{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U4XWGHQADWGCB4MISEITGMZLGM","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":"50ffae40ce74aff6a063338550211cfa4df3c7441ea319f4804d27fdd743dec3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T17:17:00Z","title_canon_sha256":"699f7b9e18c4a111f72d13bb65a5e9e1ff9d83288d651d95caa06468a2cff090"},"schema_version":"1.0","source":{"id":"2508.20063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20063","created_at":"2026-07-05T12:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20063v1","created_at":"2026-07-05T12:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20063","created_at":"2026-07-05T12:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"U4XWGHQADWGC","created_at":"2026-07-05T12:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"U4XWGHQADWGCB4MI","created_at":"2026-07-05T12:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"U4XWGHQA","created_at":"2026-07-05T12:00:23Z"}],"graph_snapshots":[{"event_id":"sha256:65f70cf8ea0c1c50f51aa63175ebdd2ad92aab7e3f0632c9ed37ef21979d2d70","target":"graph","created_at":"2026-07-05T12:00:23Z","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/2508.20063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary (OV) 3D object detection is an emerging field, yet its exploration through image-based methods remains limited compared to 3D point cloud-based methods. We introduce OpenM3D, a novel open-vocabulary multi-view indoor 3D object detector trained without human annotations. In particular, OpenM3D is a single-stage detector adapting the 2D-induced voxel features from the ImGeoNet model. To support OV, it is jointly trained with a class-agnostic 3D localization loss requiring high-quality 3D pseudo boxes and a voxel-semantic alignment loss requiring diverse pre-trained CLIP features.","authors_text":"Albert Y. C. Chen, Cheng-Hao Kuo, Fu-En Wang, Ke Zhang, Ming-Feng Li, Min Sun, Peng-Hao Hsu, Tao Tu, Yu-Lun Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T17:17:00Z","title":"OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20063","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":"sha256:8cfc7b0680b360786f923655053531b4cec9f8fce6c1e09f2749ce8562bbec92","target":"record","created_at":"2026-07-05T12:00:23Z","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":"50ffae40ce74aff6a063338550211cfa4df3c7441ea319f4804d27fdd743dec3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-27T17:17:00Z","title_canon_sha256":"699f7b9e18c4a111f72d13bb65a5e9e1ff9d83288d651d95caa06468a2cff090"},"schema_version":"1.0","source":{"id":"2508.20063","kind":"arxiv","version":1}},"canonical_sha256":"a72f631e001d8c20f188911133332b330b91627fc1d985a87fd3aff17cbf4b46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a72f631e001d8c20f188911133332b330b91627fc1d985a87fd3aff17cbf4b46","first_computed_at":"2026-07-05T12:00:23.565595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:23.565595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QtDk50uyO9HFtw95/TeK/wMrnQg5Q/qs51Df2MnzSfQjKh0ZyCFWEVDGm1F1VKPzzBbri12UAzWLKL7MHCkyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:23.566098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cfc7b0680b360786f923655053531b4cec9f8fce6c1e09f2749ce8562bbec92","sha256:65f70cf8ea0c1c50f51aa63175ebdd2ad92aab7e3f0632c9ed37ef21979d2d70"],"state_sha256":"25f0636e7adc1df2623537c084e3c453389f97ca82f7013710ec40318dbd5bef"}