{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2V7X3W7UWXKK2VADEMHYJTVSLO","short_pith_number":"pith:2V7X3W7U","canonical_record":{"source":{"id":"2411.18666","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T16:10:44Z","cross_cats_sorted":[],"title_canon_sha256":"7255e237a5fcc921fd1967856fe393c042f38f74541f8ac1f5d48e6019390613","abstract_canon_sha256":"6df63fe124f1657dc445c80095a1b01a77e62ef0c9385cd682eb3045db1df237"},"schema_version":"1.0"},"canonical_sha256":"d57f7ddbf4b5d4ad5403230f84ceb25b8debbdad8d2795c994e95dcb2fa86db7","source":{"kind":"arxiv","id":"2411.18666","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18666","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18666v1","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18666","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"2V7X3W7UWXKK","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"2V7X3W7UWXKK2VAD","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"2V7X3W7U","created_at":"2026-07-05T09:41:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2V7X3W7UWXKK2VADEMHYJTVSLO","target":"record","payload":{"canonical_record":{"source":{"id":"2411.18666","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T16:10:44Z","cross_cats_sorted":[],"title_canon_sha256":"7255e237a5fcc921fd1967856fe393c042f38f74541f8ac1f5d48e6019390613","abstract_canon_sha256":"6df63fe124f1657dc445c80095a1b01a77e62ef0c9385cd682eb3045db1df237"},"schema_version":"1.0"},"canonical_sha256":"d57f7ddbf4b5d4ad5403230f84ceb25b8debbdad8d2795c994e95dcb2fa86db7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:49.131936Z","signature_b64":"iknGIus6wAUMBCgtMNF4Wv7niWcxtvQ8LB36XY1vYzzVToG1V3hz51HEzgm0zGRz0NqGrR/HVxAg7lREF05xDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d57f7ddbf4b5d4ad5403230f84ceb25b8debbdad8d2795c994e95dcb2fa86db7","last_reissued_at":"2026-07-05T09:41:49.131454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:49.131454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.18666","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":"2026-07-05T09:41:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/GCe2hhVxa+HSfMBsOlfXmKgXeIz+3l/z+v7LzJ35t2D6LU4JopvjjdjXEz9zq/8aoVKho+nSAL11ScDZhKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:23:42.144344Z"},"content_sha256":"9849182322351256ddd6036dc21e486a002449da04a462545a0c98a7c7ce8841","schema_version":"1.0","event_id":"sha256:9849182322351256ddd6036dc21e486a002449da04a462545a0c98a7c7ce8841"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2V7X3W7UWXKK2VADEMHYJTVSLO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"3D Scene Graph Guided Vision-Language Pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haihong Xiao, Hao Liu, Yan Liu, Yanni Ma, Ying He","submitted_at":"2024-11-27T16:10:44Z","abstract_excerpt":"3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typically follow task-specific, highly specialized paradigms. Therefore, these methods focus on a limited range of reasoning sub-tasks and rely heavily on the hand-crafted modules and auxiliary losses. This highlights the need for a simpler, unified and general-purpose model. In this paper, we leverage the inherent connection between 3D scene graphs and natural language, proposing a 3D scene graph-guided vision-language "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18666","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/2411.18666/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":"2026-07-05T09:41:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vi2pomURBBvsbGDwqSboAkKPpJf/Ago54p9TTHaH4pHBd1AglWhx0BwgJS1Nqb5kC3abRj7FBh3DjSkNv37yDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:23:42.144828Z"},"content_sha256":"a10d6092e7223f26031ce04ba31ab85f168226c7fb453404b9422a2d4288a7f1","schema_version":"1.0","event_id":"sha256:a10d6092e7223f26031ce04ba31ab85f168226c7fb453404b9422a2d4288a7f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2V7X3W7UWXKK2VADEMHYJTVSLO/bundle.json","state_url":"https://pith.science/pith/2V7X3W7UWXKK2VADEMHYJTVSLO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2V7X3W7UWXKK2VADEMHYJTVSLO/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":"2026-08-06T06:23:42Z","links":{"resolver":"https://pith.science/pith/2V7X3W7UWXKK2VADEMHYJTVSLO","bundle":"https://pith.science/pith/2V7X3W7UWXKK2VADEMHYJTVSLO/bundle.json","state":"https://pith.science/pith/2V7X3W7UWXKK2VADEMHYJTVSLO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2V7X3W7UWXKK2VADEMHYJTVSLO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2V7X3W7UWXKK2VADEMHYJTVSLO","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":"6df63fe124f1657dc445c80095a1b01a77e62ef0c9385cd682eb3045db1df237","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T16:10:44Z","title_canon_sha256":"7255e237a5fcc921fd1967856fe393c042f38f74541f8ac1f5d48e6019390613"},"schema_version":"1.0","source":{"id":"2411.18666","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.18666","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"2411.18666v1","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18666","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"2V7X3W7UWXKK","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"2V7X3W7UWXKK2VAD","created_at":"2026-07-05T09:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"2V7X3W7U","created_at":"2026-07-05T09:41:49Z"}],"graph_snapshots":[{"event_id":"sha256:a10d6092e7223f26031ce04ba31ab85f168226c7fb453404b9422a2d4288a7f1","target":"graph","created_at":"2026-07-05T09:41:49Z","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/2411.18666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D vision-language (VL) reasoning has gained significant attention due to its potential to bridge the 3D physical world with natural language descriptions. Existing approaches typically follow task-specific, highly specialized paradigms. Therefore, these methods focus on a limited range of reasoning sub-tasks and rely heavily on the hand-crafted modules and auxiliary losses. This highlights the need for a simpler, unified and general-purpose model. In this paper, we leverage the inherent connection between 3D scene graphs and natural language, proposing a 3D scene graph-guided vision-language ","authors_text":"Haihong Xiao, Hao Liu, Yan Liu, Yanni Ma, Ying He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T16:10:44Z","title":"3D Scene Graph Guided Vision-Language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18666","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":"sha256:9849182322351256ddd6036dc21e486a002449da04a462545a0c98a7c7ce8841","target":"record","created_at":"2026-07-05T09:41:49Z","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":"6df63fe124f1657dc445c80095a1b01a77e62ef0c9385cd682eb3045db1df237","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T16:10:44Z","title_canon_sha256":"7255e237a5fcc921fd1967856fe393c042f38f74541f8ac1f5d48e6019390613"},"schema_version":"1.0","source":{"id":"2411.18666","kind":"arxiv","version":1}},"canonical_sha256":"d57f7ddbf4b5d4ad5403230f84ceb25b8debbdad8d2795c994e95dcb2fa86db7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d57f7ddbf4b5d4ad5403230f84ceb25b8debbdad8d2795c994e95dcb2fa86db7","first_computed_at":"2026-07-05T09:41:49.131454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:49.131454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iknGIus6wAUMBCgtMNF4Wv7niWcxtvQ8LB36XY1vYzzVToG1V3hz51HEzgm0zGRz0NqGrR/HVxAg7lREF05xDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:49.131936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.18666","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9849182322351256ddd6036dc21e486a002449da04a462545a0c98a7c7ce8841","sha256:a10d6092e7223f26031ce04ba31ab85f168226c7fb453404b9422a2d4288a7f1"],"state_sha256":"1e27423b912acf1fc9d68199c7d8b23179ae4b37e402666817cf9ab0ef07efcc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fl/PRDaILn06OHAu9vZA4OPiGqIFcmhViqsK55mJPUSN0E55OfCwaPa8LSCiLpD9zJi7d2Nsy//g693c+JSNAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:23:42.148372Z","bundle_sha256":"5e5368a78955173305afd46a5e28cb53ee0116ce2f5986a6cdc743d474ab9d6e"}}