{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6RBPVBTSAZQ7ZX7VHYQYI27BVL","short_pith_number":"pith:6RBPVBTS","canonical_record":{"source":{"id":"2503.16707","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T20:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"84b19911078c350a96fe087f32292b78f7f9c3d652e6387d4da981f90e2fec12","abstract_canon_sha256":"65d20fdd7c3e7851196131e57c80a84988f51b1e9ce84d661dbe1ab7c7359b56"},"schema_version":"1.0"},"canonical_sha256":"f442fa86720661fcdff53e21846be1aafce665eb6ed09a65ba9f302e6b8440dd","source":{"kind":"arxiv","id":"2503.16707","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16707","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16707v2","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16707","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"6RBPVBTSAZQ7","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"6RBPVBTSAZQ7ZX7V","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"6RBPVBTS","created_at":"2026-07-05T10:41:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6RBPVBTSAZQ7ZX7VHYQYI27BVL","target":"record","payload":{"canonical_record":{"source":{"id":"2503.16707","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T20:58:48Z","cross_cats_sorted":[],"title_canon_sha256":"84b19911078c350a96fe087f32292b78f7f9c3d652e6387d4da981f90e2fec12","abstract_canon_sha256":"65d20fdd7c3e7851196131e57c80a84988f51b1e9ce84d661dbe1ab7c7359b56"},"schema_version":"1.0"},"canonical_sha256":"f442fa86720661fcdff53e21846be1aafce665eb6ed09a65ba9f302e6b8440dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:00.914345Z","signature_b64":"o8xKZS14evLI4zQGIPIbyx8Evjq2caNWGNJzmOWf+9pnIaSV61imHW1yqz/+QdzCPJMV8BT51wkq9KxmDwqYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f442fa86720661fcdff53e21846be1aafce665eb6ed09a65ba9f302e6b8440dd","last_reissued_at":"2026-07-05T10:41:00.913877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:00.913877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.16707","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/uZYBxbXnGD3atKx6ap2CJ/yMlNL0hnoWSkGUOrdhSAmlPyVAvU5lKeyv3pUFOu7fijAFWLm2ysJ4tNNubTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:12:23.462407Z"},"content_sha256":"5463e1e319d92343ea767c86ba08c79681a34998a9ed53e1e235b71fc089a0a9","schema_version":"1.0","event_id":"sha256:5463e1e319d92343ea767c86ba08c79681a34998a9ed53e1e235b71fc089a0a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6RBPVBTSAZQ7ZX7VHYQYI27BVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cristiano Saltori, Fabio Poiesi, Jinlong Li, Nicu Sebe","submitted_at":"2025-03-20T20:58:48Z","abstract_excerpt":"The lack of a large-scale 3D-text corpus has led recent works to distill open-vocabulary knowledge from vision-language models (VLMs). However, these methods typically rely on a single VLM to align the feature spaces of 3D models within a common language space, which limits the potential of 3D models to leverage the diverse spatial and semantic capabilities encapsulated in various foundation models. In this paper, we propose Cross-modal and Uncertainty-aware Agglomeration for Open-vocabulary 3D Scene Understanding dubbed CUA-O3D, the first model to integrate multiple foundation models-such as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16707","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/2503.16707/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"78qa7+afn/+dYISSvni3N9xm2SmA1zxQQ3XwuQ6tCCsWKxK2ZVLvCCicjjQxeOzU8O8a5beRYWmhhOBOzEf/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:12:23.462772Z"},"content_sha256":"4fa4f7daa6e96d1c93c809e39f4715669703c9630a1c9ef9b38b214d94ade5ce","schema_version":"1.0","event_id":"sha256:4fa4f7daa6e96d1c93c809e39f4715669703c9630a1c9ef9b38b214d94ade5ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6RBPVBTSAZQ7ZX7VHYQYI27BVL/bundle.json","state_url":"https://pith.science/pith/6RBPVBTSAZQ7ZX7VHYQYI27BVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6RBPVBTSAZQ7ZX7VHYQYI27BVL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T11:12:23Z","links":{"resolver":"https://pith.science/pith/6RBPVBTSAZQ7ZX7VHYQYI27BVL","bundle":"https://pith.science/pith/6RBPVBTSAZQ7ZX7VHYQYI27BVL/bundle.json","state":"https://pith.science/pith/6RBPVBTSAZQ7ZX7VHYQYI27BVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6RBPVBTSAZQ7ZX7VHYQYI27BVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6RBPVBTSAZQ7ZX7VHYQYI27BVL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"65d20fdd7c3e7851196131e57c80a84988f51b1e9ce84d661dbe1ab7c7359b56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T20:58:48Z","title_canon_sha256":"84b19911078c350a96fe087f32292b78f7f9c3d652e6387d4da981f90e2fec12"},"schema_version":"1.0","source":{"id":"2503.16707","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16707","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16707v2","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16707","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"6RBPVBTSAZQ7","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"pith_short_16","alias_value":"6RBPVBTSAZQ7ZX7V","created_at":"2026-07-05T10:41:00Z"},{"alias_kind":"pith_short_8","alias_value":"6RBPVBTS","created_at":"2026-07-05T10:41:00Z"}],"graph_snapshots":[{"event_id":"sha256:4fa4f7daa6e96d1c93c809e39f4715669703c9630a1c9ef9b38b214d94ade5ce","target":"graph","created_at":"2026-07-05T10:41:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.16707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The lack of a large-scale 3D-text corpus has led recent works to distill open-vocabulary knowledge from vision-language models (VLMs). However, these methods typically rely on a single VLM to align the feature spaces of 3D models within a common language space, which limits the potential of 3D models to leverage the diverse spatial and semantic capabilities encapsulated in various foundation models. In this paper, we propose Cross-modal and Uncertainty-aware Agglomeration for Open-vocabulary 3D Scene Understanding dubbed CUA-O3D, the first model to integrate multiple foundation models-such as ","authors_text":"Cristiano Saltori, Fabio Poiesi, Jinlong Li, Nicu Sebe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T20:58:48Z","title":"Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16707","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5463e1e319d92343ea767c86ba08c79681a34998a9ed53e1e235b71fc089a0a9","target":"record","created_at":"2026-07-05T10:41:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"65d20fdd7c3e7851196131e57c80a84988f51b1e9ce84d661dbe1ab7c7359b56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T20:58:48Z","title_canon_sha256":"84b19911078c350a96fe087f32292b78f7f9c3d652e6387d4da981f90e2fec12"},"schema_version":"1.0","source":{"id":"2503.16707","kind":"arxiv","version":2}},"canonical_sha256":"f442fa86720661fcdff53e21846be1aafce665eb6ed09a65ba9f302e6b8440dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f442fa86720661fcdff53e21846be1aafce665eb6ed09a65ba9f302e6b8440dd","first_computed_at":"2026-07-05T10:41:00.913877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:00.913877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o8xKZS14evLI4zQGIPIbyx8Evjq2caNWGNJzmOWf+9pnIaSV61imHW1yqz/+QdzCPJMV8BT51wkq9KxmDwqYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:00.914345Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16707","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5463e1e319d92343ea767c86ba08c79681a34998a9ed53e1e235b71fc089a0a9","sha256:4fa4f7daa6e96d1c93c809e39f4715669703c9630a1c9ef9b38b214d94ade5ce"],"state_sha256":"b55d6749e5537417f110c8d9f8b516ad9db07a2dc1d3d788158a312a4c73bd3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"331rIQkfLFARm1xM8v30dAnGF1xe0F+xHPMOi3nnPJmujpEB2OY7EWWunK8dVxIWbj6zhielMZX59RnWSz4dAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:12:23.464755Z","bundle_sha256":"80792e1e69c81954657a974050ff173cf5540246e6c5f15dbfc4b03234420009"}}