{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N6ZDM423AA37RYD3QJQ6CGQZN4","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":"f31ede56969c6a4900a8a30bb94390621b22351faedeb26ee2b6d6619470c197","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T17:59:12Z","title_canon_sha256":"09a76c18ea8f2eac481ef354edf5842c9235a7e94ca0632a9a773c53cfc461d5"},"schema_version":"1.0","source":{"id":"2605.27365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27365","created_at":"2026-05-27T02:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27365v1","created_at":"2026-05-27T02:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27365","created_at":"2026-05-27T02:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"N6ZDM423AA37","created_at":"2026-05-27T02:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"N6ZDM423AA37RYD3","created_at":"2026-05-27T02:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"N6ZDM423","created_at":"2026-05-27T02:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:1abaa27cb77aa51ab383e79d09d7346736279335a0144bfa6bece6c9f83f8993","target":"graph","created_at":"2026-05-27T02:06:20Z","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/2605.27365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) commonly formulate visual grounding and detection as a coordinate-token generation problem, serializing each 2D box into multiple 1D tokens that are learned and decoded largely independently. This token-by-token decoding mismatches the coupled structure of box geometry and creates a practical inference bottleneck due to strictly sequential generation. We introduce LocateAnything, a unified generative grounding and detection framework based on Parallel Box Decoding (PBD). By decoding geometric elements such as bounding boxes and points as atomic units in a single s","authors_text":"Andrew Tao, Guilin Liu, Guo Chen, Jan Kautz, Lei Zhang, Shihao Wang, Shilong Liu, Xinyu Wei, Yangzhou Liu, Yuanguo Kuang, Yunze Man, Zhiding Yu, Zhiqi Li","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T17:59:12Z","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27365","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":"sha256:806702d55e20fd5013ddcedde7c524034e433945591514b68cd84be2dedf3cf1","target":"record","created_at":"2026-05-27T02:06:20Z","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":"f31ede56969c6a4900a8a30bb94390621b22351faedeb26ee2b6d6619470c197","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T17:59:12Z","title_canon_sha256":"09a76c18ea8f2eac481ef354edf5842c9235a7e94ca0632a9a773c53cfc461d5"},"schema_version":"1.0","source":{"id":"2605.27365","kind":"arxiv","version":1}},"canonical_sha256":"6fb236735b0037f8e07b8261e11a196f1baf3bb0466722bb13df8ae3dc749cf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fb236735b0037f8e07b8261e11a196f1baf3bb0466722bb13df8ae3dc749cf7","first_computed_at":"2026-05-27T02:06:20.552940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:06:20.552940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HOJYwGIgHs23YMCPzFrTv2p1QrtXHm0wYhDES2thxZtDmKyRWZ0UJJhFbtsP8Twd/8BiWFlUTXLIIOL5MPOXCw==","signature_status":"signed_v1","signed_at":"2026-05-27T02:06:20.553754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:806702d55e20fd5013ddcedde7c524034e433945591514b68cd84be2dedf3cf1","sha256:1abaa27cb77aa51ab383e79d09d7346736279335a0144bfa6bece6c9f83f8993"],"state_sha256":"d55f322440b60fed441d3df347e5a5898fb40ce841bdfd8605f2e896e7917351"}