{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K2PCLZR6AY2PSFDH3INKXXKUCC","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":"009678bb0dca913dd93544c1ee15920a0e43b2791fbe944cd1d08ae3b4bc3c45","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T15:00:13Z","title_canon_sha256":"a058fad15f3db2a28596d181626abffc6bd07c755eb24c5cf8864531a721b5c3"},"schema_version":"1.0","source":{"id":"2507.13363","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13363","created_at":"2026-07-05T11:39:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13363v1","created_at":"2026-07-05T11:39:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13363","created_at":"2026-07-05T11:39:15Z"},{"alias_kind":"pith_short_12","alias_value":"K2PCLZR6AY2P","created_at":"2026-07-05T11:39:15Z"},{"alias_kind":"pith_short_16","alias_value":"K2PCLZR6AY2PSFDH","created_at":"2026-07-05T11:39:15Z"},{"alias_kind":"pith_short_8","alias_value":"K2PCLZR6","created_at":"2026-07-05T11:39:15Z"}],"graph_snapshots":[{"event_id":"sha256:7f519165a27f06fc410c2b8a73f06629642124a38be0bd85ddec781ed2dab521","target":"graph","created_at":"2026-07-05T11:39:15Z","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/2507.13363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern 3D object detection datasets are constrained by narrow class taxonomies and costly manual annotations, limiting their ability to scale to open-world settings. In contrast, 2D vision-language models trained on web-scale image-text pairs exhibit rich semantic understanding and support open-vocabulary detection via natural language prompts. In this work, we leverage the maturity and category diversity of 2D foundation models to perform open-vocabulary 3D object detection without any human-annotated 3D labels.\n  Our pipeline uses a 2D vision-language detector to generate text-conditioned pr","authors_text":"Atharv Goel, Mehar Khurana","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T15:00:13Z","title":"Just Add Geometry: Gradient-Free Open-Vocabulary 3D Detection Without Human-in-the-Loop"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13363","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":"sha256:6d15599546ae38d05ea40c921aaf116529b01bc5b4df22bc366b15dfed0fa43a","target":"record","created_at":"2026-07-05T11:39:15Z","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":"009678bb0dca913dd93544c1ee15920a0e43b2791fbe944cd1d08ae3b4bc3c45","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T15:00:13Z","title_canon_sha256":"a058fad15f3db2a28596d181626abffc6bd07c755eb24c5cf8864531a721b5c3"},"schema_version":"1.0","source":{"id":"2507.13363","kind":"arxiv","version":1}},"canonical_sha256":"569e25e63e0634f91467da1aabdd5410ad8aeb3238ba46719f9ef0acf2fb8b7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"569e25e63e0634f91467da1aabdd5410ad8aeb3238ba46719f9ef0acf2fb8b7c","first_computed_at":"2026-07-05T11:39:15.965937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:15.965937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MPx3T4Waox7uMPLoeAdEVEwzWtHS/WA0BcJitcNt+w4e2tun2FUzoP2QbfMbX0r8iRvEhi4H43kp86m1+QqKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:15.966410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13363","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d15599546ae38d05ea40c921aaf116529b01bc5b4df22bc366b15dfed0fa43a","sha256:7f519165a27f06fc410c2b8a73f06629642124a38be0bd85ddec781ed2dab521"],"state_sha256":"822355d3e4bc23609c785f8539e7643e5f001f5289045844f87d87ec9de7a67b"}