{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VJ6R2CTT57XBCKMHSZKOMUTRWT","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":"3f3e83bc35f5807255a826a569fc97d8f4c4f47ccfdf2647721eff8e963d017a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T01:13:57Z","title_canon_sha256":"f53a977b083c7362ea681ed5f3577d79df36e5c95acb9561a95f1635cd2eb628"},"schema_version":"1.0","source":{"id":"2607.23917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23917","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23917v1","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23917","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_12","alias_value":"VJ6R2CTT57XB","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_16","alias_value":"VJ6R2CTT57XBCKMH","created_at":"2026-07-28T01:23:17Z"},{"alias_kind":"pith_short_8","alias_value":"VJ6R2CTT","created_at":"2026-07-28T01:23:17Z"}],"graph_snapshots":[{"event_id":"sha256:a79eb51f1255345ca2fd3501145974e3c65b3aa52b16f77961a2ace9c9cc4655","target":"graph","created_at":"2026-07-28T01:23:17Z","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/2607.23917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel learning problem: decoding gaze into natural language descriptions of human goals across diverse visual tasks. Unlike prior work, which frames gaze decoding as a discriminative task over predefined categories, we formulate it as a generative learning problem: training a model to produce free-form descriptions that capture the rich nuances and open-ended nature of human intentions beyond fixed labels. To this end, we introduce Gazette, the first gaze-to-text decoding framework. Based on multimodal large language models (MLLMs), Gazette learns to decode gaze scanpaths into n","authors_text":"Dimitris Samaras, Gregory Zelinsky, Minh Hoai, Sounak Mondal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T01:13:57Z","title":"Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23917","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":"sha256:87078e9a33488d78b0508da6198d68d1e8dd9c292e38ce8f76e8978cf859c515","target":"record","created_at":"2026-07-28T01:23:17Z","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":"3f3e83bc35f5807255a826a569fc97d8f4c4f47ccfdf2647721eff8e963d017a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T01:13:57Z","title_canon_sha256":"f53a977b083c7362ea681ed5f3577d79df36e5c95acb9561a95f1635cd2eb628"},"schema_version":"1.0","source":{"id":"2607.23917","kind":"arxiv","version":1}},"canonical_sha256":"aa7d1d0a73efee1129879654e65271b4fbd00e2dd5e5dc3b0099f856e3559ac2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa7d1d0a73efee1129879654e65271b4fbd00e2dd5e5dc3b0099f856e3559ac2","first_computed_at":"2026-07-28T01:23:17.658719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:17.658719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wd4ZGJTHmFRW2EFYyifVHlA71qhhYpklS/qOT51x297TVymsM7XWMP46jak0gTCsXsiop+xtV6iYDrMgf5wJBw==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:17.659582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87078e9a33488d78b0508da6198d68d1e8dd9c292e38ce8f76e8978cf859c515","sha256:a79eb51f1255345ca2fd3501145974e3c65b3aa52b16f77961a2ace9c9cc4655"],"state_sha256":"a16dfce785694e6b618126cb06d7d0e3066d1ac53f3ca7aadc30336a5d163796"}