{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2K6SHYXLW37LRFGXOIMJJM7ACU","short_pith_number":"pith:2K6SHYXL","schema_version":"1.0","canonical_sha256":"d2bd23e2ebb6feb894d7721894b3e0150f122028f4fc974c17146e27a3ffb2de","source":{"kind":"arxiv","id":"2305.12427","version":2},"attestation_state":"computed","paper":{"title":"VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chris Xiaoxuan Lu, Nikolaos Tsagkas, Oisin Mac Aodha","submitted_at":"2023-05-21T10:55:27Z","abstract_excerpt":"We present Visual-Language Fields (VL-Fields), a neural implicit spatial representation that enables open-vocabulary semantic queries. Our model encodes and fuses the geometry of a scene with vision-language trained latent features by distilling information from a language-driven segmentation model. VL-Fields is trained without requiring any prior knowledge of the scene object classes, which makes it a promising representation for the field of robotics. Our model outperformed the similar CLIP-Fields model in the task of semantic segmentation by almost 10%."},"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":"2305.12427","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-21T10:55:27Z","cross_cats_sorted":[],"title_canon_sha256":"182e3bc540db194bbd3823a9611a3ee8ea6effe9bb213e1d1d3ce971d7b18e22","abstract_canon_sha256":"4e6c7262771841b0ed249b8d53b10a23531d14dc80a6a60f743512fc7812dcbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:39.965059Z","signature_b64":"W9lM+tf6ln/yfiNUBVvDCNaO+gjT8gTi+l55IdtjU8BKPiru29XSFKPavABu5aFwRJV1r4LMuMWsIRg+cgHeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2bd23e2ebb6feb894d7721894b3e0150f122028f4fc974c17146e27a3ffb2de","last_reissued_at":"2026-07-05T06:13:39.964585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:39.964585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chris Xiaoxuan Lu, Nikolaos Tsagkas, Oisin Mac Aodha","submitted_at":"2023-05-21T10:55:27Z","abstract_excerpt":"We present Visual-Language Fields (VL-Fields), a neural implicit spatial representation that enables open-vocabulary semantic queries. Our model encodes and fuses the geometry of a scene with vision-language trained latent features by distilling information from a language-driven segmentation model. VL-Fields is trained without requiring any prior knowledge of the scene object classes, which makes it a promising representation for the field of robotics. Our model outperformed the similar CLIP-Fields model in the task of semantic segmentation by almost 10%."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12427","kind":"arxiv","version":2},"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/2305.12427/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":"2305.12427","created_at":"2026-07-05T06:13:39.964640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12427v2","created_at":"2026-07-05T06:13:39.964640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12427","created_at":"2026-07-05T06:13:39.964640+00:00"},{"alias_kind":"pith_short_12","alias_value":"2K6SHYXLW37L","created_at":"2026-07-05T06:13:39.964640+00:00"},{"alias_kind":"pith_short_16","alias_value":"2K6SHYXLW37LRFGX","created_at":"2026-07-05T06:13:39.964640+00:00"},{"alias_kind":"pith_short_8","alias_value":"2K6SHYXL","created_at":"2026-07-05T06:13:39.964640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04837","citing_title":"OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU","json":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU.json","graph_json":"https://pith.science/api/pith-number/2K6SHYXLW37LRFGXOIMJJM7ACU/graph.json","events_json":"https://pith.science/api/pith-number/2K6SHYXLW37LRFGXOIMJJM7ACU/events.json","paper":"https://pith.science/paper/2K6SHYXL"},"agent_actions":{"view_html":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU","download_json":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU.json","view_paper":"https://pith.science/paper/2K6SHYXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12427&json=true","fetch_graph":"https://pith.science/api/pith-number/2K6SHYXLW37LRFGXOIMJJM7ACU/graph.json","fetch_events":"https://pith.science/api/pith-number/2K6SHYXLW37LRFGXOIMJJM7ACU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU/action/storage_attestation","attest_author":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU/action/author_attestation","sign_citation":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU/action/citation_signature","submit_replication":"https://pith.science/pith/2K6SHYXLW37LRFGXOIMJJM7ACU/action/replication_record"}},"created_at":"2026-07-05T06:13:39.964640+00:00","updated_at":"2026-07-05T06:13:39.964640+00:00"}