{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BUH2ZE5ISQQPQPXXN5LJASAIRK","short_pith_number":"pith:BUH2ZE5I","canonical_record":{"source":{"id":"2412.06322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T09:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"edcaffb8c056fa1d557fd1396629eaebd4defc4ba61e014d38cfdc0e0aa3e0eb","abstract_canon_sha256":"41e37693a3f18d444f5f083c9632e8922955a831f73452db1d4ce29c15f5105b"},"schema_version":"1.0"},"canonical_sha256":"0d0fac93a89420f83ef76f569048088a82ede231dc2a5a1bcba72eff01afea12","source":{"kind":"arxiv","id":"2412.06322","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06322","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06322v1","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06322","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"BUH2ZE5ISQQP","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"BUH2ZE5ISQQPQPXX","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"BUH2ZE5I","created_at":"2026-07-05T09:46:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BUH2ZE5ISQQPQPXXN5LJASAIRK","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T09:18:32Z","cross_cats_sorted":[],"title_canon_sha256":"edcaffb8c056fa1d557fd1396629eaebd4defc4ba61e014d38cfdc0e0aa3e0eb","abstract_canon_sha256":"41e37693a3f18d444f5f083c9632e8922955a831f73452db1d4ce29c15f5105b"},"schema_version":"1.0"},"canonical_sha256":"0d0fac93a89420f83ef76f569048088a82ede231dc2a5a1bcba72eff01afea12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:19.139584Z","signature_b64":"fCCs/jfOaEyd6C6DI03j4IgbfLuH+Dsf0X2jVJpB/iaplMB9b+bG1sMdjeafQYgU/rGVJozb9jNh3nuhpvuwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d0fac93a89420f83ef76f569048088a82ede231dc2a5a1bcba72eff01afea12","last_reissued_at":"2026-07-05T09:46:19.139103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:19.139103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06322","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":"2026-07-05T09:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tOJ92gPSCcEb+qUq+x45gdq2WWsNqjMvamm/VQoE1eJafMBNhLULRdBewfzabDoDBF5lnsiX/7sUrlE/8OS+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:12:54.728614Z"},"content_sha256":"da8281dc6e7fe052a83775cedfdb1cb18cd5865c3daf7189d54131993845d7f0","schema_version":"1.0","event_id":"sha256:da8281dc6e7fe052a83775cedfdb1cb18cd5865c3daf7189d54131993845d7f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BUH2ZE5ISQQPQPXXN5LJASAIRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jason Chun Lok Li, Mengyang Wu, Mingjie Xu, Weifeng Ou, Yuzhi Zhao","submitted_at":"2024-12-09T09:18:32Z","abstract_excerpt":"Scene Graph Generation (SGG) converts visual scenes into structured graph representations, providing deeper scene understanding for complex vision tasks. However, existing SGG models often overlook essential spatial relationships and struggle with generalization in open-vocabulary contexts. To address these limitations, we propose LLaVA-SpaceSGG, a multimodal large language model (MLLM) designed for open-vocabulary SGG with enhanced spatial relation modeling. To train it, we collect the SGG instruction-tuning dataset, named SpaceSGG. This dataset is constructed by combining publicly available "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06322","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/2412.06322/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":"2026-07-05T09:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fX6w2zVvq2t+g6vmiL+mXnjb9W7zFEAvqPUM2Uq/GpHukHqwLIvD3nH8jUQ5ocNDOQcnNcyWo3Ve8KF18zkvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:12:54.729098Z"},"content_sha256":"3849024ad699890ed1add9214859f13b0ed7b1ebb5a27e874c93a0a99063f229","schema_version":"1.0","event_id":"sha256:3849024ad699890ed1add9214859f13b0ed7b1ebb5a27e874c93a0a99063f229"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUH2ZE5ISQQPQPXXN5LJASAIRK/bundle.json","state_url":"https://pith.science/pith/BUH2ZE5ISQQPQPXXN5LJASAIRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUH2ZE5ISQQPQPXXN5LJASAIRK/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":"2026-08-06T19:12:54Z","links":{"resolver":"https://pith.science/pith/BUH2ZE5ISQQPQPXXN5LJASAIRK","bundle":"https://pith.science/pith/BUH2ZE5ISQQPQPXXN5LJASAIRK/bundle.json","state":"https://pith.science/pith/BUH2ZE5ISQQPQPXXN5LJASAIRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUH2ZE5ISQQPQPXXN5LJASAIRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUH2ZE5ISQQPQPXXN5LJASAIRK","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":"41e37693a3f18d444f5f083c9632e8922955a831f73452db1d4ce29c15f5105b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T09:18:32Z","title_canon_sha256":"edcaffb8c056fa1d557fd1396629eaebd4defc4ba61e014d38cfdc0e0aa3e0eb"},"schema_version":"1.0","source":{"id":"2412.06322","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06322","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06322v1","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06322","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"pith_short_12","alias_value":"BUH2ZE5ISQQP","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"pith_short_16","alias_value":"BUH2ZE5ISQQPQPXX","created_at":"2026-07-05T09:46:19Z"},{"alias_kind":"pith_short_8","alias_value":"BUH2ZE5I","created_at":"2026-07-05T09:46:19Z"}],"graph_snapshots":[{"event_id":"sha256:3849024ad699890ed1add9214859f13b0ed7b1ebb5a27e874c93a0a99063f229","target":"graph","created_at":"2026-07-05T09:46:19Z","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/2412.06322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scene Graph Generation (SGG) converts visual scenes into structured graph representations, providing deeper scene understanding for complex vision tasks. However, existing SGG models often overlook essential spatial relationships and struggle with generalization in open-vocabulary contexts. To address these limitations, we propose LLaVA-SpaceSGG, a multimodal large language model (MLLM) designed for open-vocabulary SGG with enhanced spatial relation modeling. To train it, we collect the SGG instruction-tuning dataset, named SpaceSGG. This dataset is constructed by combining publicly available ","authors_text":"Jason Chun Lok Li, Mengyang Wu, Mingjie Xu, Weifeng Ou, Yuzhi Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T09:18:32Z","title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06322","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:da8281dc6e7fe052a83775cedfdb1cb18cd5865c3daf7189d54131993845d7f0","target":"record","created_at":"2026-07-05T09:46:19Z","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":"41e37693a3f18d444f5f083c9632e8922955a831f73452db1d4ce29c15f5105b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T09:18:32Z","title_canon_sha256":"edcaffb8c056fa1d557fd1396629eaebd4defc4ba61e014d38cfdc0e0aa3e0eb"},"schema_version":"1.0","source":{"id":"2412.06322","kind":"arxiv","version":1}},"canonical_sha256":"0d0fac93a89420f83ef76f569048088a82ede231dc2a5a1bcba72eff01afea12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d0fac93a89420f83ef76f569048088a82ede231dc2a5a1bcba72eff01afea12","first_computed_at":"2026-07-05T09:46:19.139103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:19.139103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fCCs/jfOaEyd6C6DI03j4IgbfLuH+Dsf0X2jVJpB/iaplMB9b+bG1sMdjeafQYgU/rGVJozb9jNh3nuhpvuwBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:19.139584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06322","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da8281dc6e7fe052a83775cedfdb1cb18cd5865c3daf7189d54131993845d7f0","sha256:3849024ad699890ed1add9214859f13b0ed7b1ebb5a27e874c93a0a99063f229"],"state_sha256":"23fea3b960fb561fcda30ab657b48241a9031f604cec746345edf945a30c8a81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H/5RF66F7+N6Bjhvq/nC0D2WYhPFbaZaK+75PdyzMtOTfKePps8NGzfwVs15MfVKb8K3iMWGJ6NegmALwhOxDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:12:54.732376Z","bundle_sha256":"c83daf814ad9f8a0550d376c6a0be99df698fdad6dce81f0c91762d97a4eca6a"}}