{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LR7DURQ3NRDQXR23O5267JRSM5","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":"764230791f2f78609ba45c1597c2876dadd39b492ff56e9797d69410da8bad9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T09:54:39Z","title_canon_sha256":"8b8552fe86825f0a590c24bb17bf89cf10506221c0841d0179a0b161f8a017d1"},"schema_version":"1.0","source":{"id":"2606.22409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22409","created_at":"2026-06-23T02:13:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22409v1","created_at":"2026-06-23T02:13:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22409","created_at":"2026-06-23T02:13:37Z"},{"alias_kind":"pith_short_12","alias_value":"LR7DURQ3NRDQ","created_at":"2026-06-23T02:13:37Z"},{"alias_kind":"pith_short_16","alias_value":"LR7DURQ3NRDQXR23","created_at":"2026-06-23T02:13:37Z"},{"alias_kind":"pith_short_8","alias_value":"LR7DURQ3","created_at":"2026-06-23T02:13:37Z"}],"graph_snapshots":[{"event_id":"sha256:54db44708aef6737fb154f7aa1a1f7fc957d2419d3d44a19d9f58b128fac5463","target":"graph","created_at":"2026-06-23T02:13:37Z","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/2606.22409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robots operating in everyday environments must understand fine-grained human actions, intentions, and contextual cues from broad views where people occupy only small regions, a capability unmet by current systems. While open-vocabulary action recognition methods remain limited to assigning predefined labels, and vision-language models (VLMs) face an inherent trade-off between informational richness and factual fidelity in their outputs, neither approach achieves the deep semantic interpretation required for reliable human-robot interaction. We propose Gold Points Sniper (GPS), a novel framewor","authors_text":"Changshui Zhang, Haodi Liu, Kunda Yan, Sen Cui, Xinhang Yang, Zeyu Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T09:54:39Z","title":"Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22409","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":"sha256:4f0330a449344cd0ec3f4fcb92d198aba24a0f88788f4980f0d2106337e77b2d","target":"record","created_at":"2026-06-23T02:13:37Z","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":"764230791f2f78609ba45c1597c2876dadd39b492ff56e9797d69410da8bad9d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T09:54:39Z","title_canon_sha256":"8b8552fe86825f0a590c24bb17bf89cf10506221c0841d0179a0b161f8a017d1"},"schema_version":"1.0","source":{"id":"2606.22409","kind":"arxiv","version":1}},"canonical_sha256":"5c7e3a461b6c470bc75b7775efa632676c452c6276a3f617abe018a95bef6b90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c7e3a461b6c470bc75b7775efa632676c452c6276a3f617abe018a95bef6b90","first_computed_at":"2026-06-23T02:13:37.628694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:37.628694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wdqeIoNUXz02uy7vMyxpjabrxvqSGltmMV1BseAclCeaSlISTQxlyOmsJNCAfV5YW1hCIOIuBJsx5Gc6qr8wAA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:37.629111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f0330a449344cd0ec3f4fcb92d198aba24a0f88788f4980f0d2106337e77b2d","sha256:54db44708aef6737fb154f7aa1a1f7fc957d2419d3d44a19d9f58b128fac5463"],"state_sha256":"5f526a11e49aac30d0566bbfe9ffe507daf55558fcfa255b0133c9da733f040d"}