{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YDMHNW6EEP4P3GC2SEWTES273O","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":"11acb384a69cd642f1da139265d123ef5961e661817619bbde6ece0eeb5edab9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:33:19Z","title_canon_sha256":"c685cbea457371b71af00cb52b94184a349975ed01cec9282859f23f543d29e6"},"schema_version":"1.0","source":{"id":"2605.25334","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25334","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25334v1","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25334","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"YDMHNW6EEP4P","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"YDMHNW6EEP4P3GC2","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"YDMHNW6E","created_at":"2026-05-26T02:04:29Z"}],"graph_snapshots":[{"event_id":"sha256:2968b123bae23aa14efe2ac8bb6ba33d2b2bdd1df21a5e7d75dc4fd0de41066e","target":"graph","created_at":"2026-05-26T02:04:29Z","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/2605.25334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial understanding of the physical world from 2D visual inputs hinges on two complementary forms of geometric knowledge: holistic 3D structural perception and fine-grained metric scale estimation. Existing multimodal large language models (MLLMs) typically address only one facet, ingesting either depth maps or point clouds as additional model inputs, which incurs substantial computational overhead and inherits the generalization limitations of upstream prediction models. We propose GAMSI, a dual-pathway Geometry-Aware MLLM for Spatial Intelligence that takes only RGB images as input while i","authors_text":"Chenfeng Wang, Chunpeng Zhou, Jiawei Liu, Pengfei Yu, Wei Zhai, Xuhan Zhu, Yang Cao, Yongchao Xu, Yufei Zheng, Yunnan Wang, Zheng-Jun Zha, Zide Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:33:19Z","title":"Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25334","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":"sha256:83be0e690ed4d18a71c1911046dea78950134824ad4f12b1a9afabef95b315ae","target":"record","created_at":"2026-05-26T02:04:29Z","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":"11acb384a69cd642f1da139265d123ef5961e661817619bbde6ece0eeb5edab9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:33:19Z","title_canon_sha256":"c685cbea457371b71af00cb52b94184a349975ed01cec9282859f23f543d29e6"},"schema_version":"1.0","source":{"id":"2605.25334","kind":"arxiv","version":1}},"canonical_sha256":"c0d876dbc423f8fd985a912d324b5fdb87a68131bebe5ba60805dcf8ddb57112","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0d876dbc423f8fd985a912d324b5fdb87a68131bebe5ba60805dcf8ddb57112","first_computed_at":"2026-05-26T02:04:29.398757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:29.398757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e6aia5povwA9v+lv1xzJ3twqFMJPDwb6/25VJbzW1htN4e2fcApcsxrZK/RMwaqPry5R8EysF3Ybro+6yzLZBw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:29.399259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25334","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83be0e690ed4d18a71c1911046dea78950134824ad4f12b1a9afabef95b315ae","sha256:2968b123bae23aa14efe2ac8bb6ba33d2b2bdd1df21a5e7d75dc4fd0de41066e"],"state_sha256":"5da799e40a9f92a34df35407e034218aa0f5925e432d7e5cca120509e58d52ae"}