{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3IZ3N6X73MWQXU4MUGRZE6PAY4","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":"d690727c893bfa4b27d44c0abc8c491878190be19c35558605b4c75beb74067e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-30T15:24:50Z","title_canon_sha256":"516cb2baaf47c084119cc99350acd64860a4f46cb7c31d4e479f19ae1327aeb4"},"schema_version":"1.0","source":{"id":"2401.00260","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00260","created_at":"2026-07-05T10:26:36Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00260v4","created_at":"2026-07-05T10:26:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00260","created_at":"2026-07-05T10:26:36Z"},{"alias_kind":"pith_short_12","alias_value":"3IZ3N6X73MWQ","created_at":"2026-07-05T10:26:36Z"},{"alias_kind":"pith_short_16","alias_value":"3IZ3N6X73MWQXU4M","created_at":"2026-07-05T10:26:36Z"},{"alias_kind":"pith_short_8","alias_value":"3IZ3N6X7","created_at":"2026-07-05T10:26:36Z"}],"graph_snapshots":[{"event_id":"sha256:4af15e1acb55fb7e6b6e6f931697b243105e1d462e8b0f45716bfef207586456","target":"graph","created_at":"2026-07-05T10:26:36Z","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/2401.00260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual gaze estimation, with its wide-ranging application scenarios, has garnered increasing attention within the research community. Although existing approaches infer gaze solely from image signals, recent advances in visual-language collaboration have demonstrated that the integration of linguistic information can significantly enhance performance across various visual tasks. Leveraging the remarkable transferability of large-scale Contrastive Language-Image Pre-training (CLIP) models, we address the open and urgent question of how to effectively apply linguistic cues to gaze estimation. In","authors_text":"Hao Ruan, Jun Wang, Liangjian Wen, Mingjie Wang, Yong Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-30T15:24:50Z","title":"GazeCLIP: Enhancing Gaze Estimation Through Text-Guided Multimodal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00260","kind":"arxiv","version":4},"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:c20f5d47ce3d30a9fa543ea6ba9997fa471874b6c9dbc837a0edbe84d45304df","target":"record","created_at":"2026-07-05T10:26:36Z","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":"d690727c893bfa4b27d44c0abc8c491878190be19c35558605b4c75beb74067e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-30T15:24:50Z","title_canon_sha256":"516cb2baaf47c084119cc99350acd64860a4f46cb7c31d4e479f19ae1327aeb4"},"schema_version":"1.0","source":{"id":"2401.00260","kind":"arxiv","version":4}},"canonical_sha256":"da33b6faffdb2d0bd38ca1a39279e0c710dc779ad3c26cc5591e0512d4efb858","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da33b6faffdb2d0bd38ca1a39279e0c710dc779ad3c26cc5591e0512d4efb858","first_computed_at":"2026-07-05T10:26:36.837086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:36.837086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EMK59tL3hFKavddiVqkpNtBnUF/2RzzQQ9VdTw9kRwZnnKunudBqfsU8mFOFARkr2cRHfngLc436SW6xHaT8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:36.837617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00260","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c20f5d47ce3d30a9fa543ea6ba9997fa471874b6c9dbc837a0edbe84d45304df","sha256:4af15e1acb55fb7e6b6e6f931697b243105e1d462e8b0f45716bfef207586456"],"state_sha256":"3a4e3a359fdbbc450df430b8ca7e2c7cb1bea9d42113cce7abeae337f41e1d88"}