{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NI4PV7BYYCBXH4IST6NBKIH47H","short_pith_number":"pith:NI4PV7BY","schema_version":"1.0","canonical_sha256":"6a38fafc38c08373f1129f9a1520fcf9d68df7611124d70fe2484b0de9f43b7b","source":{"kind":"arxiv","id":"2303.10962","version":1},"attestation_state":"computed","paper":{"title":"Neural Implicit Vision-Language Feature Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Francesco Milano, Jen Jen Chung, Kenneth Blomqvist, Lionel Ott, Roland Siegwart","submitted_at":"2023-03-20T09:38:09Z","abstract_excerpt":"Recently, groundbreaking results have been presented on open-vocabulary semantic image segmentation. Such methods segment each pixel in an image into arbitrary categories provided at run-time in the form of text prompts, as opposed to a fixed set of classes defined at training time. In this work, we present a zero-shot volumetric open-vocabulary semantic scene segmentation method. Our method builds on the insight that we can fuse image features from a vision-language model into a neural implicit representation. We show that the resulting feature field can be segmented into different classes by"},"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":"2303.10962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-20T09:38:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"7c996a5b2eb9c235238afa5c2fd93fd6b5d46e83c6ca645354e4da01c6ddda86","abstract_canon_sha256":"3b4c08a821f19b073b301121f9f148627dbe64098fc707f73f5bfd5cc0872804"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:38.744217Z","signature_b64":"/Jbuit4drGV7GN3RSTmUkS+uQKE4vcuFSnRRjWMcQ5sw3cZ9TJxPKiEEdoQDv5T7BW00IRTGnxpwGYdNgaf6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a38fafc38c08373f1129f9a1520fcf9d68df7611124d70fe2484b0de9f43b7b","last_reissued_at":"2026-07-05T05:52:38.743878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:38.743878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Implicit Vision-Language Feature Fields","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Francesco Milano, Jen Jen Chung, Kenneth Blomqvist, Lionel Ott, Roland Siegwart","submitted_at":"2023-03-20T09:38:09Z","abstract_excerpt":"Recently, groundbreaking results have been presented on open-vocabulary semantic image segmentation. Such methods segment each pixel in an image into arbitrary categories provided at run-time in the form of text prompts, as opposed to a fixed set of classes defined at training time. In this work, we present a zero-shot volumetric open-vocabulary semantic scene segmentation method. Our method builds on the insight that we can fuse image features from a vision-language model into a neural implicit representation. We show that the resulting feature field can be segmented into different classes by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10962","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/2303.10962/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":"2303.10962","created_at":"2026-07-05T05:52:38.743934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10962v1","created_at":"2026-07-05T05:52:38.743934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10962","created_at":"2026-07-05T05:52:38.743934+00:00"},{"alias_kind":"pith_short_12","alias_value":"NI4PV7BYYCBX","created_at":"2026-07-05T05:52:38.743934+00:00"},{"alias_kind":"pith_short_16","alias_value":"NI4PV7BYYCBXH4IS","created_at":"2026-07-05T05:52:38.743934+00:00"},{"alias_kind":"pith_short_8","alias_value":"NI4PV7BY","created_at":"2026-07-05T05:52:38.743934+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/NI4PV7BYYCBXH4IST6NBKIH47H","json":"https://pith.science/pith/NI4PV7BYYCBXH4IST6NBKIH47H.json","graph_json":"https://pith.science/api/pith-number/NI4PV7BYYCBXH4IST6NBKIH47H/graph.json","events_json":"https://pith.science/api/pith-number/NI4PV7BYYCBXH4IST6NBKIH47H/events.json","paper":"https://pith.science/paper/NI4PV7BY"},"agent_actions":{"view_html":"https://pith.science/pith/NI4PV7BYYCBXH4IST6NBKIH47H","download_json":"https://pith.science/pith/NI4PV7BYYCBXH4IST6NBKIH47H.json","view_paper":"https://pith.science/paper/NI4PV7BY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10962&json=true","fetch_graph":"https://pith.science/api/pith-number/NI4PV7BYYCBXH4IST6NBKIH47H/graph.json","fetch_events":"https://pith.science/api/pith-number/NI4PV7BYYCBXH4IST6NBKIH47H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NI4PV7BYYCBXH4IST6NBKIH47H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NI4PV7BYYCBXH4IST6NBKIH47H/action/storage_attestation","attest_author":"https://pith.science/pith/NI4PV7BYYCBXH4IST6NBKIH47H/action/author_attestation","sign_citation":"https://pith.science/pith/NI4PV7BYYCBXH4IST6NBKIH47H/action/citation_signature","submit_replication":"https://pith.science/pith/NI4PV7BYYCBXH4IST6NBKIH47H/action/replication_record"}},"created_at":"2026-07-05T05:52:38.743934+00:00","updated_at":"2026-07-05T05:52:38.743934+00:00"}