{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PU5J22APYHMMNLHOLHWNA7KWDK","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":"e84193d44d4b5c494672ef999d20245b0a8520d9173be29ba2409180d7542e07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T14:45:17Z","title_canon_sha256":"a5d866fdfb343c6e542e7f03dcaa81dd41da5f2441e2042c8296f80a7ea34b5a"},"schema_version":"1.0","source":{"id":"2403.12778","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.12778","created_at":"2026-07-05T09:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.12778v2","created_at":"2026-07-05T09:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12778","created_at":"2026-07-05T09:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"PU5J22APYHMM","created_at":"2026-07-05T09:35:08Z"},{"alias_kind":"pith_short_16","alias_value":"PU5J22APYHMMNLHO","created_at":"2026-07-05T09:35:08Z"},{"alias_kind":"pith_short_8","alias_value":"PU5J22AP","created_at":"2026-07-05T09:35:08Z"}],"graph_snapshots":[{"event_id":"sha256:cba095fd5053fb19231db4013648d71f2796ec2836e173229fc59fcf77a8eaa2","target":"graph","created_at":"2026-07-05T09:35:08Z","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/2403.12778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gaze following aims to interpret human-scene interactions by predicting the person's focal point of gaze. Prevailing approaches often adopt a two-stage framework, whereby multi-modality information is extracted in the initial stage for gaze target prediction. Consequently, the efficacy of these methods highly depends on the precision of the preceding modality extraction. Others use a single-modality approach with complex decoders, increasing network computational load. Inspired by the remarkable success of pre-trained plain vision transformers (ViTs), we introduce a novel single-modality gaze ","authors_text":"Jingfeng Yao, Jinglin Zhang, Wenyu Liu, Xiangmin Xu, Xinggang Wang, Yuehao Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T14:45:17Z","title":"ViTGaze: Gaze Following with Interaction Features in Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12778","kind":"arxiv","version":2},"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":"sha256:14213ae2f33da0c1e3c563402fb613ca084475dabe8ef72c27dfb7706a1f7d3e","target":"record","created_at":"2026-07-05T09:35:08Z","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":"e84193d44d4b5c494672ef999d20245b0a8520d9173be29ba2409180d7542e07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T14:45:17Z","title_canon_sha256":"a5d866fdfb343c6e542e7f03dcaa81dd41da5f2441e2042c8296f80a7ea34b5a"},"schema_version":"1.0","source":{"id":"2403.12778","kind":"arxiv","version":2}},"canonical_sha256":"7d3a9d680fc1d8c6acee59ecd07d561ab8df35b8268498e0f4d75075ab878b0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d3a9d680fc1d8c6acee59ecd07d561ab8df35b8268498e0f4d75075ab878b0b","first_computed_at":"2026-07-05T09:35:08.975375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:08.975375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XWYftNPxbLUdhdDOkHB5C5lZCfAgF67Xkgpypk3Q4tqGxzewvcP1DMZOI9SyI7uZQzYX5UhzbCA4KJAtsUQBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:08.975847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.12778","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14213ae2f33da0c1e3c563402fb613ca084475dabe8ef72c27dfb7706a1f7d3e","sha256:cba095fd5053fb19231db4013648d71f2796ec2836e173229fc59fcf77a8eaa2"],"state_sha256":"cf31e42cceba4f0cbd2458c9233e30ecb5531ecffa90e06facc23b90b7733b64"}