{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GWAXIDELMOZDJYN23TTTEOM2XH","short_pith_number":"pith:GWAXIDEL","schema_version":"1.0","canonical_sha256":"3581740c8b63b234e1badce732399ab9c9addab4cc8e6d88cd1b9b7d2faf1e5f","source":{"kind":"arxiv","id":"2506.07643","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Visual Genome","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Farhadi, Cheng-Yu Hsieh, Chenhao Zheng, Jae Sung Park, Khyathi Chandu, Linjie Li, Norimasa Kobori, Quan Kong, Ranjay Krishna, Ximing Lu, Yejin Choi, Zixian Ma","submitted_at":"2025-06-09T11:09:10Z","abstract_excerpt":"Reasoning over visual relationships-spatial, functional, interactional, social, etc.-is considered to be a fundamental component of human cognition. Yet, despite the major advances in visual comprehension in multimodal language models (MLMs), precise reasoning over relationships and their generations remains a challenge. We introduce ROBIN: an MLM instruction-tuned with densely annotated relationships capable of constructing high-quality dense scene graphs at scale. To train ROBIN, we curate SVG, a synthetic scene graph dataset by completing the missing relations of selected objects in existin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.07643","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T11:09:10Z","cross_cats_sorted":[],"title_canon_sha256":"921de317798aef3bc1387d59cb4b8b6c26fb4a96a110c430350f804f99ded577","abstract_canon_sha256":"7a66c1386c5df7dbee351eb6c7f0b8625f9aa1fee3c048f59412c28401ccbb22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:30.810581Z","signature_b64":"MDG7gMyFTgu5Uj39JCsyVLd0K9L5PDMfzakLU2DKfe7hJ/raiADQVW7b4nf2L+i6EV5H6CjklYAHxA+xJ1jmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3581740c8b63b234e1badce732399ab9c9addab4cc8e6d88cd1b9b7d2faf1e5f","last_reissued_at":"2026-07-05T11:18:30.810086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:30.810086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Visual Genome","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Farhadi, Cheng-Yu Hsieh, Chenhao Zheng, Jae Sung Park, Khyathi Chandu, Linjie Li, Norimasa Kobori, Quan Kong, Ranjay Krishna, Ximing Lu, Yejin Choi, Zixian Ma","submitted_at":"2025-06-09T11:09:10Z","abstract_excerpt":"Reasoning over visual relationships-spatial, functional, interactional, social, etc.-is considered to be a fundamental component of human cognition. Yet, despite the major advances in visual comprehension in multimodal language models (MLMs), precise reasoning over relationships and their generations remains a challenge. We introduce ROBIN: an MLM instruction-tuned with densely annotated relationships capable of constructing high-quality dense scene graphs at scale. To train ROBIN, we curate SVG, a synthetic scene graph dataset by completing the missing relations of selected objects in existin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07643","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/2506.07643/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.07643","created_at":"2026-07-05T11:18:30.810142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07643v1","created_at":"2026-07-05T11:18:30.810142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07643","created_at":"2026-07-05T11:18:30.810142+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWAXIDELMOZD","created_at":"2026-07-05T11:18:30.810142+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWAXIDELMOZDJYN2","created_at":"2026-07-05T11:18:30.810142+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWAXIDEL","created_at":"2026-07-05T11:18:30.810142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH","json":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH.json","graph_json":"https://pith.science/api/pith-number/GWAXIDELMOZDJYN23TTTEOM2XH/graph.json","events_json":"https://pith.science/api/pith-number/GWAXIDELMOZDJYN23TTTEOM2XH/events.json","paper":"https://pith.science/paper/GWAXIDEL"},"agent_actions":{"view_html":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH","download_json":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH.json","view_paper":"https://pith.science/paper/GWAXIDEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07643&json=true","fetch_graph":"https://pith.science/api/pith-number/GWAXIDELMOZDJYN23TTTEOM2XH/graph.json","fetch_events":"https://pith.science/api/pith-number/GWAXIDELMOZDJYN23TTTEOM2XH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH/action/storage_attestation","attest_author":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH/action/author_attestation","sign_citation":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH/action/citation_signature","submit_replication":"https://pith.science/pith/GWAXIDELMOZDJYN23TTTEOM2XH/action/replication_record"}},"created_at":"2026-07-05T11:18:30.810142+00:00","updated_at":"2026-07-05T11:18:30.810142+00:00"}