{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VJ6R2CTT57XBCKMHSZKOMUTRWT","short_pith_number":"pith:VJ6R2CTT","schema_version":"1.0","canonical_sha256":"aa7d1d0a73efee1129879654e65271b4fbd00e2dd5e5dc3b0099f856e3559ac2","source":{"kind":"arxiv","id":"2607.23917","version":1},"attestation_state":"computed","paper":{"title":"Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris Samaras, Gregory Zelinsky, Minh Hoai, Sounak Mondal","submitted_at":"2026-07-27T01:13:57Z","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"},"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":"2607.23917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T01:13:57Z","cross_cats_sorted":[],"title_canon_sha256":"f53a977b083c7362ea681ed5f3577d79df36e5c95acb9561a95f1635cd2eb628","abstract_canon_sha256":"3f3e83bc35f5807255a826a569fc97d8f4c4f47ccfdf2647721eff8e963d017a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:17.659582Z","signature_b64":"wd4ZGJTHmFRW2EFYyifVHlA71qhhYpklS/qOT51x297TVymsM7XWMP46jak0gTCsXsiop+xtV6iYDrMgf5wJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa7d1d0a73efee1129879654e65271b4fbd00e2dd5e5dc3b0099f856e3559ac2","last_reissued_at":"2026-07-28T01:23:17.658719Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:17.658719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris Samaras, Gregory Zelinsky, Minh Hoai, Sounak Mondal","submitted_at":"2026-07-27T01:13:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23917","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/2607.23917/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":"2607.23917","created_at":"2026-07-28T01:23:17.659158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23917v1","created_at":"2026-07-28T01:23:17.659158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23917","created_at":"2026-07-28T01:23:17.659158+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJ6R2CTT57XB","created_at":"2026-07-28T01:23:17.659158+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJ6R2CTT57XBCKMH","created_at":"2026-07-28T01:23:17.659158+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJ6R2CTT","created_at":"2026-07-28T01:23:17.659158+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/VJ6R2CTT57XBCKMHSZKOMUTRWT","json":"https://pith.science/pith/VJ6R2CTT57XBCKMHSZKOMUTRWT.json","graph_json":"https://pith.science/api/pith-number/VJ6R2CTT57XBCKMHSZKOMUTRWT/graph.json","events_json":"https://pith.science/api/pith-number/VJ6R2CTT57XBCKMHSZKOMUTRWT/events.json","paper":"https://pith.science/paper/VJ6R2CTT"},"agent_actions":{"view_html":"https://pith.science/pith/VJ6R2CTT57XBCKMHSZKOMUTRWT","download_json":"https://pith.science/pith/VJ6R2CTT57XBCKMHSZKOMUTRWT.json","view_paper":"https://pith.science/paper/VJ6R2CTT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23917&json=true","fetch_graph":"https://pith.science/api/pith-number/VJ6R2CTT57XBCKMHSZKOMUTRWT/graph.json","fetch_events":"https://pith.science/api/pith-number/VJ6R2CTT57XBCKMHSZKOMUTRWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJ6R2CTT57XBCKMHSZKOMUTRWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJ6R2CTT57XBCKMHSZKOMUTRWT/action/storage_attestation","attest_author":"https://pith.science/pith/VJ6R2CTT57XBCKMHSZKOMUTRWT/action/author_attestation","sign_citation":"https://pith.science/pith/VJ6R2CTT57XBCKMHSZKOMUTRWT/action/citation_signature","submit_replication":"https://pith.science/pith/VJ6R2CTT57XBCKMHSZKOMUTRWT/action/replication_record"}},"created_at":"2026-07-28T01:23:17.659158+00:00","updated_at":"2026-07-28T01:23:17.659158+00:00"}