{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7KPSYXHXQBOBZQEM225DTBT74D","short_pith_number":"pith:7KPSYXHX","schema_version":"1.0","canonical_sha256":"fa9f2c5cf7805c1cc08cd6ba39867fe0edd09e230563cbc25f399ba840206e7d","source":{"kind":"arxiv","id":"2502.20858","version":1},"attestation_state":"computed","paper":{"title":"EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Denghao Zhang, Hao Sun, Ruihua Song, Xiaochuan Liu, Xiaoxue Wu, Xin Cheng, Yuchong Sun","submitted_at":"2025-02-28T09:01:30Z","abstract_excerpt":"Imitating how humans move their gaze in a visual scene is a vital research problem for both visual understanding and psychology, kindling crucial applications such as building alive virtual characters. Previous studies aim to predict gaze trajectories when humans are free-viewing an image, searching for required targets, or looking for clues to answer questions in an image. While these tasks focus on visual-centric scenarios, humans move their gaze also along with audio signal inputs in more common scenarios. To fill this gap, we introduce a new task that predicts human gaze trajectories in a "},"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":"2502.20858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-02-28T09:01:30Z","cross_cats_sorted":[],"title_canon_sha256":"18cd4670c5a9238037dda68c3d22eea77b1dc172d0173cd1d7665baacb9de6c8","abstract_canon_sha256":"7ab9fbc866ba606be531740a6b1f8b3dae82e59497d311a9c172ad2c1282f7b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:41.250578Z","signature_b64":"R40WdtHN4b7wvjE5cYoFVsT370z+/v/Xhqo16nvHDknGK33njf23vWtaj1LFJ1MirNBY/sn5OSdrwnXyCKHmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa9f2c5cf7805c1cc08cd6ba39867fe0edd09e230563cbc25f399ba840206e7d","last_reissued_at":"2026-07-05T10:21:41.250063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:41.250063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Denghao Zhang, Hao Sun, Ruihua Song, Xiaochuan Liu, Xiaoxue Wu, Xin Cheng, Yuchong Sun","submitted_at":"2025-02-28T09:01:30Z","abstract_excerpt":"Imitating how humans move their gaze in a visual scene is a vital research problem for both visual understanding and psychology, kindling crucial applications such as building alive virtual characters. Previous studies aim to predict gaze trajectories when humans are free-viewing an image, searching for required targets, or looking for clues to answer questions in an image. While these tasks focus on visual-centric scenarios, humans move their gaze also along with audio signal inputs in more common scenarios. To fill this gap, we introduce a new task that predicts human gaze trajectories in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20858","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/2502.20858/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":"2502.20858","created_at":"2026-07-05T10:21:41.250126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20858v1","created_at":"2026-07-05T10:21:41.250126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20858","created_at":"2026-07-05T10:21:41.250126+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KPSYXHXQBOB","created_at":"2026-07-05T10:21:41.250126+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KPSYXHXQBOBZQEM","created_at":"2026-07-05T10:21:41.250126+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KPSYXHX","created_at":"2026-07-05T10:21:41.250126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23021","citing_title":"Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D","json":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D.json","graph_json":"https://pith.science/api/pith-number/7KPSYXHXQBOBZQEM225DTBT74D/graph.json","events_json":"https://pith.science/api/pith-number/7KPSYXHXQBOBZQEM225DTBT74D/events.json","paper":"https://pith.science/paper/7KPSYXHX"},"agent_actions":{"view_html":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D","download_json":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D.json","view_paper":"https://pith.science/paper/7KPSYXHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20858&json=true","fetch_graph":"https://pith.science/api/pith-number/7KPSYXHXQBOBZQEM225DTBT74D/graph.json","fetch_events":"https://pith.science/api/pith-number/7KPSYXHXQBOBZQEM225DTBT74D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D/action/storage_attestation","attest_author":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D/action/author_attestation","sign_citation":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D/action/citation_signature","submit_replication":"https://pith.science/pith/7KPSYXHXQBOBZQEM225DTBT74D/action/replication_record"}},"created_at":"2026-07-05T10:21:41.250126+00:00","updated_at":"2026-07-05T10:21:41.250126+00:00"}