{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUZUNLT4QHQSSK2SN5TI264FDM","short_pith_number":"pith:NUZUNLT4","schema_version":"1.0","canonical_sha256":"6d3346ae7c81e1292b526f668d7b851b2b6816d6dc55cd473a548276df868ff5","source":{"kind":"arxiv","id":"2605.22558","version":1},"attestation_state":"computed","paper":{"title":"GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deshui Miao, Haijun Zhang, Ming-Hsuan Yang, Xingsen Huang, Xin Li, Yameng Gu","submitted_at":"2026-05-21T14:40:03Z","abstract_excerpt":"Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models incorporate geometric information through structural branches, 3D-aware supervision, reasoning-stage fusion, or long-horizon memory. While these approaches demonstrate the importance of geometry for spatial intelligence, they typically treat geometric cues as a shared signal across all visual tokens. We note that this overlooks a finer-grained challenge: different visual tokens require different geometric evidence d"},"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":"2605.22558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T14:40:03Z","cross_cats_sorted":[],"title_canon_sha256":"aff00ab4e1a3c1e9f28fb56ffdf1d8252196919fe09d6ee4688611c1312dde51","abstract_canon_sha256":"4bff876e18fb8e31768b56b0b83ec93442764e215ad2aa3e584dcd0a23b318fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:57.293550Z","signature_b64":"2SdeqJzZEw4MM4K3dKESeuAfY4S6jFDvcnOvs5+E8wI5qDpM0xKsJjjqwHsgVo6yr4QZBApSBan8tv1yQBhHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d3346ae7c81e1292b526f668d7b851b2b6816d6dc55cd473a548276df868ff5","last_reissued_at":"2026-05-22T01:04:57.292808Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:57.292808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deshui Miao, Haijun Zhang, Ming-Hsuan Yang, Xingsen Huang, Xin Li, Yameng Gu","submitted_at":"2026-05-21T14:40:03Z","abstract_excerpt":"Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearance. Recent multimodal models incorporate geometric information through structural branches, 3D-aware supervision, reasoning-stage fusion, or long-horizon memory. While these approaches demonstrate the importance of geometry for spatial intelligence, they typically treat geometric cues as a shared signal across all visual tokens. We note that this overlooks a finer-grained challenge: different visual tokens require different geometric evidence d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22558","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/2605.22558/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":"2605.22558","created_at":"2026-05-22T01:04:57.292922+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22558v1","created_at":"2026-05-22T01:04:57.292922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22558","created_at":"2026-05-22T01:04:57.292922+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUZUNLT4QHQS","created_at":"2026-05-22T01:04:57.292922+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUZUNLT4QHQSSK2S","created_at":"2026-05-22T01:04:57.292922+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUZUNLT4","created_at":"2026-05-22T01:04:57.292922+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/NUZUNLT4QHQSSK2SN5TI264FDM","json":"https://pith.science/pith/NUZUNLT4QHQSSK2SN5TI264FDM.json","graph_json":"https://pith.science/api/pith-number/NUZUNLT4QHQSSK2SN5TI264FDM/graph.json","events_json":"https://pith.science/api/pith-number/NUZUNLT4QHQSSK2SN5TI264FDM/events.json","paper":"https://pith.science/paper/NUZUNLT4"},"agent_actions":{"view_html":"https://pith.science/pith/NUZUNLT4QHQSSK2SN5TI264FDM","download_json":"https://pith.science/pith/NUZUNLT4QHQSSK2SN5TI264FDM.json","view_paper":"https://pith.science/paper/NUZUNLT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22558&json=true","fetch_graph":"https://pith.science/api/pith-number/NUZUNLT4QHQSSK2SN5TI264FDM/graph.json","fetch_events":"https://pith.science/api/pith-number/NUZUNLT4QHQSSK2SN5TI264FDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUZUNLT4QHQSSK2SN5TI264FDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUZUNLT4QHQSSK2SN5TI264FDM/action/storage_attestation","attest_author":"https://pith.science/pith/NUZUNLT4QHQSSK2SN5TI264FDM/action/author_attestation","sign_citation":"https://pith.science/pith/NUZUNLT4QHQSSK2SN5TI264FDM/action/citation_signature","submit_replication":"https://pith.science/pith/NUZUNLT4QHQSSK2SN5TI264FDM/action/replication_record"}},"created_at":"2026-05-22T01:04:57.292922+00:00","updated_at":"2026-05-22T01:04:57.292922+00:00"}