{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YLGJUVHNPDNVJU6FZNMZ3XCFKP","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":"f430262ebfc8a5375d243715c0d5445ff69a574a78e03138625a14b42dba6fd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-13T05:39:17Z","title_canon_sha256":"b7034b3fed857a1e8d28a5d672e65fc1055e3e42148b4534c7bff18319a6928a"},"schema_version":"1.0","source":{"id":"2407.09781","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09781","created_at":"2026-07-05T08:43:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09781v1","created_at":"2026-07-05T08:43:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09781","created_at":"2026-07-05T08:43:34Z"},{"alias_kind":"pith_short_12","alias_value":"YLGJUVHNPDNV","created_at":"2026-07-05T08:43:34Z"},{"alias_kind":"pith_short_16","alias_value":"YLGJUVHNPDNVJU6F","created_at":"2026-07-05T08:43:34Z"},{"alias_kind":"pith_short_8","alias_value":"YLGJUVHN","created_at":"2026-07-05T08:43:34Z"}],"graph_snapshots":[{"event_id":"sha256:87fd1140b71c3d55ae58116c81ee6c91543640c6ff2bad9fc0bb2339c6523487","target":"graph","created_at":"2026-07-05T08:43:34Z","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/2407.09781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or text supervision while neglecting the collective strength of all modalities. In this work, we propose a Dense Multimodal Alignment (DMA) framework to densely co-embed different modalities into a common space for maximizing their synergistic benefits. Instead of extracting coarse view- or region-level text prompts, we leverage large vision-language models to ext","authors_text":"Chenhang He, Lei Zhang, Ruihuang Li, Vishal M. Patel, Zhengqiang Zhang, Zhiyuan Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-13T05:39:17Z","title":"Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09781","kind":"arxiv","version":1},"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":"sha256:17ab426f9e4d77dcdcbc02ab09f5cd7c1fe2964a829d1f13998fcbaf91b15a5b","target":"record","created_at":"2026-07-05T08:43:34Z","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":"f430262ebfc8a5375d243715c0d5445ff69a574a78e03138625a14b42dba6fd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-13T05:39:17Z","title_canon_sha256":"b7034b3fed857a1e8d28a5d672e65fc1055e3e42148b4534c7bff18319a6928a"},"schema_version":"1.0","source":{"id":"2407.09781","kind":"arxiv","version":1}},"canonical_sha256":"c2cc9a54ed78db54d3c5cb599ddc4553f6b033c09668ec94e0369c5f5eaba9af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2cc9a54ed78db54d3c5cb599ddc4553f6b033c09668ec94e0369c5f5eaba9af","first_computed_at":"2026-07-05T08:43:34.623277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:34.623277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ogMs9XgtUCPK8xc2NBV39qLuFPbp+8ho3VH830vWaoxmHroS0dISJEoDfKFII6oGINvQSTXMUAyC5ApETKrXDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:34.623635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09781","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17ab426f9e4d77dcdcbc02ab09f5cd7c1fe2964a829d1f13998fcbaf91b15a5b","sha256:87fd1140b71c3d55ae58116c81ee6c91543640c6ff2bad9fc0bb2339c6523487"],"state_sha256":"2c5c74cc0fe0ee71e354eeea429265ee47531079175820838a31d3d4c79c801c"}