{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3QPZ3RBFEMGESGKQ6EAAQJ4ZJP","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":"6b6fb16ef409a5a23b4f155d0f8c577eeb1cb670468156a7d94ed0aa26d667fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-08T11:22:18Z","title_canon_sha256":"5341441c34dac2ffac31bba2159269853de938b29d8593983a8505b1f8ffadc3"},"schema_version":"1.0","source":{"id":"2604.06961","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.06961","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"arxiv_version","alias_value":"2604.06961v2","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.06961","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_12","alias_value":"3QPZ3RBFEMGE","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_16","alias_value":"3QPZ3RBFEMGESGKQ","created_at":"2026-06-11T01:10:35Z"},{"alias_kind":"pith_short_8","alias_value":"3QPZ3RBF","created_at":"2026-06-11T01:10:35Z"}],"graph_snapshots":[{"event_id":"sha256:f166e29032ce0d7e157a32d96d42b723250c7fc915ca4ab44d85f588986d6366","target":"graph","created_at":"2026-06-11T01:10:35Z","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":"Notably, after accounting for these confounders, we show that performance disparities across gender and race vanish. However, we identify a statistically significant age-related effect, with higher biases observed for older individuals."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The controlled statistical methodology successfully disentangles demographic effects from confounding visual factors such as head pose and image resolution without residual interactions or dataset-specific artifacts that could mask or create apparent biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"After accounting for confounding factors like head pose and resolution, demographic biases in facial landmark detection largely vanish except for a statistically significant age effect disadvantaging older people."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"After controlling for head pose and image resolution, facial landmark detectors show no bias by gender or race but retain an age-related bias."}],"snapshot_sha256":"593f59561054f888fee82e9e42a799d236b9e6a723ec0e1bdf151c5a389afdbe"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.06961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fairness in human-robot interaction critically depends on the reliability of the perceptual models that enable robots to interpret human behavior. While demographic biases have been widely studied in high-level facial analysis tasks, their presence in facial landmark detection remains unexplored. In this paper, we conduct a systematic audit of demographic bias in this task, analyzing the age, gender, and race biases. To this end, we introduce a controlled statistical methodology to disentangle demographic effects from confounding visual factors. Our analysis demonstrates that visual confounder","authors_text":"Jos\\'e M. Buenaposada, Luis Baumela, Pablo Parte, Roberto Valle","cross_cats":[],"headline":"After controlling for head pose and image resolution, facial landmark detectors show no bias by gender or race but retain an age-related bias.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-08T11:22:18Z","title":"Auditing Demographic Bias in Facial Landmark Detection for Fair Human-Robot Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.06961","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T18:02:22.400510Z","id":"b5d7b65c-873f-4ea3-a7b3-0bedc8e9068c","model_set":{"reader":"grok-4.3"},"one_line_summary":"After accounting for confounding factors like head pose and resolution, demographic biases in facial landmark detection largely vanish except for a statistically significant age effect disadvantaging older people.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"After controlling for head pose and image resolution, facial landmark detectors show no bias by gender or race but retain an age-related bias.","strongest_claim":"Notably, after accounting for these confounders, we show that performance disparities across gender and race vanish. However, we identify a statistically significant age-related effect, with higher biases observed for older individuals.","weakest_assumption":"The controlled statistical methodology successfully disentangles demographic effects from confounding visual factors such as head pose and image resolution without residual interactions or dataset-specific artifacts that could mask or create apparent biases."}},"verdict_id":"b5d7b65c-873f-4ea3-a7b3-0bedc8e9068c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:634dc8aa3e5bffc5fd893b5ac9e961fac3e4aa0f3166072493ede8b57911fd01","target":"record","created_at":"2026-06-11T01:10:35Z","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":"6b6fb16ef409a5a23b4f155d0f8c577eeb1cb670468156a7d94ed0aa26d667fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-08T11:22:18Z","title_canon_sha256":"5341441c34dac2ffac31bba2159269853de938b29d8593983a8505b1f8ffadc3"},"schema_version":"1.0","source":{"id":"2604.06961","kind":"arxiv","version":2}},"canonical_sha256":"dc1f9dc425230c491950f1000827994bdd3388dfd07e11e773ae934291741c17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc1f9dc425230c491950f1000827994bdd3388dfd07e11e773ae934291741c17","first_computed_at":"2026-06-11T01:10:35.796627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:35.796627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qqtp8EvJYgW8pRhDVN25rhVdTPcGQzFJduO/uabwZmdgOe1P/PDN0AnStKmuRUb2sqCto2k0WUrM+RgyjwLhCA==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:35.797722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.06961","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:634dc8aa3e5bffc5fd893b5ac9e961fac3e4aa0f3166072493ede8b57911fd01","sha256:f166e29032ce0d7e157a32d96d42b723250c7fc915ca4ab44d85f588986d6366"],"state_sha256":"489e3ffdddee48702d0dd5a7f520971a9fdc0581a22637273babb7e541f2dd48"}