{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UQH3WNZZQPIB7RPWXPJ2A4L2AZ","short_pith_number":"pith:UQH3WNZZ","schema_version":"1.0","canonical_sha256":"a40fbb373983d01fc5f6bbd3a0717a067d3e7b0a6cfed7d899c646848f85ce00","source":{"kind":"arxiv","id":"2607.02083","version":1},"attestation_state":"computed","paper":{"title":"DeepGaze3.5-VL: Modeling Scanpaths via Autoregressive Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matthias Bethge, Matthias K\\\"ummerer, Susmit Agrawal","submitted_at":"2026-07-02T12:25:45Z","abstract_excerpt":"Understanding human visual attention on a scene over time has applications in domains such as interface design and inferring cognitive states. Modeling visual scanpaths has historically relied on specialized architectures with hand-crafted priors. While these architectures can model fixation sequences, their rigid structural biases restrict easy extendability and flexible conditioning. For instance, integrating task-specific instructions or adapting to distinct viewer identities requires custom, disjoint architectural additions. We frame scanpath prediction purely as a discrete sequence modeli"},"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":"2607.02083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T12:25:45Z","cross_cats_sorted":[],"title_canon_sha256":"c19875b26f39d49f3acc5ade28934ab5d5c2d58d40ecc2d94cb587eaf175d9e2","abstract_canon_sha256":"e0d89089e3008fda27dd1abe9977e69d659fc7cb429dc4b32ffd70ce2429b3be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:41.725140Z","signature_b64":"ZYJruBYwmEpZe4XFvakW3OuMmELw4eCJLhM73nAILjrfxkezs4ltWraTDBAr/mYF1GLcaY1A9SCFeSlqBFSnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a40fbb373983d01fc5f6bbd3a0717a067d3e7b0a6cfed7d899c646848f85ce00","last_reissued_at":"2026-07-03T01:17:41.724667Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:41.724667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepGaze3.5-VL: Modeling Scanpaths via Autoregressive Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matthias Bethge, Matthias K\\\"ummerer, Susmit Agrawal","submitted_at":"2026-07-02T12:25:45Z","abstract_excerpt":"Understanding human visual attention on a scene over time has applications in domains such as interface design and inferring cognitive states. Modeling visual scanpaths has historically relied on specialized architectures with hand-crafted priors. While these architectures can model fixation sequences, their rigid structural biases restrict easy extendability and flexible conditioning. For instance, integrating task-specific instructions or adapting to distinct viewer identities requires custom, disjoint architectural additions. We frame scanpath prediction purely as a discrete sequence modeli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02083","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/2607.02083/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":"2607.02083","created_at":"2026-07-03T01:17:41.724744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02083v1","created_at":"2026-07-03T01:17:41.724744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02083","created_at":"2026-07-03T01:17:41.724744+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQH3WNZZQPIB","created_at":"2026-07-03T01:17:41.724744+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQH3WNZZQPIB7RPW","created_at":"2026-07-03T01:17:41.724744+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQH3WNZZ","created_at":"2026-07-03T01:17:41.724744+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ","json":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ.json","graph_json":"https://pith.science/api/pith-number/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/graph.json","events_json":"https://pith.science/api/pith-number/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/events.json","paper":"https://pith.science/paper/UQH3WNZZ"},"agent_actions":{"view_html":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ","download_json":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ.json","view_paper":"https://pith.science/paper/UQH3WNZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02083&json=true","fetch_graph":"https://pith.science/api/pith-number/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/action/storage_attestation","attest_author":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/action/author_attestation","sign_citation":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/action/citation_signature","submit_replication":"https://pith.science/pith/UQH3WNZZQPIB7RPWXPJ2A4L2AZ/action/replication_record"}},"created_at":"2026-07-03T01:17:41.724744+00:00","updated_at":"2026-07-03T01:17:41.724744+00:00"}