{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AIHH6F27MFQIMUYNKQ3SQTTVBQ","short_pith_number":"pith:AIHH6F27","schema_version":"1.0","canonical_sha256":"020e7f175f616086530d5437284e750c0341612efd436ca0829871e6d7727757","source":{"kind":"arxiv","id":"2103.15875","version":2},"attestation_state":"computed","paper":{"title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew J. Davison, Shuaifeng Zhi, Stefan Leutenegger, Tristan Laidlow","submitted_at":"2021-03-29T18:30:55Z","abstract_excerpt":"Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are appealing as they do not require prior training data, but the same fully self-supervised approach is not possible for semantics because labels are human-defined properties.\n  We extend neural radiance fields (NeRF) to jointly encode semantics with appearance and geometry, so that complete and accurate 2D semantic labels can be achieved using a small amount of in-p"},"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":"2103.15875","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-29T18:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"64d913460d625cf4123bdc9e69aab70deae3711eeac371df95b374adfcab9c19","abstract_canon_sha256":"4e0aa61238c7bb983b8bb3fdb7fd2b264bc4efee21ee213533c1ce64e6e2424d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:48.040516Z","signature_b64":"L+BXT0FvXwG3o51SsuQEOv/aIDWDPegAN24+3/LFUH9FNzM5euSBwDE8tNMDoSpLajTr6vHDPrcloSfmc29mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"020e7f175f616086530d5437284e750c0341612efd436ca0829871e6d7727757","last_reissued_at":"2026-07-05T03:07:48.039968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:48.039968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew J. Davison, Shuaifeng Zhi, Stefan Leutenegger, Tristan Laidlow","submitted_at":"2021-03-29T18:30:55Z","abstract_excerpt":"Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are appealing as they do not require prior training data, but the same fully self-supervised approach is not possible for semantics because labels are human-defined properties.\n  We extend neural radiance fields (NeRF) to jointly encode semantics with appearance and geometry, so that complete and accurate 2D semantic labels can be achieved using a small amount of in-p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.15875","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/2103.15875/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":"2103.15875","created_at":"2026-07-05T03:07:48.040027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.15875v2","created_at":"2026-07-05T03:07:48.040027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.15875","created_at":"2026-07-05T03:07:48.040027+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIHH6F27MFQI","created_at":"2026-07-05T03:07:48.040027+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIHH6F27MFQIMUYN","created_at":"2026-07-05T03:07:48.040027+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIHH6F27","created_at":"2026-07-05T03:07:48.040027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03073","citing_title":"LEG-SLAM: Real-Time Language-Enhanced Gaussian Splatting for SLAM","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ","json":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ.json","graph_json":"https://pith.science/api/pith-number/AIHH6F27MFQIMUYNKQ3SQTTVBQ/graph.json","events_json":"https://pith.science/api/pith-number/AIHH6F27MFQIMUYNKQ3SQTTVBQ/events.json","paper":"https://pith.science/paper/AIHH6F27"},"agent_actions":{"view_html":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ","download_json":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ.json","view_paper":"https://pith.science/paper/AIHH6F27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.15875&json=true","fetch_graph":"https://pith.science/api/pith-number/AIHH6F27MFQIMUYNKQ3SQTTVBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AIHH6F27MFQIMUYNKQ3SQTTVBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ/action/storage_attestation","attest_author":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ/action/author_attestation","sign_citation":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ/action/citation_signature","submit_replication":"https://pith.science/pith/AIHH6F27MFQIMUYNKQ3SQTTVBQ/action/replication_record"}},"created_at":"2026-07-05T03:07:48.040027+00:00","updated_at":"2026-07-05T03:07:48.040027+00:00"}