{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MOMYEIAFPCVDOGESOFDPV2IRBO","short_pith_number":"pith:MOMYEIAF","schema_version":"1.0","canonical_sha256":"639982200578aa3718927146fae9110ba08e67aa5c9941cb45584951c410f79e","source":{"kind":"arxiv","id":"2605.28490","version":1},"attestation_state":"computed","paper":{"title":"SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajie Xu, Jiawei Li, Long Chen, Weijie Shi, Xiaofang Zhou, Ziyi Liu","submitted_at":"2026-05-27T13:45:34Z","abstract_excerpt":"3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning, yet many rely on a single pointer-style grounding decision that compresses a relational instruction into one selection. This is brittle for fine-grained queries where multiple same-class candidates must be ruled out by context objects and spatial relations. We propose Structured Spatial Reasoning 3D-LLM (SSR3D-LLM), a structured grounding interface for unified 3D-LLMs. Given fixed Mask3D object proposals, the LLM w"},"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":"2605.28490","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T13:45:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1da6a29fbbaca1bb5da579a64c6c5d916db9c10af57aa697f09a55b5972428b","abstract_canon_sha256":"4e9854187dbba5c03910867d6897b14a15634f9deafc41fbeae0a16adfab65be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:54.409765Z","signature_b64":"RFJIlFV2mWdln0lpuzcSSOOzzlUKL4rOsCtZpdWP4dBtKeeqr3tG+ef0k2BKZDLyLaQTRJVrFih256HUw1MTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"639982200578aa3718927146fae9110ba08e67aa5c9941cb45584951c410f79e","last_reissued_at":"2026-05-28T02:04:54.409307Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:54.409307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiajie Xu, Jiawei Li, Long Chen, Weijie Shi, Xiaofang Zhou, Ziyi Liu","submitted_at":"2026-05-27T13:45:34Z","abstract_excerpt":"3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning, yet many rely on a single pointer-style grounding decision that compresses a relational instruction into one selection. This is brittle for fine-grained queries where multiple same-class candidates must be ruled out by context objects and spatial relations. We propose Structured Spatial Reasoning 3D-LLM (SSR3D-LLM), a structured grounding interface for unified 3D-LLMs. Given fixed Mask3D object proposals, the LLM w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28490","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/2605.28490/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":"2605.28490","created_at":"2026-05-28T02:04:54.409377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28490v1","created_at":"2026-05-28T02:04:54.409377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28490","created_at":"2026-05-28T02:04:54.409377+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOMYEIAFPCVD","created_at":"2026-05-28T02:04:54.409377+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOMYEIAFPCVDOGES","created_at":"2026-05-28T02:04:54.409377+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOMYEIAF","created_at":"2026-05-28T02:04:54.409377+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/MOMYEIAFPCVDOGESOFDPV2IRBO","json":"https://pith.science/pith/MOMYEIAFPCVDOGESOFDPV2IRBO.json","graph_json":"https://pith.science/api/pith-number/MOMYEIAFPCVDOGESOFDPV2IRBO/graph.json","events_json":"https://pith.science/api/pith-number/MOMYEIAFPCVDOGESOFDPV2IRBO/events.json","paper":"https://pith.science/paper/MOMYEIAF"},"agent_actions":{"view_html":"https://pith.science/pith/MOMYEIAFPCVDOGESOFDPV2IRBO","download_json":"https://pith.science/pith/MOMYEIAFPCVDOGESOFDPV2IRBO.json","view_paper":"https://pith.science/paper/MOMYEIAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28490&json=true","fetch_graph":"https://pith.science/api/pith-number/MOMYEIAFPCVDOGESOFDPV2IRBO/graph.json","fetch_events":"https://pith.science/api/pith-number/MOMYEIAFPCVDOGESOFDPV2IRBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOMYEIAFPCVDOGESOFDPV2IRBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOMYEIAFPCVDOGESOFDPV2IRBO/action/storage_attestation","attest_author":"https://pith.science/pith/MOMYEIAFPCVDOGESOFDPV2IRBO/action/author_attestation","sign_citation":"https://pith.science/pith/MOMYEIAFPCVDOGESOFDPV2IRBO/action/citation_signature","submit_replication":"https://pith.science/pith/MOMYEIAFPCVDOGESOFDPV2IRBO/action/replication_record"}},"created_at":"2026-05-28T02:04:54.409377+00:00","updated_at":"2026-05-28T02:04:54.409377+00:00"}