{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5K73IYMEDR653LBHSXBS6LNRYQ","short_pith_number":"pith:5K73IYME","schema_version":"1.0","canonical_sha256":"eabfb461841c7dddac2795c32f2db1c421eea80c78bc020e24908a84c2025f8d","source":{"kind":"arxiv","id":"2404.03650","version":1},"attestation_state":"computed","paper":{"title":"OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabian Manhardt, Federico Tombari, Francis Engelmann, Keisuke Tateno, Marc Pollefeys, Michael Niemeyer","submitted_at":"2024-04-04T17:59:08Z","abstract_excerpt":"Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only segment classes from a pre-defined training set. More recently, first works on open-set segmentation in 3D scenes have appeared in the literature. These methods are heavily influenced by closed-set 3D convolutional approaches that process point clouds or polygon meshes. However, these 3D scene representations do not align well with the image-based nature of the vi"},"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":"2404.03650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T17:59:08Z","cross_cats_sorted":[],"title_canon_sha256":"7cd5908a9b4f4a7f81a116a6f056b7cdaeee4937cfdcc47005b1e52cf86f7cdc","abstract_canon_sha256":"8521e5f4dbe8ac33995b3d14025ada0023bbd6dfda8eff73ded1f1f6c1ad37de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:28.778898Z","signature_b64":"TznShfsHS/AkwCKfCT/+8m5MOtpiv3DloUmGefT8Fe5QUjA4AN0sA+BZGQ2oXnCOOSQx3/JmUJ5glY4/ha6lDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eabfb461841c7dddac2795c32f2db1c421eea80c78bc020e24908a84c2025f8d","last_reissued_at":"2026-07-05T08:04:28.778435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:28.778435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fabian Manhardt, Federico Tombari, Francis Engelmann, Keisuke Tateno, Marc Pollefeys, Michael Niemeyer","submitted_at":"2024-04-04T17:59:08Z","abstract_excerpt":"Large visual-language models (VLMs), like CLIP, enable open-set image segmentation to segment arbitrary concepts from an image in a zero-shot manner. This goes beyond the traditional closed-set assumption, i.e., where models can only segment classes from a pre-defined training set. More recently, first works on open-set segmentation in 3D scenes have appeared in the literature. These methods are heavily influenced by closed-set 3D convolutional approaches that process point clouds or polygon meshes. However, these 3D scene representations do not align well with the image-based nature of the vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03650","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/2404.03650/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":"2404.03650","created_at":"2026-07-05T08:04:28.778493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03650v1","created_at":"2026-07-05T08:04:28.778493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03650","created_at":"2026-07-05T08:04:28.778493+00:00"},{"alias_kind":"pith_short_12","alias_value":"5K73IYMEDR65","created_at":"2026-07-05T08:04:28.778493+00:00"},{"alias_kind":"pith_short_16","alias_value":"5K73IYMEDR653LBH","created_at":"2026-07-05T08:04:28.778493+00:00"},{"alias_kind":"pith_short_8","alias_value":"5K73IYME","created_at":"2026-07-05T08:04:28.778493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08980","citing_title":"EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01140","citing_title":"Relation-Centric Open-Vocabulary 3D Gaussian Segmentation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08925","citing_title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08831","citing_title":"3AM: 3egment Anything with Geometric Consistency in Videos","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08925","citing_title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ","json":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ.json","graph_json":"https://pith.science/api/pith-number/5K73IYMEDR653LBHSXBS6LNRYQ/graph.json","events_json":"https://pith.science/api/pith-number/5K73IYMEDR653LBHSXBS6LNRYQ/events.json","paper":"https://pith.science/paper/5K73IYME"},"agent_actions":{"view_html":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ","download_json":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ.json","view_paper":"https://pith.science/paper/5K73IYME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03650&json=true","fetch_graph":"https://pith.science/api/pith-number/5K73IYMEDR653LBHSXBS6LNRYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5K73IYMEDR653LBHSXBS6LNRYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ/action/storage_attestation","attest_author":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ/action/author_attestation","sign_citation":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ/action/citation_signature","submit_replication":"https://pith.science/pith/5K73IYMEDR653LBHSXBS6LNRYQ/action/replication_record"}},"created_at":"2026-07-05T08:04:28.778493+00:00","updated_at":"2026-07-05T08:04:28.778493+00:00"}