{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W2K32ELX6THYJMYEALR375CR2V","short_pith_number":"pith:W2K32ELX","schema_version":"1.0","canonical_sha256":"b695bd1177f4cf84b30402e3bff451d55b6510f46679fd39ed29bd1ed90ba1fd","source":{"kind":"arxiv","id":"2605.06088","version":2},"attestation_state":"computed","paper":{"title":"OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OpenGaFF models semantics as a continuous function of 3D Gaussian geometry to achieve spatially coherent open-vocabulary scene understanding.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Kunyi Li, Michael Niemeyer, Nassir Navab, Sen Wang, Stefano Gasperini","submitted_at":"2026-05-07T12:10:07Z","abstract_excerpt":"Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a novel framework for open-vocabulary 3D scene understanding built upon 3D Gaussian Splatting. At the core of our method is a Gaussian Feature Field that models semantics as a continuous function of Gaussian geometry and appearance. By explicitly conditioning semantic predictions on geometric structure, this formulation strengthens the coupling between geometry and se"},"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":"2605.06088","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-07T12:10:07Z","cross_cats_sorted":[],"title_canon_sha256":"3a7aa2b7f22f1ffae4a17cc0ef6fabd51c3e11955671f4404542581da69ff021","abstract_canon_sha256":"a43211dbf562e4f3cb60c1b1efbb12d14d3e5b2e8b143f0b81030cb329a23e4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:12.430917Z","signature_b64":"zsSEKXf4BS2mfLWecgA1UQphKDiTAo3yM51DpuEKMm0cA83ab1CO87YLjUulmY4OLjZPkrUPwtWdDnKGhx7wCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b695bd1177f4cf84b30402e3bff451d55b6510f46679fd39ed29bd1ed90ba1fd","last_reissued_at":"2026-05-20T00:02:12.429994Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:12.429994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"OpenGaFF models semantics as a continuous function of 3D Gaussian geometry to achieve spatially coherent open-vocabulary scene understanding.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Kunyi Li, Michael Niemeyer, Nassir Navab, Sen Wang, Stefano Gasperini","submitted_at":"2026-05-07T12:10:07Z","abstract_excerpt":"Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a novel framework for open-vocabulary 3D scene understanding built upon 3D Gaussian Splatting. At the core of our method is a Gaussian Feature Field that models semantics as a continuous function of Gaussian geometry and appearance. By explicitly conditioning semantic predictions on geometric structure, this formulation strengthens the coupling between geometry and se"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments on standard 2D and 3D open-vocabulary benchmarks demonstrate that our method consistently outperforms prior approaches, achieving improved segmentation quality, stronger 3D semantic consistency and a semantically interpretable codebook that provides insight into the learned representation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That explicitly conditioning semantic predictions on geometric structure will strengthen the coupling between geometry and semantics and thereby improve spatial coherence across similar structures in 3D space.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"OpenGaFF combines a geometry-conditioned Gaussian Feature Field with codebook-guided attention to deliver more spatially coherent open-vocabulary 3D semantic segmentation than prior methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"OpenGaFF models semantics as a continuous function of 3D Gaussian geometry to achieve spatially coherent open-vocabulary scene understanding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"42e8632cbe2ccd49b0f2ea1ae14a441ab86887ccc7f5e90d3b0f1e442814b536"},"source":{"id":"2605.06088","kind":"arxiv","version":2},"verdict":{"id":"3967e812-c76a-4ab8-8f02-1c839b5a92eb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T14:04:10.168160Z","strongest_claim":"Extensive experiments on standard 2D and 3D open-vocabulary benchmarks demonstrate that our method consistently outperforms prior approaches, achieving improved segmentation quality, stronger 3D semantic consistency and a semantically interpretable codebook that provides insight into the learned representation.","one_line_summary":"OpenGaFF combines a geometry-conditioned Gaussian Feature Field with codebook-guided attention to deliver more spatially coherent open-vocabulary 3D semantic segmentation than prior methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That explicitly conditioning semantic predictions on geometric structure will strengthen the coupling between geometry and semantics and thereby improve spatial coherence across similar structures in 3D space.","pith_extraction_headline":"OpenGaFF models semantics as a continuous function of 3D Gaussian geometry to achieve spatially coherent open-vocabulary scene understanding."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.06088/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.520813Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:57:10.665678Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6e1d78a92112d4200ae20b500cbc1d24fa40b8741aff3383b0a0b39fbcaa6717"},"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":"2605.06088","created_at":"2026-05-20T00:02:12.430160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.06088v2","created_at":"2026-05-20T00:02:12.430160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.06088","created_at":"2026-05-20T00:02:12.430160+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2K32ELX6THY","created_at":"2026-05-20T00:02:12.430160+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2K32ELX6THYJMYE","created_at":"2026-05-20T00:02:12.430160+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2K32ELX","created_at":"2026-05-20T00:02:12.430160+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/W2K32ELX6THYJMYEALR375CR2V","json":"https://pith.science/pith/W2K32ELX6THYJMYEALR375CR2V.json","graph_json":"https://pith.science/api/pith-number/W2K32ELX6THYJMYEALR375CR2V/graph.json","events_json":"https://pith.science/api/pith-number/W2K32ELX6THYJMYEALR375CR2V/events.json","paper":"https://pith.science/paper/W2K32ELX"},"agent_actions":{"view_html":"https://pith.science/pith/W2K32ELX6THYJMYEALR375CR2V","download_json":"https://pith.science/pith/W2K32ELX6THYJMYEALR375CR2V.json","view_paper":"https://pith.science/paper/W2K32ELX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.06088&json=true","fetch_graph":"https://pith.science/api/pith-number/W2K32ELX6THYJMYEALR375CR2V/graph.json","fetch_events":"https://pith.science/api/pith-number/W2K32ELX6THYJMYEALR375CR2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2K32ELX6THYJMYEALR375CR2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2K32ELX6THYJMYEALR375CR2V/action/storage_attestation","attest_author":"https://pith.science/pith/W2K32ELX6THYJMYEALR375CR2V/action/author_attestation","sign_citation":"https://pith.science/pith/W2K32ELX6THYJMYEALR375CR2V/action/citation_signature","submit_replication":"https://pith.science/pith/W2K32ELX6THYJMYEALR375CR2V/action/replication_record"}},"created_at":"2026-05-20T00:02:12.430160+00:00","updated_at":"2026-05-20T00:02:12.430160+00:00"}