{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5KWM7HPCLKOYYTF4NA6LWQOPHO","short_pith_number":"pith:5KWM7HPC","schema_version":"1.0","canonical_sha256":"eaaccf9de25a9d8c4cbc683cbb41cf3bb3a3761950334b220dd1ec938db9f2fa","source":{"kind":"arxiv","id":"2401.05925","version":4},"attestation_state":"computed","paper":{"title":"Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Dou, Tianyu Zhang, Yongjia Ma, Zejian Yuan, Zhaohui Wang","submitted_at":"2024-01-11T14:05:01Z","abstract_excerpt":"Zero-shot neural scene segmentation, which reconstructs 3D neural segmentation field without manual annotations, serves as an effective way for scene understanding. However, existing models, especially the efficient 3D Gaussian-based methods, struggle to produce compact segmentation results. This issue stems primarily from their redundant learnable attributes assigned on individual Gaussians, leading to a lack of robustness against the 3D-inconsistencies in zero-shot generated raw labels. To address this problem, our work, named Compact Segmented 3D Gaussians (CoSegGaussians), proposes the Fea"},"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":"2401.05925","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-11T14:05:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38f716d75ba079e12b35557bdadacd837b14949777aa4101584cb6d638f6347d","abstract_canon_sha256":"6dc108e9f3305b2e4783e1c392bfee326d83323716b7728ba8ce9c54582283aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:27.888334Z","signature_b64":"ilymr6rnctRbvWhwtQSned4UYaDz2DV6eB9cWBE6ceebufoBezbPHtsrDQh8lahEFzsEPZDF3WmZMk0Bvc7jCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaaccf9de25a9d8c4cbc683cbb41cf3bb3a3761950334b220dd1ec938db9f2fa","last_reissued_at":"2026-07-05T08:49:27.887859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:27.887859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Dou, Tianyu Zhang, Yongjia Ma, Zejian Yuan, Zhaohui Wang","submitted_at":"2024-01-11T14:05:01Z","abstract_excerpt":"Zero-shot neural scene segmentation, which reconstructs 3D neural segmentation field without manual annotations, serves as an effective way for scene understanding. However, existing models, especially the efficient 3D Gaussian-based methods, struggle to produce compact segmentation results. This issue stems primarily from their redundant learnable attributes assigned on individual Gaussians, leading to a lack of robustness against the 3D-inconsistencies in zero-shot generated raw labels. To address this problem, our work, named Compact Segmented 3D Gaussians (CoSegGaussians), proposes the Fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05925","kind":"arxiv","version":4},"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/2401.05925/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":"2401.05925","created_at":"2026-07-05T08:49:27.887918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05925v4","created_at":"2026-07-05T08:49:27.887918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05925","created_at":"2026-07-05T08:49:27.887918+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KWM7HPCLKOY","created_at":"2026-07-05T08:49:27.887918+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KWM7HPCLKOYYTF4","created_at":"2026-07-05T08:49:27.887918+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KWM7HPC","created_at":"2026-07-05T08:49:27.887918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09176","citing_title":"LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO","json":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO.json","graph_json":"https://pith.science/api/pith-number/5KWM7HPCLKOYYTF4NA6LWQOPHO/graph.json","events_json":"https://pith.science/api/pith-number/5KWM7HPCLKOYYTF4NA6LWQOPHO/events.json","paper":"https://pith.science/paper/5KWM7HPC"},"agent_actions":{"view_html":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO","download_json":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO.json","view_paper":"https://pith.science/paper/5KWM7HPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05925&json=true","fetch_graph":"https://pith.science/api/pith-number/5KWM7HPCLKOYYTF4NA6LWQOPHO/graph.json","fetch_events":"https://pith.science/api/pith-number/5KWM7HPCLKOYYTF4NA6LWQOPHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO/action/storage_attestation","attest_author":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO/action/author_attestation","sign_citation":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO/action/citation_signature","submit_replication":"https://pith.science/pith/5KWM7HPCLKOYYTF4NA6LWQOPHO/action/replication_record"}},"created_at":"2026-07-05T08:49:27.887918+00:00","updated_at":"2026-07-05T08:49:27.887918+00:00"}