{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EX7554VVTNK2CNITRG7HP3F7OA","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":"58b3f81d59f38d309c300f70942f999bddcbebe15c36f80fe8e192e73c8864cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T01:47:10Z","title_canon_sha256":"caa08157d1333cb8ad63ca16444082488f188043dc501b9aefbfe79a5b13213b"},"schema_version":"1.0","source":{"id":"2606.17410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17410","created_at":"2026-06-19T16:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17410v1","created_at":"2026-06-19T16:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17410","created_at":"2026-06-19T16:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"EX7554VVTNK2","created_at":"2026-06-19T16:10:12Z"},{"alias_kind":"pith_short_16","alias_value":"EX7554VVTNK2CNIT","created_at":"2026-06-19T16:10:12Z"},{"alias_kind":"pith_short_8","alias_value":"EX7554VV","created_at":"2026-06-19T16:10:12Z"}],"graph_snapshots":[{"event_id":"sha256:320014994aad3c3da62837b60fad87f881c62d346754f8b85fe41b3f8694a9df","target":"graph","created_at":"2026-06-19T16:10:12Z","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/2606.17410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Declan Campbell, Hanna Hornfeld, Isaac R. Christian, Michael Graziano, Samuel Nastase, Taylor Webb, Udith Haputhanthrige","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T01:47:10Z","title":"Attention Alignment Between Humans and Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17410","kind":"arxiv","version":1},"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":"sha256:628c042f61b24839d68d0e0e232cda9d81816553184440c70f4cd8027045a749","target":"record","created_at":"2026-06-19T16:10:12Z","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":"58b3f81d59f38d309c300f70942f999bddcbebe15c36f80fe8e192e73c8864cd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-16T01:47:10Z","title_canon_sha256":"caa08157d1333cb8ad63ca16444082488f188043dc501b9aefbfe79a5b13213b"},"schema_version":"1.0","source":{"id":"2606.17410","kind":"arxiv","version":1}},"canonical_sha256":"25ffdef2b59b55a1351389be77ecbf7016f99a10a3bdcf2125a4cfa94298c3c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25ffdef2b59b55a1351389be77ecbf7016f99a10a3bdcf2125a4cfa94298c3c2","first_computed_at":"2026-06-19T16:10:12.161725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:12.161725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d5WoL7DeV9Ryp9dAN79Vncvf7HgjvewrreFmz0UVT2LtrrDa4/iggQPgllwqtlugMRjQbtCT9R6JVTLlSuz9Aw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:12.162112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:628c042f61b24839d68d0e0e232cda9d81816553184440c70f4cd8027045a749","sha256:320014994aad3c3da62837b60fad87f881c62d346754f8b85fe41b3f8694a9df"],"state_sha256":"21895ddb11038162341bfc702da3283c26282320a72310db5ce126e6fbb96e51"}