{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:U4KTQPYENBH4IGQ3O7JUP7LHCI","short_pith_number":"pith:U4KTQPYE","canonical_record":{"source":{"id":"1607.06520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-21T22:26:20Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"039a1aa0b0a0b87dab40dd58a932b72861abd572f78d08f0049488c2475b3931","abstract_canon_sha256":"ca23eff23c68b924240a19bbf22c54e8642550622f924035d3d911e980e9b765"},"schema_version":"1.0"},"canonical_sha256":"a715383f04684fc41a1b77d347fd67123fce4ac9e1b6f0100f5a26b487141866","source":{"kind":"arxiv","id":"1607.06520","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.06520","created_at":"2026-05-18T01:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"1607.06520v1","created_at":"2026-05-18T01:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.06520","created_at":"2026-05-18T01:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"U4KTQPYENBH4","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"U4KTQPYENBH4IGQ3","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"U4KTQPYE","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:U4KTQPYENBH4IGQ3O7JUP7LHCI","target":"record","payload":{"canonical_record":{"source":{"id":"1607.06520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-21T22:26:20Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"039a1aa0b0a0b87dab40dd58a932b72861abd572f78d08f0049488c2475b3931","abstract_canon_sha256":"ca23eff23c68b924240a19bbf22c54e8642550622f924035d3d911e980e9b765"},"schema_version":"1.0"},"canonical_sha256":"a715383f04684fc41a1b77d347fd67123fce4ac9e1b6f0100f5a26b487141866","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:41.584852Z","signature_b64":"4rHOJuvCW+oDJM9PViokW6zv3DPGSVqjQk5sL2r2CrOtYVAAUBebsioquT6xRdmrm7FyDAvedP8jSYmc1990DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a715383f04684fc41a1b77d347fd67123fce4ac9e1b6f0100f5a26b487141866","last_reissued_at":"2026-05-18T01:10:41.584439Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:41.584439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.06520","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":"2026-05-18T01:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsXbrXQ6VaVlmIstPKKO7nDHAGTR3lPLgo+QKElYymTTaHdddM5ifHkOqumdvkjLoNbCsRHiA3rrkxYKG1OrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:01:30.098581Z"},"content_sha256":"5586e302fd926d7a2a95449509c1140c6f1f87b818dcf9182aa9fce59bdbf449","schema_version":"1.0","event_id":"sha256:5586e302fd926d7a2a95449509c1140c6f1f87b818dcf9182aa9fce59bdbf449"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:U4KTQPYENBH4IGQ3O7JUP7LHCI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Adam Kalai, James Zou, Kai-Wei Chang, Tolga Bolukbasi, Venkatesh Saligrama","submitted_at":"2016-07-21T22:26:20Z","abstract_excerpt":"The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings trained on Google News articles exhibit female/male gender stereotypes to a disturbing extent. This raises concerns because their widespread use, as we describe, often tends to amplify these biases. Geometrically, gender bias is first shown to be captured by a direction in the word emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.06520","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":""},"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":"2026-05-18T01:10:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkqv4ZZnhxKr1Tyv3evjU4kdO1991AsYsPsimP0ng1W77Ot0ESoz4EpP8hfo7IOjCWJAAXl1xdy/tHWq41VZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:01:30.098934Z"},"content_sha256":"943f3da439257f36212f297b679849f78b541e8802a0301cc63842e8ab263e40","schema_version":"1.0","event_id":"sha256:943f3da439257f36212f297b679849f78b541e8802a0301cc63842e8ab263e40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U4KTQPYENBH4IGQ3O7JUP7LHCI/bundle.json","state_url":"https://pith.science/pith/U4KTQPYENBH4IGQ3O7JUP7LHCI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U4KTQPYENBH4IGQ3O7JUP7LHCI/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":"2026-06-02T22:01:30Z","links":{"resolver":"https://pith.science/pith/U4KTQPYENBH4IGQ3O7JUP7LHCI","bundle":"https://pith.science/pith/U4KTQPYENBH4IGQ3O7JUP7LHCI/bundle.json","state":"https://pith.science/pith/U4KTQPYENBH4IGQ3O7JUP7LHCI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U4KTQPYENBH4IGQ3O7JUP7LHCI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:U4KTQPYENBH4IGQ3O7JUP7LHCI","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":"ca23eff23c68b924240a19bbf22c54e8642550622f924035d3d911e980e9b765","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-21T22:26:20Z","title_canon_sha256":"039a1aa0b0a0b87dab40dd58a932b72861abd572f78d08f0049488c2475b3931"},"schema_version":"1.0","source":{"id":"1607.06520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.06520","created_at":"2026-05-18T01:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"1607.06520v1","created_at":"2026-05-18T01:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.06520","created_at":"2026-05-18T01:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"U4KTQPYENBH4","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"U4KTQPYENBH4IGQ3","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"U4KTQPYE","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:943f3da439257f36212f297b679849f78b541e8802a0301cc63842e8ab263e40","target":"graph","created_at":"2026-05-18T01:10:41Z","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"},"paper":{"abstract_excerpt":"The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings trained on Google News articles exhibit female/male gender stereotypes to a disturbing extent. This raises concerns because their widespread use, as we describe, often tends to amplify these biases. Geometrically, gender bias is first shown to be captured by a direction in the word emb","authors_text":"Adam Kalai, James Zou, Kai-Wei Chang, Tolga Bolukbasi, Venkatesh Saligrama","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-21T22:26:20Z","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.06520","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":"sha256:5586e302fd926d7a2a95449509c1140c6f1f87b818dcf9182aa9fce59bdbf449","target":"record","created_at":"2026-05-18T01:10:41Z","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":"ca23eff23c68b924240a19bbf22c54e8642550622f924035d3d911e980e9b765","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-21T22:26:20Z","title_canon_sha256":"039a1aa0b0a0b87dab40dd58a932b72861abd572f78d08f0049488c2475b3931"},"schema_version":"1.0","source":{"id":"1607.06520","kind":"arxiv","version":1}},"canonical_sha256":"a715383f04684fc41a1b77d347fd67123fce4ac9e1b6f0100f5a26b487141866","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a715383f04684fc41a1b77d347fd67123fce4ac9e1b6f0100f5a26b487141866","first_computed_at":"2026-05-18T01:10:41.584439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:41.584439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4rHOJuvCW+oDJM9PViokW6zv3DPGSVqjQk5sL2r2CrOtYVAAUBebsioquT6xRdmrm7FyDAvedP8jSYmc1990DQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:41.584852Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.06520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5586e302fd926d7a2a95449509c1140c6f1f87b818dcf9182aa9fce59bdbf449","sha256:943f3da439257f36212f297b679849f78b541e8802a0301cc63842e8ab263e40"],"state_sha256":"fd8e5cd45f81016ba78e6f053ba4cbc30a4d304edb8d9705a7da645714665617"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kAawT4yYJbPD2WNbv18HmguwEl0Yek9Y45hGX+6fdaldS3XR7f+XzBczs+ttylDPhP/IAjUWYyuIMXDe3nlGAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:01:30.100935Z","bundle_sha256":"d158240b39ace24041b4e05c49bbf3a172a58ecc01b5f9ad932d53cde3750881"}}