{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EX7554VVTNK2CNITRG7HP3F7OA","short_pith_number":"pith:EX7554VV","schema_version":"1.0","canonical_sha256":"25ffdef2b59b55a1351389be77ecbf7016f99a10a3bdcf2125a4cfa94298c3c2","source":{"kind":"arxiv","id":"2606.17410","version":1},"attestation_state":"computed","paper":{"title":"Attention Alignment Between Humans and Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Declan Campbell, Hanna Hornfeld, Isaac R. Christian, Michael Graziano, Samuel Nastase, Taylor Webb, Udith Haputhanthrige","submitted_at":"2026-06-16T01:47:10Z","abstract_excerpt":"Visual perception depends on top-down goals and bottom-up sensory mechanisms. Vision-language models implement both, allowing us to treat each component as a separable hypothesis about what drives where we look. We compared spatial attention maps from six vision-language models against human fixation heatmaps recorded on 200 images during two tasks (general description and social captioning). The six models spanned a 2$\\times$2 factorial of CNN vs.\\ ViT encoders crossed with LSTM vs.\\ Transformer decoders, plus Molmo 7B-D and Qwen3.5 9B. We found that both decoder and encoder architecture shap"},"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":"2606.17410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T01:47:10Z","cross_cats_sorted":[],"title_canon_sha256":"caa08157d1333cb8ad63ca16444082488f188043dc501b9aefbfe79a5b13213b","abstract_canon_sha256":"58b3f81d59f38d309c300f70942f999bddcbebe15c36f80fe8e192e73c8864cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:12.162112Z","signature_b64":"d5WoL7DeV9Ryp9dAN79Vncvf7HgjvewrreFmz0UVT2LtrrDa4/iggQPgllwqtlugMRjQbtCT9R6JVTLlSuz9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ffdef2b59b55a1351389be77ecbf7016f99a10a3bdcf2125a4cfa94298c3c2","last_reissued_at":"2026-06-19T16:10:12.161725Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:12.161725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention Alignment Between Humans and Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Declan Campbell, Hanna Hornfeld, Isaac R. Christian, Michael Graziano, Samuel Nastase, Taylor Webb, Udith Haputhanthrige","submitted_at":"2026-06-16T01:47:10Z","abstract_excerpt":"Visual perception depends on top-down goals and bottom-up sensory mechanisms. Vision-language models implement both, allowing us to treat each component as a separable hypothesis about what drives where we look. We compared spatial attention maps from six vision-language models against human fixation heatmaps recorded on 200 images during two tasks (general description and social captioning). The six models spanned a 2$\\times$2 factorial of CNN vs.\\ ViT encoders crossed with LSTM vs.\\ Transformer decoders, plus Molmo 7B-D and Qwen3.5 9B. We found that both decoder and encoder architecture shap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17410","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/2606.17410/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":"2606.17410","created_at":"2026-06-19T16:10:12.161791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17410v1","created_at":"2026-06-19T16:10:12.161791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17410","created_at":"2026-06-19T16:10:12.161791+00:00"},{"alias_kind":"pith_short_12","alias_value":"EX7554VVTNK2","created_at":"2026-06-19T16:10:12.161791+00:00"},{"alias_kind":"pith_short_16","alias_value":"EX7554VVTNK2CNIT","created_at":"2026-06-19T16:10:12.161791+00:00"},{"alias_kind":"pith_short_8","alias_value":"EX7554VV","created_at":"2026-06-19T16:10:12.161791+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/EX7554VVTNK2CNITRG7HP3F7OA","json":"https://pith.science/pith/EX7554VVTNK2CNITRG7HP3F7OA.json","graph_json":"https://pith.science/api/pith-number/EX7554VVTNK2CNITRG7HP3F7OA/graph.json","events_json":"https://pith.science/api/pith-number/EX7554VVTNK2CNITRG7HP3F7OA/events.json","paper":"https://pith.science/paper/EX7554VV"},"agent_actions":{"view_html":"https://pith.science/pith/EX7554VVTNK2CNITRG7HP3F7OA","download_json":"https://pith.science/pith/EX7554VVTNK2CNITRG7HP3F7OA.json","view_paper":"https://pith.science/paper/EX7554VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17410&json=true","fetch_graph":"https://pith.science/api/pith-number/EX7554VVTNK2CNITRG7HP3F7OA/graph.json","fetch_events":"https://pith.science/api/pith-number/EX7554VVTNK2CNITRG7HP3F7OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EX7554VVTNK2CNITRG7HP3F7OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EX7554VVTNK2CNITRG7HP3F7OA/action/storage_attestation","attest_author":"https://pith.science/pith/EX7554VVTNK2CNITRG7HP3F7OA/action/author_attestation","sign_citation":"https://pith.science/pith/EX7554VVTNK2CNITRG7HP3F7OA/action/citation_signature","submit_replication":"https://pith.science/pith/EX7554VVTNK2CNITRG7HP3F7OA/action/replication_record"}},"created_at":"2026-06-19T16:10:12.161791+00:00","updated_at":"2026-06-19T16:10:12.161791+00:00"}