{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5M7FWEMWEK2YFM6GPLWPD5RCST","short_pith_number":"pith:5M7FWEMW","schema_version":"1.0","canonical_sha256":"eb3e5b119622b582b3c67aecf1f62294d4005b36e76aa7b0b26d92e7aa25060f","source":{"kind":"arxiv","id":"2606.29376","version":1},"attestation_state":"computed","paper":{"title":"SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlu Zhan, Gaoang Wang, Hongwei Wang, Yufei Zhang","submitted_at":"2026-06-28T12:52:46Z","abstract_excerpt":"Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce boundary leakage and identity switches. Directly optimizing against these unreliable 2D targets forces the 3D representation to absorb multi-view contradictions, leading to severe error accumulation. To resolve this limitation, we propose SAD-GS, a framework for learning reliable 3D semantic Gaussian fields via dynami"},"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":"2606.29376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-28T12:52:46Z","cross_cats_sorted":[],"title_canon_sha256":"63ee9db3c8fd1d703275cadaa512e166f957000f522d4d32a77edeef4469ed38","abstract_canon_sha256":"537cd9c3e4bba5ac32fb14844179d5efe52220abd108e189074670ca346e93d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:03.467016Z","signature_b64":"bd7eXwYeEygQ7q0/V/ODf+Vb1d/qSDVJSkOKlb979Me/iLmBCE6qJtbTEU7vDEeFGscRekbuS8mnDB5Hog9LBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb3e5b119622b582b3c67aecf1f62294d4005b36e76aa7b0b26d92e7aa25060f","last_reissued_at":"2026-06-30T01:18:03.466422Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:03.466422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenlu Zhan, Gaoang Wang, Hongwei Wang, Yufei Zhang","submitted_at":"2026-06-28T12:52:46Z","abstract_excerpt":"Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce boundary leakage and identity switches. Directly optimizing against these unreliable 2D targets forces the 3D representation to absorb multi-view contradictions, leading to severe error accumulation. To resolve this limitation, we propose SAD-GS, a framework for learning reliable 3D semantic Gaussian fields via dynami"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29376","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/2606.29376/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":"2606.29376","created_at":"2026-06-30T01:18:03.466503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29376v1","created_at":"2026-06-30T01:18:03.466503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29376","created_at":"2026-06-30T01:18:03.466503+00:00"},{"alias_kind":"pith_short_12","alias_value":"5M7FWEMWEK2Y","created_at":"2026-06-30T01:18:03.466503+00:00"},{"alias_kind":"pith_short_16","alias_value":"5M7FWEMWEK2YFM6G","created_at":"2026-06-30T01:18:03.466503+00:00"},{"alias_kind":"pith_short_8","alias_value":"5M7FWEMW","created_at":"2026-06-30T01:18:03.466503+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/5M7FWEMWEK2YFM6GPLWPD5RCST","json":"https://pith.science/pith/5M7FWEMWEK2YFM6GPLWPD5RCST.json","graph_json":"https://pith.science/api/pith-number/5M7FWEMWEK2YFM6GPLWPD5RCST/graph.json","events_json":"https://pith.science/api/pith-number/5M7FWEMWEK2YFM6GPLWPD5RCST/events.json","paper":"https://pith.science/paper/5M7FWEMW"},"agent_actions":{"view_html":"https://pith.science/pith/5M7FWEMWEK2YFM6GPLWPD5RCST","download_json":"https://pith.science/pith/5M7FWEMWEK2YFM6GPLWPD5RCST.json","view_paper":"https://pith.science/paper/5M7FWEMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29376&json=true","fetch_graph":"https://pith.science/api/pith-number/5M7FWEMWEK2YFM6GPLWPD5RCST/graph.json","fetch_events":"https://pith.science/api/pith-number/5M7FWEMWEK2YFM6GPLWPD5RCST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5M7FWEMWEK2YFM6GPLWPD5RCST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5M7FWEMWEK2YFM6GPLWPD5RCST/action/storage_attestation","attest_author":"https://pith.science/pith/5M7FWEMWEK2YFM6GPLWPD5RCST/action/author_attestation","sign_citation":"https://pith.science/pith/5M7FWEMWEK2YFM6GPLWPD5RCST/action/citation_signature","submit_replication":"https://pith.science/pith/5M7FWEMWEK2YFM6GPLWPD5RCST/action/replication_record"}},"created_at":"2026-06-30T01:18:03.466503+00:00","updated_at":"2026-06-30T01:18:03.466503+00:00"}