{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YO3HBDECLQGR4VXCAFIT4MCIJV","short_pith_number":"pith:YO3HBDEC","schema_version":"1.0","canonical_sha256":"c3b6708c825c0d1e56e201513e30484d6657bc96c29eaf5c51dfce9cc8aa2a2a","source":{"kind":"arxiv","id":"2512.14364","version":3},"attestation_state":"computed","paper":{"title":"Unified Semantic Transformer for 3D Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Hidenobu Matsuki, Johanna Wald, Pedro Hermosilla, Sebastian Koch, Timo Ropinski","submitted_at":"2025-12-16T12:49:35Z","abstract_excerpt":"Holistic 3D scene understanding involves capturing and parsing unstructured 3D environments. Due to the inherent complexity of the real world, existing models have predominantly been developed and limited to be task-specific. We introduce UNITE, a Unified Semantic Transformer for 3D scene understanding, a novel feed-forward neural network that unifies a diverse set of 3D dense semantic indoor tasks within a single model. Our model operates on unseen scenes trained in a fully end-to-end manner and only takes a couple seconds to infer the full 3D semantic geometry. Our approach is capable of dir"},"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":"2512.14364","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-16T12:49:35Z","cross_cats_sorted":[],"title_canon_sha256":"7007ffef8d752d8d95370efa4d10fa284409ec936e908a6f689f3bf60994257c","abstract_canon_sha256":"fb906ea4583efb36a037b124a0ea6248bdfd58a90a58e9b5ca132211b81a6a04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:36.402871Z","signature_b64":"1aoM4nnAV2cd0sLYV/QLmtucjf//UKltI/76SMZk68aVzFjcZaoqaqvszEAYhvwHAxg54uA0rXX7qKtVM49GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3b6708c825c0d1e56e201513e30484d6657bc96c29eaf5c51dfce9cc8aa2a2a","last_reissued_at":"2026-06-02T03:04:36.402364Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:36.402364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Semantic Transformer for 3D Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Federico Tombari, Hidenobu Matsuki, Johanna Wald, Pedro Hermosilla, Sebastian Koch, Timo Ropinski","submitted_at":"2025-12-16T12:49:35Z","abstract_excerpt":"Holistic 3D scene understanding involves capturing and parsing unstructured 3D environments. Due to the inherent complexity of the real world, existing models have predominantly been developed and limited to be task-specific. We introduce UNITE, a Unified Semantic Transformer for 3D scene understanding, a novel feed-forward neural network that unifies a diverse set of 3D dense semantic indoor tasks within a single model. Our model operates on unseen scenes trained in a fully end-to-end manner and only takes a couple seconds to infer the full 3D semantic geometry. Our approach is capable of dir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.14364","kind":"arxiv","version":3},"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/2512.14364/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":"2512.14364","created_at":"2026-06-02T03:04:36.402422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.14364v3","created_at":"2026-06-02T03:04:36.402422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14364","created_at":"2026-06-02T03:04:36.402422+00:00"},{"alias_kind":"pith_short_12","alias_value":"YO3HBDECLQGR","created_at":"2026-06-02T03:04:36.402422+00:00"},{"alias_kind":"pith_short_16","alias_value":"YO3HBDECLQGR4VXC","created_at":"2026-06-02T03:04:36.402422+00:00"},{"alias_kind":"pith_short_8","alias_value":"YO3HBDEC","created_at":"2026-06-02T03:04:36.402422+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/YO3HBDECLQGR4VXCAFIT4MCIJV","json":"https://pith.science/pith/YO3HBDECLQGR4VXCAFIT4MCIJV.json","graph_json":"https://pith.science/api/pith-number/YO3HBDECLQGR4VXCAFIT4MCIJV/graph.json","events_json":"https://pith.science/api/pith-number/YO3HBDECLQGR4VXCAFIT4MCIJV/events.json","paper":"https://pith.science/paper/YO3HBDEC"},"agent_actions":{"view_html":"https://pith.science/pith/YO3HBDECLQGR4VXCAFIT4MCIJV","download_json":"https://pith.science/pith/YO3HBDECLQGR4VXCAFIT4MCIJV.json","view_paper":"https://pith.science/paper/YO3HBDEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.14364&json=true","fetch_graph":"https://pith.science/api/pith-number/YO3HBDECLQGR4VXCAFIT4MCIJV/graph.json","fetch_events":"https://pith.science/api/pith-number/YO3HBDECLQGR4VXCAFIT4MCIJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YO3HBDECLQGR4VXCAFIT4MCIJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YO3HBDECLQGR4VXCAFIT4MCIJV/action/storage_attestation","attest_author":"https://pith.science/pith/YO3HBDECLQGR4VXCAFIT4MCIJV/action/author_attestation","sign_citation":"https://pith.science/pith/YO3HBDECLQGR4VXCAFIT4MCIJV/action/citation_signature","submit_replication":"https://pith.science/pith/YO3HBDECLQGR4VXCAFIT4MCIJV/action/replication_record"}},"created_at":"2026-06-02T03:04:36.402422+00:00","updated_at":"2026-06-02T03:04:36.402422+00:00"}