{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6UTSSQZM7TXMDFPUR5DRCEDHFV","short_pith_number":"pith:6UTSSQZM","canonical_record":{"source":{"id":"2407.06084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T16:26:52Z","cross_cats_sorted":[],"title_canon_sha256":"016b2589a00e816bb560f596d6cc533d251aae01b7ad1d6a36c96e9f9e894ed8","abstract_canon_sha256":"81e574ea52ee077e283dc627d7948df535195c96c2597e89baa285e582b44002"},"schema_version":"1.0"},"canonical_sha256":"f52729432cfceec195f48f471110672d531b7ac78ad95bb256a58264b33b5bc8","source":{"kind":"arxiv","id":"2407.06084","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06084","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06084v1","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06084","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"pith_short_12","alias_value":"6UTSSQZM7TXM","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"pith_short_16","alias_value":"6UTSSQZM7TXMDFPU","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"pith_short_8","alias_value":"6UTSSQZM","created_at":"2026-07-05T08:41:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6UTSSQZM7TXMDFPUR5DRCEDHFV","target":"record","payload":{"canonical_record":{"source":{"id":"2407.06084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T16:26:52Z","cross_cats_sorted":[],"title_canon_sha256":"016b2589a00e816bb560f596d6cc533d251aae01b7ad1d6a36c96e9f9e894ed8","abstract_canon_sha256":"81e574ea52ee077e283dc627d7948df535195c96c2597e89baa285e582b44002"},"schema_version":"1.0"},"canonical_sha256":"f52729432cfceec195f48f471110672d531b7ac78ad95bb256a58264b33b5bc8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:23.161451Z","signature_b64":"klSRhfxNgGkoYZTZWTE/+foaY03q67K3ohV36Z4eqG0UQttyaCXK/vjuJpyRN2MeRg2r2rdiKqrg6JUx52msAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f52729432cfceec195f48f471110672d531b7ac78ad95bb256a58264b33b5bc8","last_reissued_at":"2026-07-05T08:41:23.161032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:23.161032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.06084","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":"2026-07-05T08:41:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GUdBo6pMP/ZNbkGMQ+9RR8IARzafQhJb6LIQFSb7SJyTNRqHQ2BMqUBpoZB4jyDmZebBEXC+3D8hyVIhIbPhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:35:04.075654Z"},"content_sha256":"3d6025769a5092f54bd1be3d7a7ad399f352c505ded22eafe018fd2ea704c536","schema_version":"1.0","event_id":"sha256:3d6025769a5092f54bd1be3d7a7ad399f352c505ded22eafe018fd2ea704c536"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6UTSSQZM7TXMDFPUR5DRCEDHFV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dejie Yang, Qingchao Chen, Siyuan Huang, Wentao Mo, Yang Liu, Zhu Xu","submitted_at":"2024-07-08T16:26:52Z","abstract_excerpt":"3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited scene-level diversity and insufficient fine-grained annotations (only 1.2K scenes and 280K textual annotations in ScanScribe), primarily due to the labor-intensive of collecting and annotating 3D scenes. To overcome these obstacles, we construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06084","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/2407.06084/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":"2026-07-05T08:41:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WcDUZBFE9GT17Zu5kpJTeV6kYdPex1vk1ULiCMvB8/QuXxFNBSFIlExeOJk0Ejq5GSQa0zRrJxtyAK9vOSsGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:35:04.077439Z"},"content_sha256":"89e8a6217b393c77786d954aac9958a25185c1aa24a9658ce3ab635022965c8e","schema_version":"1.0","event_id":"sha256:89e8a6217b393c77786d954aac9958a25185c1aa24a9658ce3ab635022965c8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UTSSQZM7TXMDFPUR5DRCEDHFV/bundle.json","state_url":"https://pith.science/pith/6UTSSQZM7TXMDFPUR5DRCEDHFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UTSSQZM7TXMDFPUR5DRCEDHFV/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":"2026-08-07T19:35:04Z","links":{"resolver":"https://pith.science/pith/6UTSSQZM7TXMDFPUR5DRCEDHFV","bundle":"https://pith.science/pith/6UTSSQZM7TXMDFPUR5DRCEDHFV/bundle.json","state":"https://pith.science/pith/6UTSSQZM7TXMDFPUR5DRCEDHFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UTSSQZM7TXMDFPUR5DRCEDHFV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6UTSSQZM7TXMDFPUR5DRCEDHFV","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":"81e574ea52ee077e283dc627d7948df535195c96c2597e89baa285e582b44002","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T16:26:52Z","title_canon_sha256":"016b2589a00e816bb560f596d6cc533d251aae01b7ad1d6a36c96e9f9e894ed8"},"schema_version":"1.0","source":{"id":"2407.06084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06084","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06084v1","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06084","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"pith_short_12","alias_value":"6UTSSQZM7TXM","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"pith_short_16","alias_value":"6UTSSQZM7TXMDFPU","created_at":"2026-07-05T08:41:23Z"},{"alias_kind":"pith_short_8","alias_value":"6UTSSQZM","created_at":"2026-07-05T08:41:23Z"}],"graph_snapshots":[{"event_id":"sha256:89e8a6217b393c77786d954aac9958a25185c1aa24a9658ce3ab635022965c8e","target":"graph","created_at":"2026-07-05T08:41:23Z","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/2407.06084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D Vision-Language Pre-training (3D-VLP) aims to provide a pre-train model which can bridge 3D scenes with natural language, which is an important technique for embodied intelligence. However, current 3D-VLP datasets are hindered by limited scene-level diversity and insufficient fine-grained annotations (only 1.2K scenes and 280K textual annotations in ScanScribe), primarily due to the labor-intensive of collecting and annotating 3D scenes. To overcome these obstacles, we construct SynVL3D, a comprehensive synthetic scene-text corpus with 10K indoor scenes and 1M descriptions at object, view, ","authors_text":"Dejie Yang, Qingchao Chen, Siyuan Huang, Wentao Mo, Yang Liu, Zhu Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T16:26:52Z","title":"3D Vision and Language Pretraining with Large-Scale Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06084","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":"sha256:3d6025769a5092f54bd1be3d7a7ad399f352c505ded22eafe018fd2ea704c536","target":"record","created_at":"2026-07-05T08:41:23Z","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":"81e574ea52ee077e283dc627d7948df535195c96c2597e89baa285e582b44002","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T16:26:52Z","title_canon_sha256":"016b2589a00e816bb560f596d6cc533d251aae01b7ad1d6a36c96e9f9e894ed8"},"schema_version":"1.0","source":{"id":"2407.06084","kind":"arxiv","version":1}},"canonical_sha256":"f52729432cfceec195f48f471110672d531b7ac78ad95bb256a58264b33b5bc8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f52729432cfceec195f48f471110672d531b7ac78ad95bb256a58264b33b5bc8","first_computed_at":"2026-07-05T08:41:23.161032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:23.161032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"klSRhfxNgGkoYZTZWTE/+foaY03q67K3ohV36Z4eqG0UQttyaCXK/vjuJpyRN2MeRg2r2rdiKqrg6JUx52msAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:23.161451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.06084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d6025769a5092f54bd1be3d7a7ad399f352c505ded22eafe018fd2ea704c536","sha256:89e8a6217b393c77786d954aac9958a25185c1aa24a9658ce3ab635022965c8e"],"state_sha256":"5661f55f516ac3324ebad80163918b7cd0b28ede10bd710300269452afc84ed5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAjFMSvZ0xnL4otpnQI/3WYY4XafeVhBvYI1ce4B8pZ1w1BjK0TmWLDQ9swfo38nviRBF5SWoOlLB43ZO1iiDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:35:04.089015Z","bundle_sha256":"93dcc8c880e0a34278f5f371890eaf41bbf476159094f2e3378b295a40d2e5f0"}}