{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N6ZDM423AA37RYD3QJQ6CGQZN4","short_pith_number":"pith:N6ZDM423","schema_version":"1.0","canonical_sha256":"6fb236735b0037f8e07b8261e11a196f1baf3bb0466722bb13df8ae3dc749cf7","source":{"kind":"arxiv","id":"2605.27365","version":1},"attestation_state":"computed","paper":{"title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","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","submitted_at":"2026-05-26T17:59:12Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.27365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T17:59:12Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"09a76c18ea8f2eac481ef354edf5842c9235a7e94ca0632a9a773c53cfc461d5","abstract_canon_sha256":"f31ede56969c6a4900a8a30bb94390621b22351faedeb26ee2b6d6619470c197"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:20.553754Z","signature_b64":"HOJYwGIgHs23YMCPzFrTv2p1QrtXHm0wYhDES2thxZtDmKyRWZ0UJJhFbtsP8Twd/8BiWFlUTXLIIOL5MPOXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fb236735b0037f8e07b8261e11a196f1baf3bb0466722bb13df8ae3dc749cf7","last_reissued_at":"2026-05-27T02:06:20.552940Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:20.552940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","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","submitted_at":"2026-05-26T17:59:12Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27365","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.27365/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.27365","created_at":"2026-05-27T02:06:20.553062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27365v1","created_at":"2026-05-27T02:06:20.553062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27365","created_at":"2026-05-27T02:06:20.553062+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6ZDM423AA37","created_at":"2026-05-27T02:06:20.553062+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6ZDM423AA37RYD3","created_at":"2026-05-27T02:06:20.553062+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6ZDM423","created_at":"2026-05-27T02:06:20.553062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4","json":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4.json","graph_json":"https://pith.science/api/pith-number/N6ZDM423AA37RYD3QJQ6CGQZN4/graph.json","events_json":"https://pith.science/api/pith-number/N6ZDM423AA37RYD3QJQ6CGQZN4/events.json","paper":"https://pith.science/paper/N6ZDM423"},"agent_actions":{"view_html":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4","download_json":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4.json","view_paper":"https://pith.science/paper/N6ZDM423","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27365&json=true","fetch_graph":"https://pith.science/api/pith-number/N6ZDM423AA37RYD3QJQ6CGQZN4/graph.json","fetch_events":"https://pith.science/api/pith-number/N6ZDM423AA37RYD3QJQ6CGQZN4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4/action/storage_attestation","attest_author":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4/action/author_attestation","sign_citation":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4/action/citation_signature","submit_replication":"https://pith.science/pith/N6ZDM423AA37RYD3QJQ6CGQZN4/action/replication_record"}},"created_at":"2026-05-27T02:06:20.553062+00:00","updated_at":"2026-05-27T02:06:20.553062+00:00"}