{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XPVRILOCV5ZOHG7WDQEVPBMF25","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":"908679c88b2e80c68735e86704c85a717f4955ae592defab4434cedc3af0effb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T15:21:14Z","title_canon_sha256":"4161ad8c994ed4307d3170574449aa656d74e6e0861fea7508918cec225fa98b"},"schema_version":"1.0","source":{"id":"2605.22607","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22607","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22607v1","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22607","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"XPVRILOCV5ZO","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"XPVRILOCV5ZOHG7W","created_at":"2026-05-22T01:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"XPVRILOC","created_at":"2026-05-22T01:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:047e2bec717e11de0e18be405499a7bf5bfb3dd4677d85981430d9e7ddcbab02","target":"graph","created_at":"2026-05-22T01:05:00Z","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/2605.22607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexandros Neophytou, Chaoqun Cui, David Wong, Hyung Jin Chang, Shijing Wang, Yaping Huang, Yihua Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T15:21:14Z","title":"Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22607","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:a128290423de291c2fca46b61afd24da72db116e2ea096ff260339bb3a2dfd0b","target":"record","created_at":"2026-05-22T01:05:00Z","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":"908679c88b2e80c68735e86704c85a717f4955ae592defab4434cedc3af0effb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T15:21:14Z","title_canon_sha256":"4161ad8c994ed4307d3170574449aa656d74e6e0861fea7508918cec225fa98b"},"schema_version":"1.0","source":{"id":"2605.22607","kind":"arxiv","version":1}},"canonical_sha256":"bbeb142dc2af72e39bf61c09578585d7425012d409fc2d3b9061f222b6e722c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbeb142dc2af72e39bf61c09578585d7425012d409fc2d3b9061f222b6e722c9","first_computed_at":"2026-05-22T01:05:00.074558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:05:00.074558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VoZ3oQyH5I7eBoqygQCVqRl6+mN2RGhcghxtdOVJ1XKBw/v8eJgO8DTBHhyvH6jWeHcwI/CTb6/crF/9QO68AQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:05:00.075416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22607","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a128290423de291c2fca46b61afd24da72db116e2ea096ff260339bb3a2dfd0b","sha256:047e2bec717e11de0e18be405499a7bf5bfb3dd4677d85981430d9e7ddcbab02"],"state_sha256":"8b928ea34f5e04a4c425775d34fbd79d4f2338889163b2ee4298db3ab5276d17"}