{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:C3W57TQJI4EHIRN6WOQUW4L6I2","short_pith_number":"pith:C3W57TQJ","canonical_record":{"source":{"id":"2205.11374","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T15:05:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"287f51b07aef5ae1c08f61057aa646626199c7580ebce18184d9c487e94912a9","abstract_canon_sha256":"079f2ba305266d495b33ead5c6215f9a279fbfc21ab88a6a89bab878b807dd47"},"schema_version":"1.0"},"canonical_sha256":"16eddfce0947087445beb3a14b717e46ae451e7cd609fb417db815e2176435ea","source":{"kind":"arxiv","id":"2205.11374","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11374","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11374v1","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11374","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"pith_short_12","alias_value":"C3W57TQJI4EH","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"pith_short_16","alias_value":"C3W57TQJI4EHIRN6","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"pith_short_8","alias_value":"C3W57TQJ","created_at":"2026-07-05T04:25:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:C3W57TQJI4EHIRN6WOQUW4L6I2","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11374","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T15:05:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"287f51b07aef5ae1c08f61057aa646626199c7580ebce18184d9c487e94912a9","abstract_canon_sha256":"079f2ba305266d495b33ead5c6215f9a279fbfc21ab88a6a89bab878b807dd47"},"schema_version":"1.0"},"canonical_sha256":"16eddfce0947087445beb3a14b717e46ae451e7cd609fb417db815e2176435ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:36.705498Z","signature_b64":"dZhdyhFD5z3DRxJHWbBmeSFiA1SJFaina+FpisPu/jofu4u4A8DIe1IqDhiFjWtOokJwAGJiiUCc8sYyYfwRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16eddfce0947087445beb3a14b717e46ae451e7cd609fb417db815e2176435ea","last_reissued_at":"2026-07-05T04:25:36.705028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:36.705028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11374","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":"2026-07-05T04:25:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gqjQkcnC/QBLFTb/pyPH0x5yeeFIPbc2wHXdNCgNEH+CWiLCeWtvfSQDc4RLsLvuonFiO2/pILAYdSSdMvm7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:57:36.764274Z"},"content_sha256":"90525ef3bef955197e247554c43f5d6c81f1f772f1d4278794c5c13f4fc9a6c8","schema_version":"1.0","event_id":"sha256:90525ef3bef955197e247554c43f5d6c81f1f772f1d4278794c5c13f4fc9a6c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:C3W57TQJI4EHIRN6WOQUW4L6I2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Gilburt, Conrad Borchers, Dalia Sara Gala, Eduard Oravkin, Hannah Rose Kirk, Wilfried Bounsi, Yuki M. Asano","submitted_at":"2022-05-23T15:05:27Z","abstract_excerpt":"The growing capability and availability of generative language models has enabled a wide range of new downstream tasks. Academic research has identified, quantified and mitigated biases present in language models but is rarely tailored to downstream tasks where wider impact on individuals and society can be felt. In this work, we leverage one popular generative language model, GPT-3, with the goal of writing unbiased and realistic job advertisements. We first assess the bias and realism of zero-shot generated advertisements and compare them to real-world advertisements. We then evaluate prompt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11374","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/2205.11374/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":"2026-07-05T04:25:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svEkU2aE5sBSA+J32d5Num71OqvHEjqPWPEjcEdnAl0mpbt4vueHjV7DeZlvWYZd+ZhJUxezAYuksyBso9wEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:57:36.765233Z"},"content_sha256":"bf8c94268aca0cba51d2de7f6dd165eb461018eab00be838059c6cecf20e3db3","schema_version":"1.0","event_id":"sha256:bf8c94268aca0cba51d2de7f6dd165eb461018eab00be838059c6cecf20e3db3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C3W57TQJI4EHIRN6WOQUW4L6I2/bundle.json","state_url":"https://pith.science/pith/C3W57TQJI4EHIRN6WOQUW4L6I2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C3W57TQJI4EHIRN6WOQUW4L6I2/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":"2026-08-20T02:57:36Z","links":{"resolver":"https://pith.science/pith/C3W57TQJI4EHIRN6WOQUW4L6I2","bundle":"https://pith.science/pith/C3W57TQJI4EHIRN6WOQUW4L6I2/bundle.json","state":"https://pith.science/pith/C3W57TQJI4EHIRN6WOQUW4L6I2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C3W57TQJI4EHIRN6WOQUW4L6I2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:C3W57TQJI4EHIRN6WOQUW4L6I2","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":"079f2ba305266d495b33ead5c6215f9a279fbfc21ab88a6a89bab878b807dd47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T15:05:27Z","title_canon_sha256":"287f51b07aef5ae1c08f61057aa646626199c7580ebce18184d9c487e94912a9"},"schema_version":"1.0","source":{"id":"2205.11374","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11374","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11374v1","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11374","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"pith_short_12","alias_value":"C3W57TQJI4EH","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"pith_short_16","alias_value":"C3W57TQJI4EHIRN6","created_at":"2026-07-05T04:25:36Z"},{"alias_kind":"pith_short_8","alias_value":"C3W57TQJ","created_at":"2026-07-05T04:25:36Z"}],"graph_snapshots":[{"event_id":"sha256:bf8c94268aca0cba51d2de7f6dd165eb461018eab00be838059c6cecf20e3db3","target":"graph","created_at":"2026-07-05T04:25:36Z","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/2205.11374/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing capability and availability of generative language models has enabled a wide range of new downstream tasks. Academic research has identified, quantified and mitigated biases present in language models but is rarely tailored to downstream tasks where wider impact on individuals and society can be felt. In this work, we leverage one popular generative language model, GPT-3, with the goal of writing unbiased and realistic job advertisements. We first assess the bias and realism of zero-shot generated advertisements and compare them to real-world advertisements. We then evaluate prompt","authors_text":"Benjamin Gilburt, Conrad Borchers, Dalia Sara Gala, Eduard Oravkin, Hannah Rose Kirk, Wilfried Bounsi, Yuki M. Asano","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T15:05:27Z","title":"Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11374","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":"sha256:90525ef3bef955197e247554c43f5d6c81f1f772f1d4278794c5c13f4fc9a6c8","target":"record","created_at":"2026-07-05T04:25:36Z","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":"079f2ba305266d495b33ead5c6215f9a279fbfc21ab88a6a89bab878b807dd47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T15:05:27Z","title_canon_sha256":"287f51b07aef5ae1c08f61057aa646626199c7580ebce18184d9c487e94912a9"},"schema_version":"1.0","source":{"id":"2205.11374","kind":"arxiv","version":1}},"canonical_sha256":"16eddfce0947087445beb3a14b717e46ae451e7cd609fb417db815e2176435ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16eddfce0947087445beb3a14b717e46ae451e7cd609fb417db815e2176435ea","first_computed_at":"2026-07-05T04:25:36.705028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:25:36.705028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dZhdyhFD5z3DRxJHWbBmeSFiA1SJFaina+FpisPu/jofu4u4A8DIe1IqDhiFjWtOokJwAGJiiUCc8sYyYfwRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:25:36.705498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11374","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90525ef3bef955197e247554c43f5d6c81f1f772f1d4278794c5c13f4fc9a6c8","sha256:bf8c94268aca0cba51d2de7f6dd165eb461018eab00be838059c6cecf20e3db3"],"state_sha256":"f0654a1b15142c83a0908dcbaa132b2a0c5844c7bbfdb76197b7d8cf30be1461"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wb6OryRCqx4DVNu8QwwanYFvR2zPd/AoRKmIwX1PJD9UdbZEo3MR8Rwe2T509sTUvsPLNOtyJR1KGJlb5t0jDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T02:57:36.771967Z","bundle_sha256":"cf72f9ce264116fafdf5df374ba11efb1a96ca195ea4d4fed9d3126d3dbca732"}}