{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3NRWFEPPA7XDX5FLV2NXRU2DJL","short_pith_number":"pith:3NRWFEPP","schema_version":"1.0","canonical_sha256":"db636291ef07ee3bf4abae9b78d3434aec6d316174ae12807969902e261eeab7","source":{"kind":"arxiv","id":"2505.12660","version":1},"attestation_state":"computed","paper":{"title":"Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Skaza, Miguel P. Eckstein, Shravan Murlidaran, William Y. Wang, Ziqi Wen","submitted_at":"2025-05-19T03:23:00Z","abstract_excerpt":"Although models exist that predict human response times (RTs) in tasks such as target search and visual discrimination, the development of image-computable predictors for scene understanding time remains an open challenge. Recent advances in vision-language models (VLMs), which can generate scene descriptions for arbitrary images, combined with the availability of quantitative metrics for comparing linguistic descriptions, offer a new opportunity to model human scene understanding. We hypothesize that the primary bottleneck in human scene understanding and the driving source of variability in "},"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":"2505.12660","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T03:23:00Z","cross_cats_sorted":[],"title_canon_sha256":"00e474fe40f145a71904aa634846d0ce41d982b2e5ea7e3c28a9465b3b06e8ff","abstract_canon_sha256":"3b707b5882f2a4822915fbbc03247402eca7f7e78cf965cd335802479fbbb713"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:07.824691Z","signature_b64":"oybeHUWNcGxcw3M78bcbmTyiYNFg7UBcyfruQybsHzptNgdc+TFqA2YhWAcOlXz4TEOZMGXuO8/zf5DkvIRjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db636291ef07ee3bf4abae9b78d3434aec6d316174ae12807969902e261eeab7","last_reissued_at":"2026-07-05T11:05:07.824197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:07.824197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Reaction Time to Comprehend Scenes with Foveated Scene Understanding Maps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jonathan Skaza, Miguel P. Eckstein, Shravan Murlidaran, William Y. Wang, Ziqi Wen","submitted_at":"2025-05-19T03:23:00Z","abstract_excerpt":"Although models exist that predict human response times (RTs) in tasks such as target search and visual discrimination, the development of image-computable predictors for scene understanding time remains an open challenge. Recent advances in vision-language models (VLMs), which can generate scene descriptions for arbitrary images, combined with the availability of quantitative metrics for comparing linguistic descriptions, offer a new opportunity to model human scene understanding. We hypothesize that the primary bottleneck in human scene understanding and the driving source of variability in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12660","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/2505.12660/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":"2505.12660","created_at":"2026-07-05T11:05:07.824262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12660v1","created_at":"2026-07-05T11:05:07.824262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12660","created_at":"2026-07-05T11:05:07.824262+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NRWFEPPA7XD","created_at":"2026-07-05T11:05:07.824262+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NRWFEPPA7XDX5FL","created_at":"2026-07-05T11:05:07.824262+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NRWFEPP","created_at":"2026-07-05T11:05:07.824262+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/3NRWFEPPA7XDX5FLV2NXRU2DJL","json":"https://pith.science/pith/3NRWFEPPA7XDX5FLV2NXRU2DJL.json","graph_json":"https://pith.science/api/pith-number/3NRWFEPPA7XDX5FLV2NXRU2DJL/graph.json","events_json":"https://pith.science/api/pith-number/3NRWFEPPA7XDX5FLV2NXRU2DJL/events.json","paper":"https://pith.science/paper/3NRWFEPP"},"agent_actions":{"view_html":"https://pith.science/pith/3NRWFEPPA7XDX5FLV2NXRU2DJL","download_json":"https://pith.science/pith/3NRWFEPPA7XDX5FLV2NXRU2DJL.json","view_paper":"https://pith.science/paper/3NRWFEPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12660&json=true","fetch_graph":"https://pith.science/api/pith-number/3NRWFEPPA7XDX5FLV2NXRU2DJL/graph.json","fetch_events":"https://pith.science/api/pith-number/3NRWFEPPA7XDX5FLV2NXRU2DJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NRWFEPPA7XDX5FLV2NXRU2DJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NRWFEPPA7XDX5FLV2NXRU2DJL/action/storage_attestation","attest_author":"https://pith.science/pith/3NRWFEPPA7XDX5FLV2NXRU2DJL/action/author_attestation","sign_citation":"https://pith.science/pith/3NRWFEPPA7XDX5FLV2NXRU2DJL/action/citation_signature","submit_replication":"https://pith.science/pith/3NRWFEPPA7XDX5FLV2NXRU2DJL/action/replication_record"}},"created_at":"2026-07-05T11:05:07.824262+00:00","updated_at":"2026-07-05T11:05:07.824262+00:00"}