{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M4KANV5I4O2U3NPOWV3VW3NH7D","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":"6d16a1a050cc95bf1c8341805369f06a3b04e50a56a1e430a93fae711af141fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-13T09:39:11Z","title_canon_sha256":"79bc3756ee7c94607fa210b53074d50e91c112a36b37ba9943b92f354b7eb269"},"schema_version":"1.0","source":{"id":"2407.09826","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09826","created_at":"2026-07-05T09:01:03Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09826v2","created_at":"2026-07-05T09:01:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09826","created_at":"2026-07-05T09:01:03Z"},{"alias_kind":"pith_short_12","alias_value":"M4KANV5I4O2U","created_at":"2026-07-05T09:01:03Z"},{"alias_kind":"pith_short_16","alias_value":"M4KANV5I4O2U3NPO","created_at":"2026-07-05T09:01:03Z"},{"alias_kind":"pith_short_8","alias_value":"M4KANV5I","created_at":"2026-07-05T09:01:03Z"}],"graph_snapshots":[{"event_id":"sha256:fd4bf00419558fe746095ae0eaf796e93a0758c93bea7ae1d7e4c1c8c19031f2","target":"graph","created_at":"2026-07-05T09:01:03Z","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/2407.09826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D Semantic Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model predicts dense-embedding for each point which is co-embedded with both the aligned image and text spaces from the 2D vision-language model. Specifically, our method exploits the superior generalization ability of the 2D vision-language models and proposes the Embeddings Soft-Guidance Stage to utilize it to implicitly align 3D embeddings and text embeddings. Moreover, we introduce the Embeddings Specialization Stage to purify the","authors_text":"Hao Tang, Jinlong Li, Lin Ma, Nicu Sebe, Qiudan Zhang, Xiaoxu Xu, Xu Wang, Yitian Yuan, Zequn Jie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-13T09:39:11Z","title":"3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09826","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":"sha256:8f04ae2b51939e839c870c88cef7ee3a7b1a6804caca45d48bea9a5aa74f13e4","target":"record","created_at":"2026-07-05T09:01:03Z","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":"6d16a1a050cc95bf1c8341805369f06a3b04e50a56a1e430a93fae711af141fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-13T09:39:11Z","title_canon_sha256":"79bc3756ee7c94607fa210b53074d50e91c112a36b37ba9943b92f354b7eb269"},"schema_version":"1.0","source":{"id":"2407.09826","kind":"arxiv","version":2}},"canonical_sha256":"671406d7a8e3b54db5eeb5775b6da7f8e6a09b6180d50d2a90528f4bdae35fc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"671406d7a8e3b54db5eeb5775b6da7f8e6a09b6180d50d2a90528f4bdae35fc8","first_computed_at":"2026-07-05T09:01:03.854631Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:03.854631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5GLfQ0HjckigSVxtebKXmmlvcdXdtuDq2etienedP0L7+McVaq3eJczSZn9ucO2aVaHoMKhKftwbOt43kgDpAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:03.855080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09826","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f04ae2b51939e839c870c88cef7ee3a7b1a6804caca45d48bea9a5aa74f13e4","sha256:fd4bf00419558fe746095ae0eaf796e93a0758c93bea7ae1d7e4c1c8c19031f2"],"state_sha256":"89bb715e08cfc6ad2e8356ec244a609f330bcc3a03c3b12731fa5c30e87657ce"}