{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DG7FRR2D5IN2SEYL2IQEYRW5VU","short_pith_number":"pith:DG7FRR2D","schema_version":"1.0","canonical_sha256":"19be58c743ea1ba9130bd2204c46ddad2493de1bb0bb8cb866a3f566b6885fec","source":{"kind":"arxiv","id":"2503.11345","version":1},"attestation_state":"computed","paper":{"title":"EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Li, Guanbin Li, Guangming Shi, Jiahao Chen, Jie Feng, Licheng Jiao, Weisheng Dong","submitted_at":"2025-03-14T12:21:26Z","abstract_excerpt":"Egocentric scenes exhibit frequent occlusions, varied viewpoints, and dynamic interactions compared to typical scene understanding tasks. Occlusions and varied viewpoints can lead to multi-view semantic inconsistencies, while dynamic objects may act as transient distractors, introducing artifacts into semantic feature modeling. To address these challenges, we propose EgoSplat, a language-embedded 3D Gaussian Splatting framework for open-vocabulary egocentric scene understanding. A multi-view consistent instance feature aggregation method is designed to leverage the segmentation and tracking ca"},"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":"2503.11345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T12:21:26Z","cross_cats_sorted":[],"title_canon_sha256":"9f6757391d6129e76c4b86e573059abb0564daedfa40c9b1b7728fef6836a3f0","abstract_canon_sha256":"7986b5ce37bb3a7f215fafda1af0077f886f319688680167a3e2d7cbd9198403"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:29.247353Z","signature_b64":"pOjqm9E2eRpeodIC6MnVNz3vVyUbjJZ5qsV32uPINBOX6DXoz4dmSG3vG+AjiLTM+M04sxqhjSU0ZLSesEd8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19be58c743ea1ba9130bd2204c46ddad2493de1bb0bb8cb866a3f566b6885fec","last_reissued_at":"2026-07-05T10:31:29.246842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:29.246842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Li, Guanbin Li, Guangming Shi, Jiahao Chen, Jie Feng, Licheng Jiao, Weisheng Dong","submitted_at":"2025-03-14T12:21:26Z","abstract_excerpt":"Egocentric scenes exhibit frequent occlusions, varied viewpoints, and dynamic interactions compared to typical scene understanding tasks. Occlusions and varied viewpoints can lead to multi-view semantic inconsistencies, while dynamic objects may act as transient distractors, introducing artifacts into semantic feature modeling. To address these challenges, we propose EgoSplat, a language-embedded 3D Gaussian Splatting framework for open-vocabulary egocentric scene understanding. A multi-view consistent instance feature aggregation method is designed to leverage the segmentation and tracking ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11345","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/2503.11345/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":"2503.11345","created_at":"2026-07-05T10:31:29.246907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11345v1","created_at":"2026-07-05T10:31:29.246907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11345","created_at":"2026-07-05T10:31:29.246907+00:00"},{"alias_kind":"pith_short_12","alias_value":"DG7FRR2D5IN2","created_at":"2026-07-05T10:31:29.246907+00:00"},{"alias_kind":"pith_short_16","alias_value":"DG7FRR2D5IN2SEYL","created_at":"2026-07-05T10:31:29.246907+00:00"},{"alias_kind":"pith_short_8","alias_value":"DG7FRR2D","created_at":"2026-07-05T10:31:29.246907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22439","citing_title":"NRGS: Neural Regularization for Robust 3D Semantic Gaussian Splatting","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13416","citing_title":"DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU","json":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU.json","graph_json":"https://pith.science/api/pith-number/DG7FRR2D5IN2SEYL2IQEYRW5VU/graph.json","events_json":"https://pith.science/api/pith-number/DG7FRR2D5IN2SEYL2IQEYRW5VU/events.json","paper":"https://pith.science/paper/DG7FRR2D"},"agent_actions":{"view_html":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU","download_json":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU.json","view_paper":"https://pith.science/paper/DG7FRR2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11345&json=true","fetch_graph":"https://pith.science/api/pith-number/DG7FRR2D5IN2SEYL2IQEYRW5VU/graph.json","fetch_events":"https://pith.science/api/pith-number/DG7FRR2D5IN2SEYL2IQEYRW5VU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU/action/storage_attestation","attest_author":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU/action/author_attestation","sign_citation":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU/action/citation_signature","submit_replication":"https://pith.science/pith/DG7FRR2D5IN2SEYL2IQEYRW5VU/action/replication_record"}},"created_at":"2026-07-05T10:31:29.246907+00:00","updated_at":"2026-07-05T10:31:29.246907+00:00"}