{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XOYUI64A5KZP5OJTGF6L5FJYQL","short_pith_number":"pith:XOYUI64A","canonical_record":{"source":{"id":"2407.21058","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T23:09:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7843d370edfaf5fdc9817901f7b606a2a861cbbda4a74261ba9c997083bf6c59","abstract_canon_sha256":"79d50fd1d6cc02869cd8576ee824d596add12146c78182f809d1743387197b6c"},"schema_version":"1.0"},"canonical_sha256":"bbb1447b80eab2feb933317cbe953882d4fb742d5606d6f2a23aab3eb0a43593","source":{"kind":"arxiv","id":"2407.21058","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21058","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21058v1","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21058","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"pith_short_12","alias_value":"XOYUI64A5KZP","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"pith_short_16","alias_value":"XOYUI64A5KZP5OJT","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"pith_short_8","alias_value":"XOYUI64A","created_at":"2026-07-05T08:50:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XOYUI64A5KZP5OJTGF6L5FJYQL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.21058","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T23:09:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7843d370edfaf5fdc9817901f7b606a2a861cbbda4a74261ba9c997083bf6c59","abstract_canon_sha256":"79d50fd1d6cc02869cd8576ee824d596add12146c78182f809d1743387197b6c"},"schema_version":"1.0"},"canonical_sha256":"bbb1447b80eab2feb933317cbe953882d4fb742d5606d6f2a23aab3eb0a43593","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:33.362118Z","signature_b64":"KAmaNjunYOGCAkLigyUfNW9aH90LjfmUJcfyTvgJ66cuK1XsPQ9u6SQg+2P8X+vDHWs5KFTBV31xLeWIYydoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbb1447b80eab2feb933317cbe953882d4fb742d5606d6f2a23aab3eb0a43593","last_reissued_at":"2026-07-05T08:50:33.361261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:33.361261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.21058","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":"2026-07-05T08:50:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNOv52jhflr9CrJJ9RqouVkAwzWxQp+6XKFNxq/xPiuY0z+ldSGAh8v6Fi5/ih1EaL0HGTm44VBtm6EKA2N5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:34:56.573797Z"},"content_sha256":"c0cdf32e700eac8bcb05b3e5efa8c8f49469737c4de34275caad03c559b4cdf9","schema_version":"1.0","event_id":"sha256:c0cdf32e700eac8bcb05b3e5efa8c8f49469737c4de34275caad03c559b4cdf9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XOYUI64A5KZP5OJTGF6L5FJYQL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ari Kobren, Michael Wick, Muhammad Ali, Qinlan Shen, Swetasudha Panda","submitted_at":"2024-07-25T23:09:33Z","abstract_excerpt":"In the current landscape of language model research, larger models, larger datasets and more compute seems to be the only way to advance towards intelligence. While there have been extensive studies of scaling laws and models' scaling behaviors, the effect of scale on a model's social biases and stereotyping tendencies has received less attention. In this study, we explore the influence of model scale and pre-training data on its learnt social biases. We focus on BERT -- an extremely popular language model -- and investigate biases as they show up during language modeling (upstream), as well a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21058","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/2407.21058/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":"2026-07-05T08:50:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8dnnPwmXUBV4UFgfi24Y0nhxR/xsMmOz1BoEJdCB/9AQRENH3wVqt36nMsFhd4P7G3vdKfIl2IcR9kwx+NdOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:34:56.574179Z"},"content_sha256":"9dcaf3035451200009fd4ab9e7b3c224818dea6a216b7da796e31c7fb5e20eb3","schema_version":"1.0","event_id":"sha256:9dcaf3035451200009fd4ab9e7b3c224818dea6a216b7da796e31c7fb5e20eb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOYUI64A5KZP5OJTGF6L5FJYQL/bundle.json","state_url":"https://pith.science/pith/XOYUI64A5KZP5OJTGF6L5FJYQL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOYUI64A5KZP5OJTGF6L5FJYQL/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":"2026-08-13T15:34:56Z","links":{"resolver":"https://pith.science/pith/XOYUI64A5KZP5OJTGF6L5FJYQL","bundle":"https://pith.science/pith/XOYUI64A5KZP5OJTGF6L5FJYQL/bundle.json","state":"https://pith.science/pith/XOYUI64A5KZP5OJTGF6L5FJYQL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOYUI64A5KZP5OJTGF6L5FJYQL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XOYUI64A5KZP5OJTGF6L5FJYQL","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":"79d50fd1d6cc02869cd8576ee824d596add12146c78182f809d1743387197b6c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T23:09:33Z","title_canon_sha256":"7843d370edfaf5fdc9817901f7b606a2a861cbbda4a74261ba9c997083bf6c59"},"schema_version":"1.0","source":{"id":"2407.21058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21058","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21058v1","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21058","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"pith_short_12","alias_value":"XOYUI64A5KZP","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"pith_short_16","alias_value":"XOYUI64A5KZP5OJT","created_at":"2026-07-05T08:50:33Z"},{"alias_kind":"pith_short_8","alias_value":"XOYUI64A","created_at":"2026-07-05T08:50:33Z"}],"graph_snapshots":[{"event_id":"sha256:9dcaf3035451200009fd4ab9e7b3c224818dea6a216b7da796e31c7fb5e20eb3","target":"graph","created_at":"2026-07-05T08:50:33Z","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/2407.21058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the current landscape of language model research, larger models, larger datasets and more compute seems to be the only way to advance towards intelligence. While there have been extensive studies of scaling laws and models' scaling behaviors, the effect of scale on a model's social biases and stereotyping tendencies has received less attention. In this study, we explore the influence of model scale and pre-training data on its learnt social biases. We focus on BERT -- an extremely popular language model -- and investigate biases as they show up during language modeling (upstream), as well a","authors_text":"Ari Kobren, Michael Wick, Muhammad Ali, Qinlan Shen, Swetasudha Panda","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T23:09:33Z","title":"Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21058","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:c0cdf32e700eac8bcb05b3e5efa8c8f49469737c4de34275caad03c559b4cdf9","target":"record","created_at":"2026-07-05T08:50:33Z","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":"79d50fd1d6cc02869cd8576ee824d596add12146c78182f809d1743387197b6c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T23:09:33Z","title_canon_sha256":"7843d370edfaf5fdc9817901f7b606a2a861cbbda4a74261ba9c997083bf6c59"},"schema_version":"1.0","source":{"id":"2407.21058","kind":"arxiv","version":1}},"canonical_sha256":"bbb1447b80eab2feb933317cbe953882d4fb742d5606d6f2a23aab3eb0a43593","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbb1447b80eab2feb933317cbe953882d4fb742d5606d6f2a23aab3eb0a43593","first_computed_at":"2026-07-05T08:50:33.361261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:33.361261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KAmaNjunYOGCAkLigyUfNW9aH90LjfmUJcfyTvgJ66cuK1XsPQ9u6SQg+2P8X+vDHWs5KFTBV31xLeWIYydoCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:33.362118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0cdf32e700eac8bcb05b3e5efa8c8f49469737c4de34275caad03c559b4cdf9","sha256:9dcaf3035451200009fd4ab9e7b3c224818dea6a216b7da796e31c7fb5e20eb3"],"state_sha256":"07124de35342396bef7a3b6f9addbaf902e3bf115c4f1c613c4b2a9bd962d1e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"egDKTWarcl/WmF3/uKaEW6Wj9xYqil90Us8H9YfapckA24S8QcOFmtYlojkQXPefT0OKwSci9k/0PFfG5sPlDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:34:56.577222Z","bundle_sha256":"82ddf3514c09ccc24f01b02745ecf5da203a9b14cbdbd819c8555011adaeab8a"}}