{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YEPSRUJQVMXIOYFDUPSEONMGY2","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":"7c4eb1e8d2fe398d9ac159ce360f4afd8de41c8297b77608ebaf6cf9bd440790","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-19T04:35:05Z","title_canon_sha256":"fadf974a0933a28a26006c2915b2c7bbf9e9fac36eb37d54053eb305ec9175dd"},"schema_version":"1.0","source":{"id":"2405.11442","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11442","created_at":"2026-07-05T08:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11442v2","created_at":"2026-07-05T08:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11442","created_at":"2026-07-05T08:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"YEPSRUJQVMXI","created_at":"2026-07-05T08:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"YEPSRUJQVMXIOYFD","created_at":"2026-07-05T08:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"YEPSRUJQ","created_at":"2026-07-05T08:47:52Z"}],"graph_snapshots":[{"event_id":"sha256:f600a0e1878ec875c42a846a188fa0192277f27659f8aed89bae1a91d7c89856","target":"graph","created_at":"2026-07-05T08:47:52Z","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/2405.11442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene. However, a considerable gap exists between existing methods and such a unified model, due to the independent application of representation and insufficient exploration of 3D multi-task training. In this paper, we introduce PQ3D, a unified model capable of using Promptable Queries to tackle a wide range of 3D-VL tasks, from low-level instance segmentation to high-level reasoning and planning. This is achieved through three key innovation","authors_text":"Baoxiong Jia, Qing Li, Siyuan Huang, Xiaojian Ma, Xuesong Niu, Yixin Chen, Zhidong Deng, Zhuofan Zhang, Ziyu Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-19T04:35:05Z","title":"Unifying 3D Vision-Language Understanding via Promptable Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11442","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":"sha256:7db5bc3cd491d2894d1c1fa7a2214a5e3f6fcc911ea0ac8dfa913c657166a945","target":"record","created_at":"2026-07-05T08:47:52Z","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":"7c4eb1e8d2fe398d9ac159ce360f4afd8de41c8297b77608ebaf6cf9bd440790","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-19T04:35:05Z","title_canon_sha256":"fadf974a0933a28a26006c2915b2c7bbf9e9fac36eb37d54053eb305ec9175dd"},"schema_version":"1.0","source":{"id":"2405.11442","kind":"arxiv","version":2}},"canonical_sha256":"c11f28d130ab2e8760a3a3e4473586c6a361f63de4575d9d73ad04e9c480a28c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c11f28d130ab2e8760a3a3e4473586c6a361f63de4575d9d73ad04e9c480a28c","first_computed_at":"2026-07-05T08:47:52.091981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:52.091981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NcZT6TePdJCyrnSGtvPfhgGm+HSNwsjs/QKSFMySSRBMOaiGbRBqGum9FcZRhw/LYHMp9LzgNMhNXvlsmtH5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:52.092455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11442","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7db5bc3cd491d2894d1c1fa7a2214a5e3f6fcc911ea0ac8dfa913c657166a945","sha256:f600a0e1878ec875c42a846a188fa0192277f27659f8aed89bae1a91d7c89856"],"state_sha256":"4a225f3d8afb112c64953f0d853c27990e044c84a27256190e776e253adcc5c0"}