{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K3IYA2OGK5CFU6WXNL4562NK32","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":"1c6e1c76d96b8783bc45ab6715f6d402a55b490c835015400e2aabb28eb75f71","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T15:13:09Z","title_canon_sha256":"c9b32b9ce7d4462c5b7f07e6ad45f3cc55cef3f5e8b8098993c3603fa4fb1b58"},"schema_version":"1.0","source":{"id":"2303.09383","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09383","created_at":"2026-07-05T08:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09383v3","created_at":"2026-07-05T08:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09383","created_at":"2026-07-05T08:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"K3IYA2OGK5CF","created_at":"2026-07-05T08:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"K3IYA2OGK5CFU6WX","created_at":"2026-07-05T08:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"K3IYA2OG","created_at":"2026-07-05T08:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:15401c0b4bb47cbe3f2898b43a3e0cf07c3edef503cd9c08c0980c804f7a5f49","target":"graph","created_at":"2026-07-05T08:02:20Z","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/2303.09383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most models of visual attention aim at predicting either top-down or bottom-up control, as studied using different visual search and free-viewing tasks. In this paper we propose the Human Attention Transformer (HAT), a single model that predicts both forms of attention control. HAT uses a novel transformer-based architecture and a simplified foveated retina that collectively create a spatio-temporal awareness akin to the dynamic visual working memory of humans. HAT not only establishes a new state-of-the-art in predicting the scanpath of fixations made during target-present and target-absent v","authors_text":"Dimitris Samaras, Gregory Zelinsky, Minh Hoai, Ruoyu Xue, Seoyoung Ahn, Sounak Mondal, Zhibo Yang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T15:13:09Z","title":"Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09383","kind":"arxiv","version":3},"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":"sha256:747f4b3a085f35bb892510a57f85445c3257dc4c59a4332c32c8613ed1c5729d","target":"record","created_at":"2026-07-05T08:02:20Z","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":"1c6e1c76d96b8783bc45ab6715f6d402a55b490c835015400e2aabb28eb75f71","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T15:13:09Z","title_canon_sha256":"c9b32b9ce7d4462c5b7f07e6ad45f3cc55cef3f5e8b8098993c3603fa4fb1b58"},"schema_version":"1.0","source":{"id":"2303.09383","kind":"arxiv","version":3}},"canonical_sha256":"56d18069c657445a7ad76af9df69aadeb912d9e50884b10a87a9ce828f9eb6a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56d18069c657445a7ad76af9df69aadeb912d9e50884b10a87a9ce828f9eb6a8","first_computed_at":"2026-07-05T08:02:20.019829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:20.019829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TXybMHe9NkKHFmxAAHhnL1uRDv+2tqr0YOEFYsx3rcTvb2AyJsqqrcrQDboN9j/Q0HiZAnGszD3xifX5TDyrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:20.020240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09383","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:747f4b3a085f35bb892510a57f85445c3257dc4c59a4332c32c8613ed1c5729d","sha256:15401c0b4bb47cbe3f2898b43a3e0cf07c3edef503cd9c08c0980c804f7a5f49"],"state_sha256":"33977b608798ea2f96adb433ee72c56f6f949dcf525f67506db408ff32cb2cab"}