{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AFVCIMKUUIYMS33HYNNYB3EGEP","short_pith_number":"pith:AFVCIMKU","schema_version":"1.0","canonical_sha256":"016a243154a230c96f67c35b80ec8623c63839a3fb2398872e49c95b1022a145","source":{"kind":"arxiv","id":"2608.07282","version":1},"attestation_state":"computed","paper":{"title":"Gaze Behavior in Visual World Experiments Can be Modeled With Off-the-shelf Language-Vision Encoders","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Rahul Murali Shankar, Sebastian Pad\\'o, Titus von der Malsburg","submitted_at":"2026-08-07T14:42:51Z","abstract_excerpt":"The recent advances in neural language models have also spurred much work in computational psycholinguistics, asking whether neural LMs are also promising models of human language processing. However, work has been overwhelmingly focused on the unimodal case of written or spoken language. In contrast, multimodal experimental paradigms, like visual world studies that present participants with both visual and linguistic input simultaneously, have been neglected. In this paper, we present a novel approach that predicts gaze behavior in visual world studies. It does so by combining a simple multi-"},"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":"2608.07282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T14:42:51Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"11d9a100a796f49bd72e4ca245f1691f3cfb74bf545686c3e373ca4a6289ff51","abstract_canon_sha256":"93fab64719ab996cbaefc93fe15920e6afc25f7cb2dd3a814ac719946ae8bb1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:14:50.936189Z","signature_b64":"QYhMylOuqGBoS8rv1WYtZy0bsWj6T+3HsfU7lcdpIvkptSiuMbzUgzajR9zH/NESPCO5qilAez1p6XqQj1DLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"016a243154a230c96f67c35b80ec8623c63839a3fb2398872e49c95b1022a145","last_reissued_at":"2026-08-10T01:14:50.933651Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:14:50.933651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaze Behavior in Visual World Experiments Can be Modeled With Off-the-shelf Language-Vision Encoders","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Rahul Murali Shankar, Sebastian Pad\\'o, Titus von der Malsburg","submitted_at":"2026-08-07T14:42:51Z","abstract_excerpt":"The recent advances in neural language models have also spurred much work in computational psycholinguistics, asking whether neural LMs are also promising models of human language processing. However, work has been overwhelmingly focused on the unimodal case of written or spoken language. In contrast, multimodal experimental paradigms, like visual world studies that present participants with both visual and linguistic input simultaneously, have been neglected. In this paper, we present a novel approach that predicts gaze behavior in visual world studies. It does so by combining a simple multi-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07282","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/2608.07282/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":"2608.07282","created_at":"2026-08-10T01:14:50.934592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07282v1","created_at":"2026-08-10T01:14:50.934592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07282","created_at":"2026-08-10T01:14:50.934592+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFVCIMKUUIYM","created_at":"2026-08-10T01:14:50.934592+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFVCIMKUUIYMS33H","created_at":"2026-08-10T01:14:50.934592+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFVCIMKU","created_at":"2026-08-10T01:14:50.934592+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/AFVCIMKUUIYMS33HYNNYB3EGEP","json":"https://pith.science/pith/AFVCIMKUUIYMS33HYNNYB3EGEP.json","graph_json":"https://pith.science/api/pith-number/AFVCIMKUUIYMS33HYNNYB3EGEP/graph.json","events_json":"https://pith.science/api/pith-number/AFVCIMKUUIYMS33HYNNYB3EGEP/events.json","paper":"https://pith.science/paper/AFVCIMKU"},"agent_actions":{"view_html":"https://pith.science/pith/AFVCIMKUUIYMS33HYNNYB3EGEP","download_json":"https://pith.science/pith/AFVCIMKUUIYMS33HYNNYB3EGEP.json","view_paper":"https://pith.science/paper/AFVCIMKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07282&json=true","fetch_graph":"https://pith.science/api/pith-number/AFVCIMKUUIYMS33HYNNYB3EGEP/graph.json","fetch_events":"https://pith.science/api/pith-number/AFVCIMKUUIYMS33HYNNYB3EGEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFVCIMKUUIYMS33HYNNYB3EGEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFVCIMKUUIYMS33HYNNYB3EGEP/action/storage_attestation","attest_author":"https://pith.science/pith/AFVCIMKUUIYMS33HYNNYB3EGEP/action/author_attestation","sign_citation":"https://pith.science/pith/AFVCIMKUUIYMS33HYNNYB3EGEP/action/citation_signature","submit_replication":"https://pith.science/pith/AFVCIMKUUIYMS33HYNNYB3EGEP/action/replication_record"}},"created_at":"2026-08-10T01:14:50.934592+00:00","updated_at":"2026-08-10T01:14:50.934592+00:00"}