{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XPVRILOCV5ZOHG7WDQEVPBMF25","short_pith_number":"pith:XPVRILOC","schema_version":"1.0","canonical_sha256":"bbeb142dc2af72e39bf61c09578585d7425012d409fc2d3b9061f222b6e722c9","source":{"kind":"arxiv","id":"2605.22607","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Neophytou, Chaoqun Cui, David Wong, Hyung Jin Chang, Shijing Wang, Yaping Huang, Yihua Cheng","submitted_at":"2026-05-21T15:21:14Z","abstract_excerpt":"Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have demonstrated strong performance on this task, enabling simpler architectures while outperforming prior methods. However, we observe a key limitation of VFM-based approaches: while VFMs substantially improve scene understanding, they contribute little to gaze reasoning. As a result, existing methods often rely on semantically salient objects rather than true gaze cues, leading to degraded performance when targets are not salient. T"},"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":"2605.22607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T15:21:14Z","cross_cats_sorted":[],"title_canon_sha256":"4161ad8c994ed4307d3170574449aa656d74e6e0861fea7508918cec225fa98b","abstract_canon_sha256":"908679c88b2e80c68735e86704c85a717f4955ae592defab4434cedc3af0effb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:05:00.075416Z","signature_b64":"VoZ3oQyH5I7eBoqygQCVqRl6+mN2RGhcghxtdOVJ1XKBw/v8eJgO8DTBHhyvH6jWeHcwI/CTb6/crF/9QO68AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbeb142dc2af72e39bf61c09578585d7425012d409fc2d3b9061f222b6e722c9","last_reissued_at":"2026-05-22T01:05:00.074558Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:05:00.074558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Neophytou, Chaoqun Cui, David Wong, Hyung Jin Chang, Shijing Wang, Yaping Huang, Yihua Cheng","submitted_at":"2026-05-21T15:21:14Z","abstract_excerpt":"Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have demonstrated strong performance on this task, enabling simpler architectures while outperforming prior methods. However, we observe a key limitation of VFM-based approaches: while VFMs substantially improve scene understanding, they contribute little to gaze reasoning. As a result, existing methods often rely on semantically salient objects rather than true gaze cues, leading to degraded performance when targets are not salient. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22607","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/2605.22607/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":"2605.22607","created_at":"2026-05-22T01:05:00.074695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22607v1","created_at":"2026-05-22T01:05:00.074695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22607","created_at":"2026-05-22T01:05:00.074695+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPVRILOCV5ZO","created_at":"2026-05-22T01:05:00.074695+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPVRILOCV5ZOHG7W","created_at":"2026-05-22T01:05:00.074695+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPVRILOC","created_at":"2026-05-22T01:05:00.074695+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/XPVRILOCV5ZOHG7WDQEVPBMF25","json":"https://pith.science/pith/XPVRILOCV5ZOHG7WDQEVPBMF25.json","graph_json":"https://pith.science/api/pith-number/XPVRILOCV5ZOHG7WDQEVPBMF25/graph.json","events_json":"https://pith.science/api/pith-number/XPVRILOCV5ZOHG7WDQEVPBMF25/events.json","paper":"https://pith.science/paper/XPVRILOC"},"agent_actions":{"view_html":"https://pith.science/pith/XPVRILOCV5ZOHG7WDQEVPBMF25","download_json":"https://pith.science/pith/XPVRILOCV5ZOHG7WDQEVPBMF25.json","view_paper":"https://pith.science/paper/XPVRILOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22607&json=true","fetch_graph":"https://pith.science/api/pith-number/XPVRILOCV5ZOHG7WDQEVPBMF25/graph.json","fetch_events":"https://pith.science/api/pith-number/XPVRILOCV5ZOHG7WDQEVPBMF25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPVRILOCV5ZOHG7WDQEVPBMF25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPVRILOCV5ZOHG7WDQEVPBMF25/action/storage_attestation","attest_author":"https://pith.science/pith/XPVRILOCV5ZOHG7WDQEVPBMF25/action/author_attestation","sign_citation":"https://pith.science/pith/XPVRILOCV5ZOHG7WDQEVPBMF25/action/citation_signature","submit_replication":"https://pith.science/pith/XPVRILOCV5ZOHG7WDQEVPBMF25/action/replication_record"}},"created_at":"2026-05-22T01:05:00.074695+00:00","updated_at":"2026-05-22T01:05:00.074695+00:00"}