{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OJOFRNHNMMGBETA356NI56AB2B","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":"2e25e451ac34117673260de35a398c7847e2f8f5fd4b7a77d74075a18c61a71b","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T07:50:56Z","title_canon_sha256":"eb75e7c1f04373c1f68437b621a8d0d46b5ffa824b4616334b6eb20bccf59c9c"},"schema_version":"1.0","source":{"id":"2606.04046","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04046","created_at":"2026-06-04T00:06:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04046v1","created_at":"2026-06-04T00:06:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04046","created_at":"2026-06-04T00:06:45Z"},{"alias_kind":"pith_short_12","alias_value":"OJOFRNHNMMGB","created_at":"2026-06-04T00:06:45Z"},{"alias_kind":"pith_short_16","alias_value":"OJOFRNHNMMGBETA3","created_at":"2026-06-04T00:06:45Z"},{"alias_kind":"pith_short_8","alias_value":"OJOFRNHN","created_at":"2026-06-04T00:06:45Z"}],"graph_snapshots":[{"event_id":"sha256:1b12ab68e6c6575c7a9ad452499e124fa9090dab1435dd74d07b33be525faf98","target":"graph","created_at":"2026-06-04T00:06:45Z","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/2606.04046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In embodied vision-language decision making tasks such as robotic manipulation and navigation, Vision-Language and Vision-Language-Action Models (VLMs & VLAs) are powerful tools with different benefits: VLMs are better at long-term planning, while VLAs are better at reactive control. However, their performance is limited by the same perceptual bottleneck: visual hallucinations arise due to the models' inability to distinguish task-relevant objects from distractors. In principle, accurate identification and focus on critical objects while filtering out irrelevant ones is the key to break this l","authors_text":"Bohong Chen, Boyuan Xiao, Ji Feng, Kun Zhou, Yao-Xiang Ding, Yumeng Li","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T07:50:56Z","title":"Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04046","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":"sha256:20eb115b7930100dad030d0bfa464b09862262df180f40938bbf1cee29e3b56f","target":"record","created_at":"2026-06-04T00:06:45Z","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":"2e25e451ac34117673260de35a398c7847e2f8f5fd4b7a77d74075a18c61a71b","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T07:50:56Z","title_canon_sha256":"eb75e7c1f04373c1f68437b621a8d0d46b5ffa824b4616334b6eb20bccf59c9c"},"schema_version":"1.0","source":{"id":"2606.04046","kind":"arxiv","version":1}},"canonical_sha256":"725c58b4ed630c124c1bef9a8ef801d054ed0d59cbc3405189f79553aecd76f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"725c58b4ed630c124c1bef9a8ef801d054ed0d59cbc3405189f79553aecd76f6","first_computed_at":"2026-06-04T00:06:45.150507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T00:06:45.150507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LyIQj12aCY21Lp6fdbqDyrtteWfenopdzdT8ue78PH+Fspl0JIjduYM+b3NrReiH/sJp4wIwHQsUzoiuEV6NCw==","signature_status":"signed_v1","signed_at":"2026-06-04T00:06:45.150895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04046","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20eb115b7930100dad030d0bfa464b09862262df180f40938bbf1cee29e3b56f","sha256:1b12ab68e6c6575c7a9ad452499e124fa9090dab1435dd74d07b33be525faf98"],"state_sha256":"919157de62485e1b009ca8612579d850d40df50a3784714e2866501af4c62c7a"}