e9cb52ef122257792b3bda12"}}