{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UYX7CVXVZ77T46RDELA6C62ZH7","short_pith_number":"pith:UYX7CVXV","canonical_record":{"source":{"id":"2203.09192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T09:29:50Z","cross_cats_sorted":[],"title_canon_sha256":"6bf8e3510b292367e23b496a7e5caceb0bdaf54f6c19c25e3aa520e15b2af05c","abstract_canon_sha256":"5dc4abc9245e43cdfb5f5f76ff8b8ed866f02ed240367a30b3397643f3792f87"},"schema_version":"1.0"},"canonical_sha256":"a62ff156f5cfff3e7a2322c1e17b593fd8bdf2dbd4a2c27767fb447ab5df8440","source":{"kind":"arxiv","id":"2203.09192","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09192","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09192v1","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09192","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"UYX7CVXVZ77T","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"UYX7CVXVZ77T46RD","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"UYX7CVXV","created_at":"2026-07-05T04:06:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UYX7CVXVZ77T46RDELA6C62ZH7","target":"record","payload":{"canonical_record":{"source":{"id":"2203.09192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T09:29:50Z","cross_cats_sorted":[],"title_canon_sha256":"6bf8e3510b292367e23b496a7e5caceb0bdaf54f6c19c25e3aa520e15b2af05c","abstract_canon_sha256":"5dc4abc9245e43cdfb5f5f76ff8b8ed866f02ed240367a30b3397643f3792f87"},"schema_version":"1.0"},"canonical_sha256":"a62ff156f5cfff3e7a2322c1e17b593fd8bdf2dbd4a2c27767fb447ab5df8440","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:08.627007Z","signature_b64":"pAiLsHKFJjDdjAA6tImCqG3XulI6rc8rlQC88Qgtkdtso6WhAYxqcqyEEq6q+T/4K8BGSSalc/duhbWvbZ5sDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a62ff156f5cfff3e7a2322c1e17b593fd8bdf2dbd4a2c27767fb447ab5df8440","last_reissued_at":"2026-07-05T04:06:08.626489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:08.626489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.09192","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":"2026-07-05T04:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L3tHIpXxa1wM1MYBCN/KQmVZdyHUU4w84I90PdF0mlj1ugTUSHf9Q/v6wPKmihd8BZV8KVHx9xtCq0vitU8rCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T22:04:05.765145Z"},"content_sha256":"6398c695cf1c10add412624f843c4ee9c64b24e0725601a503402dd338b25d76","schema_version":"1.0","event_id":"sha256:6398c695cf1c10add412624f843c4ee9c64b24e0725601a503402dd338b25d76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UYX7CVXVZ77T46RDELA6C62ZH7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debora Nozza, Dirk Hovy, Elena Baralis, Giuseppe Attanasio","submitted_at":"2022-03-17T09:29:50Z","abstract_excerpt":"Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms like gay, or women, resulting in false positives, severe unintended bias, and lower performance. Most mitigation techniques use lists of identity terms or samples from the target domain during training. However, this approach requires a-priori knowledge and introduces further bias if important terms are neglected. Instead, we propose a knowledge-fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09192","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/2203.09192/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":"2026-07-05T04:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28Vh2V6hMPvsAxb2xqhRd8uTMMgSagBOANbMEdrKCLRPNr0i88xUgYioSQrK4Y4/D81/VLJjyf/XYchBIQcbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T22:04:05.765474Z"},"content_sha256":"a0fcb89efb9b8c71166fa8fb7fcc71c70278aac4258a5ed0b09dc748a755e29e","schema_version":"1.0","event_id":"sha256:a0fcb89efb9b8c71166fa8fb7fcc71c70278aac4258a5ed0b09dc748a755e29e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYX7CVXVZ77T46RDELA6C62ZH7/bundle.json","state_url":"https://pith.science/pith/UYX7CVXVZ77T46RDELA6C62ZH7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYX7CVXVZ77T46RDELA6C62ZH7/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":"2026-08-13T22:04:05Z","links":{"resolver":"https://pith.science/pith/UYX7CVXVZ77T46RDELA6C62ZH7","bundle":"https://pith.science/pith/UYX7CVXVZ77T46RDELA6C62ZH7/bundle.json","state":"https://pith.science/pith/UYX7CVXVZ77T46RDELA6C62ZH7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYX7CVXVZ77T46RDELA6C62ZH7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UYX7CVXVZ77T46RDELA6C62ZH7","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":"5dc4abc9245e43cdfb5f5f76ff8b8ed866f02ed240367a30b3397643f3792f87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T09:29:50Z","title_canon_sha256":"6bf8e3510b292367e23b496a7e5caceb0bdaf54f6c19c25e3aa520e15b2af05c"},"schema_version":"1.0","source":{"id":"2203.09192","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09192","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09192v1","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09192","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"UYX7CVXVZ77T","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"UYX7CVXVZ77T46RD","created_at":"2026-07-05T04:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"UYX7CVXV","created_at":"2026-07-05T04:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:a0fcb89efb9b8c71166fa8fb7fcc71c70278aac4258a5ed0b09dc748a755e29e","target":"graph","created_at":"2026-07-05T04:06:08Z","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/2203.09192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by identity terms like gay, or women, resulting in false positives, severe unintended bias, and lower performance. Most mitigation techniques use lists of identity terms or samples from the target domain during training. However, this approach requires a-priori knowledge and introduces further bias if important terms are neglected. Instead, we propose a knowledge-fr","authors_text":"Debora Nozza, Dirk Hovy, Elena Baralis, Giuseppe Attanasio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T09:29:50Z","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09192","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":"sha256:6398c695cf1c10add412624f843c4ee9c64b24e0725601a503402dd338b25d76","target":"record","created_at":"2026-07-05T04:06:08Z","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":"5dc4abc9245e43cdfb5f5f76ff8b8ed866f02ed240367a30b3397643f3792f87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T09:29:50Z","title_canon_sha256":"6bf8e3510b292367e23b496a7e5caceb0bdaf54f6c19c25e3aa520e15b2af05c"},"schema_version":"1.0","source":{"id":"2203.09192","kind":"arxiv","version":1}},"canonical_sha256":"a62ff156f5cfff3e7a2322c1e17b593fd8bdf2dbd4a2c27767fb447ab5df8440","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a62ff156f5cfff3e7a2322c1e17b593fd8bdf2dbd4a2c27767fb447ab5df8440","first_computed_at":"2026-07-05T04:06:08.626489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:08.626489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pAiLsHKFJjDdjAA6tImCqG3XulI6rc8rlQC88Qgtkdtso6WhAYxqcqyEEq6q+T/4K8BGSSalc/duhbWvbZ5sDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:08.627007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.09192","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6398c695cf1c10add412624f843c4ee9c64b24e0725601a503402dd338b25d76","sha256:a0fcb89efb9b8c71166fa8fb7fcc71c70278aac4258a5ed0b09dc748a755e29e"],"state_sha256":"7e7580b8067b1c058ee94dd296783307a880653f691a6d7c9ba3a56a74bc9b96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2bbUayPf8+4naLhLs5iZa981b05VZ4AV9k084LBR4/2RglthuCFkr+RGuczf8NKsGd2md1YhQLoCpbyBScjUBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T22:04:05.807930Z","bundle_sha256":"d8da7af4f7c1f8de7c8a46bacdb760dff4fc6b1343d5dfbccc1bfe1e215df817"}}