{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DJOIS676WVW3XNDRNOP45C6ULE","short_pith_number":"pith:DJOIS676","schema_version":"1.0","canonical_sha256":"1a5c897bfeb56dbbb4716b9fce8bd4592ca85921169263a8275104d66b684771","source":{"kind":"arxiv","id":"2410.22768","version":1},"attestation_state":"computed","paper":{"title":"Emergence of Human-Like Attention in Self-Supervised Vision Transformers: an eye-tracking study","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.NC","authors_text":"Hirosato Akahoshi, Shigeru Kitazawa, Takuto Yamamoto","submitted_at":"2024-10-30T07:37:19Z","abstract_excerpt":"Many models of visual attention have been proposed so far. Traditional bottom-up models, like saliency models, fail to replicate human gaze patterns, and deep gaze prediction models lack biological plausibility due to their reliance on supervised learning. Vision Transformers (ViTs), with their self-attention mechanisms, offer a new approach but often produce dispersed attention patterns if trained with supervised learning. This study explores whether self-supervised DINO (self-DIstillation with NO labels) training enables ViTs to develop attention mechanisms resembling human visual attention."},"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":"2410.22768","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"q-bio.NC","submitted_at":"2024-10-30T07:37:19Z","cross_cats_sorted":[],"title_canon_sha256":"38776cf2e1a38d31b96b1448132cdb595795d700e0dfba33693b397c09a4b575","abstract_canon_sha256":"cb82517bf92fb2f1f04f4a0f1bd65843b538b36ee7f15248530288cd796907a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:02.025711Z","signature_b64":"sNvDYmj4zkcDZD6GutH1Ao23xghHbNHBLb/Ej9OyfT9cA2ClcYhDT+mcFrJffsg0sazBPYpslp2Ec+DnnvZhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a5c897bfeb56dbbb4716b9fce8bd4592ca85921169263a8275104d66b684771","last_reissued_at":"2026-07-05T11:10:02.025196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:02.025196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emergence of Human-Like Attention in Self-Supervised Vision Transformers: an eye-tracking study","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.NC","authors_text":"Hirosato Akahoshi, Shigeru Kitazawa, Takuto Yamamoto","submitted_at":"2024-10-30T07:37:19Z","abstract_excerpt":"Many models of visual attention have been proposed so far. Traditional bottom-up models, like saliency models, fail to replicate human gaze patterns, and deep gaze prediction models lack biological plausibility due to their reliance on supervised learning. Vision Transformers (ViTs), with their self-attention mechanisms, offer a new approach but often produce dispersed attention patterns if trained with supervised learning. This study explores whether self-supervised DINO (self-DIstillation with NO labels) training enables ViTs to develop attention mechanisms resembling human visual attention."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22768","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/2410.22768/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":"2410.22768","created_at":"2026-07-05T11:10:02.025262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22768v1","created_at":"2026-07-05T11:10:02.025262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22768","created_at":"2026-07-05T11:10:02.025262+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJOIS676WVW3","created_at":"2026-07-05T11:10:02.025262+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJOIS676WVW3XNDR","created_at":"2026-07-05T11:10:02.025262+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJOIS676","created_at":"2026-07-05T11:10:02.025262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07397","citing_title":"Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE","json":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE.json","graph_json":"https://pith.science/api/pith-number/DJOIS676WVW3XNDRNOP45C6ULE/graph.json","events_json":"https://pith.science/api/pith-number/DJOIS676WVW3XNDRNOP45C6ULE/events.json","paper":"https://pith.science/paper/DJOIS676"},"agent_actions":{"view_html":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE","download_json":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE.json","view_paper":"https://pith.science/paper/DJOIS676","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22768&json=true","fetch_graph":"https://pith.science/api/pith-number/DJOIS676WVW3XNDRNOP45C6ULE/graph.json","fetch_events":"https://pith.science/api/pith-number/DJOIS676WVW3XNDRNOP45C6ULE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE/action/storage_attestation","attest_author":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE/action/author_attestation","sign_citation":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE/action/citation_signature","submit_replication":"https://pith.science/pith/DJOIS676WVW3XNDRNOP45C6ULE/action/replication_record"}},"created_at":"2026-07-05T11:10:02.025262+00:00","updated_at":"2026-07-05T11:10:02.025262+00:00"}