{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PCPZQQEEIIKMQJIGG63ZYXT2A4","short_pith_number":"pith:PCPZQQEE","canonical_record":{"source":{"id":"2606.20946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T21:20:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b573758cd99b4017198ddbb66879c1b15d7e430e15cf2a735742c9ed32c2de44","abstract_canon_sha256":"0ad15a8ffa24b63c0cfa8eaa998244bdff4d7cd983edb4f4364cc98f9fab58fa"},"schema_version":"1.0"},"canonical_sha256":"789f9840844214c8250637b79c5e7a070593365bd4a4c2ddda0584ba33c257b0","source":{"kind":"arxiv","id":"2606.20946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20946","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20946v1","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20946","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"PCPZQQEEIIKM","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"PCPZQQEEIIKMQJIG","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"PCPZQQEE","created_at":"2026-06-23T01:12:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PCPZQQEEIIKMQJIGG63ZYXT2A4","target":"record","payload":{"canonical_record":{"source":{"id":"2606.20946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T21:20:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b573758cd99b4017198ddbb66879c1b15d7e430e15cf2a735742c9ed32c2de44","abstract_canon_sha256":"0ad15a8ffa24b63c0cfa8eaa998244bdff4d7cd983edb4f4364cc98f9fab58fa"},"schema_version":"1.0"},"canonical_sha256":"789f9840844214c8250637b79c5e7a070593365bd4a4c2ddda0584ba33c257b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:22.836159Z","signature_b64":"GPT5wao85KeEbTv7VJ80DvX4NuxqTKcQC/H8iJ7T8AZIvIHk3qHIwKtSYqcHDPxZN6aeUiUStz8mKDxazOXmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"789f9840844214c8250637b79c5e7a070593365bd4a4c2ddda0584ba33c257b0","last_reissued_at":"2026-06-23T01:12:22.835706Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:22.835706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.20946","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TLd//pt1Obtj2BqB9jNKZ3rIlDh7r0k0JMTGDxOnvmqoBFyjT7bUXFe0XxY193CdchBntXgDGyDFLI+tvEC+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T15:11:41.201909Z"},"content_sha256":"d122b2cfae5da93c13df938396371aa8d698fbb6a77540d741badaae9cb5de6d","schema_version":"1.0","event_id":"sha256:d122b2cfae5da93c13df938396371aa8d698fbb6a77540d741badaae9cb5de6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PCPZQQEEIIKMQJIGG63ZYXT2A4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Diverse Language Generation for 3D Visual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Angel X. Chang, Austin T. Wang, Dongchen Yang","submitted_at":"2026-06-18T21:20:20Z","abstract_excerpt":"Developing robust models for 3D visual grounding (3DVG), the localization of entities in a 3D scene described in natural language, is important for enabling agents to correspond spatial language with objects in the physical world. However, the lack of diverse descriptions at scale prevents models from generalizing beyond simple linguistic patterns. Recent such attempts lack diversity in the constraint types and language used to ground objects. Captioning methods cannot precisely contrast objects, which is important for visual grounding. We therefore propose ViGiL3D++, a scalable, scene-agnosti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20946","kind":"arxiv","version":1},"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/2606.20946/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":"2026-06-23T01:12:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/22hiKu4QT2RRnsU5YxS55d2NFTP6RthCu+nb/hXXOC6gcQPGRCom3gXgt+KDP5D7O8rLqefUiegZWZHgQnbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T15:11:41.202269Z"},"content_sha256":"06dad1b2c497df1b4f3934cdfb4847a9c2d7f75de958c222f5a5299307164524","schema_version":"1.0","event_id":"sha256:06dad1b2c497df1b4f3934cdfb4847a9c2d7f75de958c222f5a5299307164524"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCPZQQEEIIKMQJIGG63ZYXT2A4/bundle.json","state_url":"https://pith.science/pith/PCPZQQEEIIKMQJIGG63ZYXT2A4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCPZQQEEIIKMQJIGG63ZYXT2A4/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":"2026-07-04T15:11:41Z","links":{"resolver":"https://pith.science/pith/PCPZQQEEIIKMQJIGG63ZYXT2A4","bundle":"https://pith.science/pith/PCPZQQEEIIKMQJIGG63ZYXT2A4/bundle.json","state":"https://pith.science/pith/PCPZQQEEIIKMQJIGG63ZYXT2A4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCPZQQEEIIKMQJIGG63ZYXT2A4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PCPZQQEEIIKMQJIGG63ZYXT2A4","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":"0ad15a8ffa24b63c0cfa8eaa998244bdff4d7cd983edb4f4364cc98f9fab58fa","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T21:20:20Z","title_canon_sha256":"b573758cd99b4017198ddbb66879c1b15d7e430e15cf2a735742c9ed32c2de44"},"schema_version":"1.0","source":{"id":"2606.20946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20946","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20946v1","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20946","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"pith_short_12","alias_value":"PCPZQQEEIIKM","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"pith_short_16","alias_value":"PCPZQQEEIIKMQJIG","created_at":"2026-06-23T01:12:22Z"},{"alias_kind":"pith_short_8","alias_value":"PCPZQQEE","created_at":"2026-06-23T01:12:22Z"}],"graph_snapshots":[{"event_id":"sha256:06dad1b2c497df1b4f3934cdfb4847a9c2d7f75de958c222f5a5299307164524","target":"graph","created_at":"2026-06-23T01:12:22Z","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/2606.20946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing robust models for 3D visual grounding (3DVG), the localization of entities in a 3D scene described in natural language, is important for enabling agents to correspond spatial language with objects in the physical world. However, the lack of diverse descriptions at scale prevents models from generalizing beyond simple linguistic patterns. Recent such attempts lack diversity in the constraint types and language used to ground objects. Captioning methods cannot precisely contrast objects, which is important for visual grounding. We therefore propose ViGiL3D++, a scalable, scene-agnosti","authors_text":"Angel X. Chang, Austin T. Wang, Dongchen Yang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T21:20:20Z","title":"Scaling Diverse Language Generation for 3D Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20946","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:d122b2cfae5da93c13df938396371aa8d698fbb6a77540d741badaae9cb5de6d","target":"record","created_at":"2026-06-23T01:12:22Z","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":"0ad15a8ffa24b63c0cfa8eaa998244bdff4d7cd983edb4f4364cc98f9fab58fa","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T21:20:20Z","title_canon_sha256":"b573758cd99b4017198ddbb66879c1b15d7e430e15cf2a735742c9ed32c2de44"},"schema_version":"1.0","source":{"id":"2606.20946","kind":"arxiv","version":1}},"canonical_sha256":"789f9840844214c8250637b79c5e7a070593365bd4a4c2ddda0584ba33c257b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"789f9840844214c8250637b79c5e7a070593365bd4a4c2ddda0584ba33c257b0","first_computed_at":"2026-06-23T01:12:22.835706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:22.835706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GPT5wao85KeEbTv7VJ80DvX4NuxqTKcQC/H8iJ7T8AZIvIHk3qHIwKtSYqcHDPxZN6aeUiUStz8mKDxazOXmBA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:22.836159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d122b2cfae5da93c13df938396371aa8d698fbb6a77540d741badaae9cb5de6d","sha256:06dad1b2c497df1b4f3934cdfb4847a9c2d7f75de958c222f5a5299307164524"],"state_sha256":"e7ffd9ac4734a76cbeb34d285f502985a6c4e2294bec81785ca6f6b4140e5fd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cf5AdIQzM+l6xWk1s7+wIDCIb2ryX5Ej+En7ivli9iNhKk4NA2UrS5B88+xASDCL7Xej/MToshOCNkG8jAVkDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T15:11:41.204194Z","bundle_sha256":"12eeb852d476f89ca2d5794072c4f3ca1be0cafeced8788567efce490e0ac799"}}