{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EYO2FS5GYIRD32YPZ5F6X42PQ7","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":"ffa1597e77f3ef1b537d4aa236fc8d6cc947afdfd90670afb077af4fe8c163c8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T17:59:35Z","title_canon_sha256":"0d0ee71e9ce0e31e4cd5e08c5ed34ca4775b930484f26a0a774debb3cbb278b2"},"schema_version":"1.0","source":{"id":"2407.01525","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01525","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01525v3","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01525","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"pith_short_12","alias_value":"EYO2FS5GYIRD","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"pith_short_16","alias_value":"EYO2FS5GYIRD32YP","created_at":"2026-07-05T08:44:55Z"},{"alias_kind":"pith_short_8","alias_value":"EYO2FS5G","created_at":"2026-07-05T08:44:55Z"}],"graph_snapshots":[{"event_id":"sha256:061aa47037884e97237accfb1b80266873a9572f91bcbfd28feef4acede24372","target":"graph","created_at":"2026-07-05T08:44:55Z","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/2407.01525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although great progress has been made in 3D visual grounding, current models still rely on explicit textual descriptions for grounding and lack the ability to reason human intentions from implicit instructions. We propose a new task called 3D reasoning grounding and introduce a new benchmark ScanReason which provides over 10K question-answer-location pairs from five reasoning types that require the synerization of reasoning and grounding. We further design our approach, ReGround3D, composed of the visual-centric reasoning module empowered by Multi-modal Large Language Model (MLLM) and the 3D g","authors_text":"Chenming Zhu, Kai Chen, Tai Wang, Wenwei Zhang, Xihui Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T17:59:35Z","title":"ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01525","kind":"arxiv","version":3},"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:ec414eb5d1ed802a5657113a3c137e67f6c6f813327798852dd2af5f138c25aa","target":"record","created_at":"2026-07-05T08:44:55Z","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":"ffa1597e77f3ef1b537d4aa236fc8d6cc947afdfd90670afb077af4fe8c163c8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T17:59:35Z","title_canon_sha256":"0d0ee71e9ce0e31e4cd5e08c5ed34ca4775b930484f26a0a774debb3cbb278b2"},"schema_version":"1.0","source":{"id":"2407.01525","kind":"arxiv","version":3}},"canonical_sha256":"261da2cba6c2223deb0fcf4bebf34f87ee85b9e4d952ff23a5bb4b14c695e9ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"261da2cba6c2223deb0fcf4bebf34f87ee85b9e4d952ff23a5bb4b14c695e9ae","first_computed_at":"2026-07-05T08:44:55.573275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:55.573275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7nAIs26ez241r9KZhaOi7P/BB59QDSYH9csFu//0jNtQol0eckP4JN9K2yuJ30oZP0aHj4NCE0av1yjbQkF8CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:55.573704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01525","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec414eb5d1ed802a5657113a3c137e67f6c6f813327798852dd2af5f138c25aa","sha256:061aa47037884e97237accfb1b80266873a9572f91bcbfd28feef4acede24372"],"state_sha256":"21014e713b9c9b8243fb7301e12dd70b1f2b546981aa6c6107281a304dd2373a"}