{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CZQYIROWIAIAHK7KRLO4MRPIVA","short_pith_number":"pith:CZQYIROW","canonical_record":{"source":{"id":"2407.11933","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T17:23:41Z","cross_cats_sorted":[],"title_canon_sha256":"f8f023229047d999b523ee833f04ae218d78e71783963565d385d8227c80db51","abstract_canon_sha256":"ebc76753cf595f3b63f2e08353c0f446f4f4047ac404360556906581a9379495"},"schema_version":"1.0"},"canonical_sha256":"16618445d6401003abea8addc645e8a80611306dade4677f89bd9a4962c5519a","source":{"kind":"arxiv","id":"2407.11933","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11933","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11933v6","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11933","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"CZQYIROWIAIA","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"CZQYIROWIAIAHK7K","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"CZQYIROW","created_at":"2026-06-19T16:12:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CZQYIROWIAIAHK7KRLO4MRPIVA","target":"record","payload":{"canonical_record":{"source":{"id":"2407.11933","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T17:23:41Z","cross_cats_sorted":[],"title_canon_sha256":"f8f023229047d999b523ee833f04ae218d78e71783963565d385d8227c80db51","abstract_canon_sha256":"ebc76753cf595f3b63f2e08353c0f446f4f4047ac404360556906581a9379495"},"schema_version":"1.0"},"canonical_sha256":"16618445d6401003abea8addc645e8a80611306dade4677f89bd9a4962c5519a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:44.497620Z","signature_b64":"nrIC3sMez152I4YIK3vtFd3D+TJsqP0Yu/h9hWPQTyk5HuRcBtTWGVrpKtTerSDDhyxeCV5GHnC+MfXTfledAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16618445d6401003abea8addc645e8a80611306dade4677f89bd9a4962c5519a","last_reissued_at":"2026-06-19T16:12:44.497218Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:44.497218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.11933","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UYRwXwBZbcz4FqrMA4KzN4Zr7HnDfyvWP0GI3NqmBlHk4pbA47CfdwyQSB/uyECqTsn2cOgw5vgj9M2AYTkWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T03:02:09.909291Z"},"content_sha256":"985940d807c32982795c4128f33bb8b65eb3432a46f158a1ae4261cbeaf021b8","schema_version":"1.0","event_id":"sha256:985940d807c32982795c4128f33bb8b65eb3432a46f158a1ae4261cbeaf021b8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CZQYIROWIAIAHK7KRLO4MRPIVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fairness-Aware Multi-Group Target Detection in Online Discussion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A fairness-aware approach for detecting multiple target groups in social media posts reduces bias across demographic groups while maintaining strong predictive performance.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Maria De-Arteaga, Matthew Lease, Soumyajit Gupta","submitted_at":"2024-07-16T17:23:41Z","abstract_excerpt":"Target-group detection is the task of detecting which group(s) a piece of content is ``directed at or about''. Applications include targeted marketing, content recommendation, and group-specific content assessment. Key challenges include: 1) that a single post may target multiple groups; and 2) ensuring consistent detection accuracy across groups for fairness. In this work, we investigate fairness implications of target-group detection in the context of toxicity detection, where the perceived harm of a social media post often depends on which group(s) it targets. Because toxicity is highly con"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show our fairness-aware multi-group target detection approach both reduces bias across groups and shows strong predictive performance, surpassing existing fairness-aware baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The fairness constraints and evaluation metrics used accurately reflect real-world fairness requirements in toxicity detection across demographic groups (implied by the abstract's framing of the problem and results).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A fairness-aware multi-group target detection approach reduces bias across groups and outperforms existing fairness-aware baselines in toxicity detection tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A fairness-aware approach for detecting multiple target groups in social media posts reduces bias across demographic groups while maintaining strong predictive performance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8a38e67da924df0530aad0250155102c2fe0921aa53ddf235295a8c3920234cc"},"source":{"id":"2407.11933","kind":"arxiv","version":6},"verdict":{"id":"d480490a-a999-4e3c-a1af-defcabd9492d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-23T22:38:15.864448Z","strongest_claim":"We show our fairness-aware multi-group target detection approach both reduces bias across groups and shows strong predictive performance, surpassing existing fairness-aware baselines.","one_line_summary":"A fairness-aware multi-group target detection approach reduces bias across groups and outperforms existing fairness-aware baselines in toxicity detection tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The fairness constraints and evaluation metrics used accurately reflect real-world fairness requirements in toxicity detection across demographic groups (implied by the abstract's framing of the problem and results).","pith_extraction_headline":"A fairness-aware approach for detecting multiple target groups in social media posts reduces bias across demographic groups while maintaining strong predictive performance."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.11933/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":"d480490a-a999-4e3c-a1af-defcabd9492d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6VHlVtGcJGCK2bwtx6d/ouExOhje6v2/LFMGvSTA7jZvvyD5oHyETRTkfROv54Oo5n1eclbf2nmP4NwBeH7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T03:02:09.909769Z"},"content_sha256":"0cc8e354e9d32c17d7f87fa5c0f501b99f8f852069db0a8367945ed82f68697a","schema_version":"1.0","event_id":"sha256:0cc8e354e9d32c17d7f87fa5c0f501b99f8f852069db0a8367945ed82f68697a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZQYIROWIAIAHK7KRLO4MRPIVA/bundle.json","state_url":"https://pith.science/pith/CZQYIROWIAIAHK7KRLO4MRPIVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZQYIROWIAIAHK7KRLO4MRPIVA/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":"2026-06-26T03:02:09Z","links":{"resolver":"https://pith.science/pith/CZQYIROWIAIAHK7KRLO4MRPIVA","bundle":"https://pith.science/pith/CZQYIROWIAIAHK7KRLO4MRPIVA/bundle.json","state":"https://pith.science/pith/CZQYIROWIAIAHK7KRLO4MRPIVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZQYIROWIAIAHK7KRLO4MRPIVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CZQYIROWIAIAHK7KRLO4MRPIVA","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":"ebc76753cf595f3b63f2e08353c0f446f4f4047ac404360556906581a9379495","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T17:23:41Z","title_canon_sha256":"f8f023229047d999b523ee833f04ae218d78e71783963565d385d8227c80db51"},"schema_version":"1.0","source":{"id":"2407.11933","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11933","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11933v6","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11933","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"CZQYIROWIAIA","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"CZQYIROWIAIAHK7K","created_at":"2026-06-19T16:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"CZQYIROW","created_at":"2026-06-19T16:12:44Z"}],"graph_snapshots":[{"event_id":"sha256:0cc8e354e9d32c17d7f87fa5c0f501b99f8f852069db0a8367945ed82f68697a","target":"graph","created_at":"2026-06-19T16:12:44Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We show our fairness-aware multi-group target detection approach both reduces bias across groups and shows strong predictive performance, surpassing existing fairness-aware baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The fairness constraints and evaluation metrics used accurately reflect real-world fairness requirements in toxicity detection across demographic groups (implied by the abstract's framing of the problem and results)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A fairness-aware multi-group target detection approach reduces bias across groups and outperforms existing fairness-aware baselines in toxicity detection tasks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A fairness-aware approach for detecting multiple target groups in social media posts reduces bias across demographic groups while maintaining strong predictive performance."}],"snapshot_sha256":"8a38e67da924df0530aad0250155102c2fe0921aa53ddf235295a8c3920234cc"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.11933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target-group detection is the task of detecting which group(s) a piece of content is ``directed at or about''. Applications include targeted marketing, content recommendation, and group-specific content assessment. Key challenges include: 1) that a single post may target multiple groups; and 2) ensuring consistent detection accuracy across groups for fairness. In this work, we investigate fairness implications of target-group detection in the context of toxicity detection, where the perceived harm of a social media post often depends on which group(s) it targets. Because toxicity is highly con","authors_text":"Maria De-Arteaga, Matthew Lease, Soumyajit Gupta","cross_cats":[],"headline":"A fairness-aware approach for detecting multiple target groups in social media posts reduces bias across demographic groups while maintaining strong predictive performance.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T17:23:41Z","title":"Fairness-Aware Multi-Group Target Detection in Online Discussion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11933","kind":"arxiv","version":6},"verdict":{"created_at":"2026-05-23T22:38:15.864448Z","id":"d480490a-a999-4e3c-a1af-defcabd9492d","model_set":{"reader":"grok-4.3"},"one_line_summary":"A fairness-aware multi-group target detection approach reduces bias across groups and outperforms existing fairness-aware baselines in toxicity detection tasks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A fairness-aware approach for detecting multiple target groups in social media posts reduces bias across demographic groups while maintaining strong predictive performance.","strongest_claim":"We show our fairness-aware multi-group target detection approach both reduces bias across groups and shows strong predictive performance, surpassing existing fairness-aware baselines.","weakest_assumption":"The fairness constraints and evaluation metrics used accurately reflect real-world fairness requirements in toxicity detection across demographic groups (implied by the abstract's framing of the problem and results)."}},"verdict_id":"d480490a-a999-4e3c-a1af-defcabd9492d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:985940d807c32982795c4128f33bb8b65eb3432a46f158a1ae4261cbeaf021b8","target":"record","created_at":"2026-06-19T16:12:44Z","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":"ebc76753cf595f3b63f2e08353c0f446f4f4047ac404360556906581a9379495","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T17:23:41Z","title_canon_sha256":"f8f023229047d999b523ee833f04ae218d78e71783963565d385d8227c80db51"},"schema_version":"1.0","source":{"id":"2407.11933","kind":"arxiv","version":6}},"canonical_sha256":"16618445d6401003abea8addc645e8a80611306dade4677f89bd9a4962c5519a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16618445d6401003abea8addc645e8a80611306dade4677f89bd9a4962c5519a","first_computed_at":"2026-06-19T16:12:44.497218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:44.497218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nrIC3sMez152I4YIK3vtFd3D+TJsqP0Yu/h9hWPQTyk5HuRcBtTWGVrpKtTerSDDhyxeCV5GHnC+MfXTfledAQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:44.497620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11933","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:985940d807c32982795c4128f33bb8b65eb3432a46f158a1ae4261cbeaf021b8","sha256:0cc8e354e9d32c17d7f87fa5c0f501b99f8f852069db0a8367945ed82f68697a"],"state_sha256":"acdc9e97f59abee5fb1f6c0f871b0838c22d368f76db6093b45802be90dfaa02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wAh9KBpepEl7N+WGNqmLQEBuaXysLnLTjjjRVFn8p3tFUDpQpmNXT6gCqapEfYz+jpYyXTxuotg5l2qspRXvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T03:02:09.912017Z","bundle_sha256":"13d402768d4e740653626dc87fc46f40d323c1268249d3f254ffdcc42ddfbbd1"}}