{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V7XAODUXBBHO7TZYRR2BBCSVZV","short_pith_number":"pith:V7XAODUX","schema_version":"1.0","canonical_sha256":"afee070e97084eefcf388c74108a55cd506ce99e9cccec2642463e06a712aedf","source":{"kind":"arxiv","id":"2307.04616","version":2},"attestation_state":"computed","paper":{"title":"MiVOLO: Multi-input Transformer for Age and Gender Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Irina Tolstykh, Maksim Kuprashevich","submitted_at":"2023-07-10T14:58:10Z","abstract_excerpt":"Age and gender recognition in the wild is a highly challenging task: apart from the variability of conditions, pose complexities, and varying image quality, there are cases where the face is partially or completely occluded. We present MiVOLO (Multi Input VOLO), a straightforward approach for age and gender estimation using the latest vision transformer. Our method integrates both tasks into a unified dual input/output model, leveraging not only facial information but also person image data. This improves the generalization ability of our model and enables it to deliver satisfactory results ev"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.04616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-10T14:58:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d91274ddb70eea120d4640265a019938d4cbe7c315bb10abf4beca9f17ac449f","abstract_canon_sha256":"9d23a546a4f9e1e895deeb4f06021b4b2a7f258fa27ea2fa57107dcc3b51c2e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:08.600156Z","signature_b64":"wy9JRtUeIx8qg21SMaaSoztaAopQNG1eaR432cSFgL03gv8ti6fq9v5tRzgs5qiA8cVdnlV7vdCLs9Z9/06eCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afee070e97084eefcf388c74108a55cd506ce99e9cccec2642463e06a712aedf","last_reissued_at":"2026-07-05T06:53:08.599709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:08.599709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MiVOLO: Multi-input Transformer for Age and Gender Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Irina Tolstykh, Maksim Kuprashevich","submitted_at":"2023-07-10T14:58:10Z","abstract_excerpt":"Age and gender recognition in the wild is a highly challenging task: apart from the variability of conditions, pose complexities, and varying image quality, there are cases where the face is partially or completely occluded. We present MiVOLO (Multi Input VOLO), a straightforward approach for age and gender estimation using the latest vision transformer. Our method integrates both tasks into a unified dual input/output model, leveraging not only facial information but also person image data. This improves the generalization ability of our model and enables it to deliver satisfactory results ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04616","kind":"arxiv","version":2},"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/2307.04616/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.04616","created_at":"2026-07-05T06:53:08.599766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.04616v2","created_at":"2026-07-05T06:53:08.599766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04616","created_at":"2026-07-05T06:53:08.599766+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7XAODUXBBHO","created_at":"2026-07-05T06:53:08.599766+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7XAODUXBBHO7TZY","created_at":"2026-07-05T06:53:08.599766+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7XAODUX","created_at":"2026-07-05T06:53:08.599766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.20209","citing_title":"DIPSER: A Dataset for In-Person Student Engagement Recognition in the Wild","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV","json":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV.json","graph_json":"https://pith.science/api/pith-number/V7XAODUXBBHO7TZYRR2BBCSVZV/graph.json","events_json":"https://pith.science/api/pith-number/V7XAODUXBBHO7TZYRR2BBCSVZV/events.json","paper":"https://pith.science/paper/V7XAODUX"},"agent_actions":{"view_html":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV","download_json":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV.json","view_paper":"https://pith.science/paper/V7XAODUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.04616&json=true","fetch_graph":"https://pith.science/api/pith-number/V7XAODUXBBHO7TZYRR2BBCSVZV/graph.json","fetch_events":"https://pith.science/api/pith-number/V7XAODUXBBHO7TZYRR2BBCSVZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV/action/storage_attestation","attest_author":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV/action/author_attestation","sign_citation":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV/action/citation_signature","submit_replication":"https://pith.science/pith/V7XAODUXBBHO7TZYRR2BBCSVZV/action/replication_record"}},"created_at":"2026-07-05T06:53:08.599766+00:00","updated_at":"2026-07-05T06:53:08.599766+00:00"}