{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JSFQXEAXH5FKR7EFFRIGK5PQAY","short_pith_number":"pith:JSFQXEAX","schema_version":"1.0","canonical_sha256":"4c8b0b90173f4aa8fc852c506575f0063133a74de9a46ef8567791b8663186c7","source":{"kind":"arxiv","id":"2607.21595","version":1},"attestation_state":"computed","paper":{"title":"3D-Aware VLMs with Implicit and Explicit Geometries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Gongjie Zhang, Quanhao Qian, Ran Xu, Shijian Lu, Wenhao Li, Xueying Jiang","submitted_at":"2026-07-23T17:59:59Z","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"},"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":"2607.21595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T17:59:59Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"21f2f87b9d6e6def2b080755f1a922161bf72c0edbd22feb91fdfa4ba12eadec","abstract_canon_sha256":"aa484de1c8e1b53a7b3a88affd673fb05d553cc09d658d3d9d252712fd8073bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:42.046880Z","signature_b64":"BUnvNbHF5YzaPJprPFRnQdiN7Ar5llRludAaqR701uwpjof7GZfUMM4g9emN5zeNXQEGzUG3XJ6UIJQGFMp1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c8b0b90173f4aa8fc852c506575f0063133a74de9a46ef8567791b8663186c7","last_reissued_at":"2026-07-24T01:24:42.046034Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:42.046034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-Aware VLMs with Implicit and Explicit Geometries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Gongjie Zhang, Quanhao Qian, Ran Xu, Shijian Lu, Wenhao Li, Xueying Jiang","submitted_at":"2026-07-23T17:59:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21595","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/2607.21595/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":"2607.21595","created_at":"2026-07-24T01:24:42.046475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21595v1","created_at":"2026-07-24T01:24:42.046475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21595","created_at":"2026-07-24T01:24:42.046475+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSFQXEAXH5FK","created_at":"2026-07-24T01:24:42.046475+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSFQXEAXH5FKR7EF","created_at":"2026-07-24T01:24:42.046475+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSFQXEAX","created_at":"2026-07-24T01:24:42.046475+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/JSFQXEAXH5FKR7EFFRIGK5PQAY","json":"https://pith.science/pith/JSFQXEAXH5FKR7EFFRIGK5PQAY.json","graph_json":"https://pith.science/api/pith-number/JSFQXEAXH5FKR7EFFRIGK5PQAY/graph.json","events_json":"https://pith.science/api/pith-number/JSFQXEAXH5FKR7EFFRIGK5PQAY/events.json","paper":"https://pith.science/paper/JSFQXEAX"},"agent_actions":{"view_html":"https://pith.science/pith/JSFQXEAXH5FKR7EFFRIGK5PQAY","download_json":"https://pith.science/pith/JSFQXEAXH5FKR7EFFRIGK5PQAY.json","view_paper":"https://pith.science/paper/JSFQXEAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21595&json=true","fetch_graph":"https://pith.science/api/pith-number/JSFQXEAXH5FKR7EFFRIGK5PQAY/graph.json","fetch_events":"https://pith.science/api/pith-number/JSFQXEAXH5FKR7EFFRIGK5PQAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSFQXEAXH5FKR7EFFRIGK5PQAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSFQXEAXH5FKR7EFFRIGK5PQAY/action/storage_attestation","attest_author":"https://pith.science/pith/JSFQXEAXH5FKR7EFFRIGK5PQAY/action/author_attestation","sign_citation":"https://pith.science/pith/JSFQXEAXH5FKR7EFFRIGK5PQAY/action/citation_signature","submit_replication":"https://pith.science/pith/JSFQXEAXH5FKR7EFFRIGK5PQAY/action/replication_record"}},"created_at":"2026-07-24T01:24:42.046475+00:00","updated_at":"2026-07-24T01:24:42.046475+00:00"}