{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JSFQXEAXH5FKR7EFFRIGK5PQAY","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":"aa484de1c8e1b53a7b3a88affd673fb05d553cc09d658d3d9d252712fd8073bf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T17:59:59Z","title_canon_sha256":"21f2f87b9d6e6def2b080755f1a922161bf72c0edbd22feb91fdfa4ba12eadec"},"schema_version":"1.0","source":{"id":"2607.21595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21595","created_at":"2026-07-24T01:24:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21595v1","created_at":"2026-07-24T01:24:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21595","created_at":"2026-07-24T01:24:42Z"},{"alias_kind":"pith_short_12","alias_value":"JSFQXEAXH5FK","created_at":"2026-07-24T01:24:42Z"},{"alias_kind":"pith_short_16","alias_value":"JSFQXEAXH5FKR7EF","created_at":"2026-07-24T01:24:42Z"},{"alias_kind":"pith_short_8","alias_value":"JSFQXEAX","created_at":"2026-07-24T01:24:42Z"}],"graph_snapshots":[{"event_id":"sha256:4d45b10691904e12df463eb0a815555ccdd9edddde4be77fea39aa134b29b0c5","target":"graph","created_at":"2026-07-24T01:24:42Z","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/2607.21595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning. To bridge this gap, we present VLM-IE3D, a unified framework that enhances the 3D spatial awareness of VLMs by equipping them with both implicit and explicit 3D geometries learned from RGB videos. Our VLM-IE3D introduces Implicit Geometry Tokens (IGTs) that capture high-level geometric priors from input videos, as well as complementary Explicit Geometry Tokens (EGTs) that encode detailed geom","authors_text":"Deli Zhao, Gongjie Zhang, Quanhao Qian, Ran Xu, Shijian Lu, Wenhao Li, Xueying Jiang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T17:59:59Z","title":"3D-Aware VLMs with Implicit and Explicit Geometries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21595","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":"sha256:7de67935f13a841cc4cea5fb76967399dc0d1bae39cb30fa99fa50bef1cd4804","target":"record","created_at":"2026-07-24T01:24:42Z","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":"aa484de1c8e1b53a7b3a88affd673fb05d553cc09d658d3d9d252712fd8073bf","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T17:59:59Z","title_canon_sha256":"21f2f87b9d6e6def2b080755f1a922161bf72c0edbd22feb91fdfa4ba12eadec"},"schema_version":"1.0","source":{"id":"2607.21595","kind":"arxiv","version":1}},"canonical_sha256":"4c8b0b90173f4aa8fc852c506575f0063133a74de9a46ef8567791b8663186c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c8b0b90173f4aa8fc852c506575f0063133a74de9a46ef8567791b8663186c7","first_computed_at":"2026-07-24T01:24:42.046034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:24:42.046034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BUnvNbHF5YzaPJprPFRnQdiN7Ar5llRludAaqR701uwpjof7GZfUMM4g9emN5zeNXQEGzUG3XJ6UIJQGFMp1Dg==","signature_status":"signed_v1","signed_at":"2026-07-24T01:24:42.046880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7de67935f13a841cc4cea5fb76967399dc0d1bae39cb30fa99fa50bef1cd4804","sha256:4d45b10691904e12df463eb0a815555ccdd9edddde4be77fea39aa134b29b0c5"],"state_sha256":"1e121a660055395a10833c71ddbc1893a70617000d5ac6015bbcba81e765be0a"}