{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OWTZRK4ERKHUHMPZDEYNVJOIAH","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":"1c7e790374608d47ee03fa8838b0cafe84bf6b30223147e2050f78abe17cc944","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T20:16:32Z","title_canon_sha256":"0a87593c1e4f0ee5c1b92a41582cb0c5afa64e5d929c5daa7e141d86850ceeb4"},"schema_version":"1.0","source":{"id":"2507.04151","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04151","created_at":"2026-07-05T11:32:42Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04151v1","created_at":"2026-07-05T11:32:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04151","created_at":"2026-07-05T11:32:42Z"},{"alias_kind":"pith_short_12","alias_value":"OWTZRK4ERKHU","created_at":"2026-07-05T11:32:42Z"},{"alias_kind":"pith_short_16","alias_value":"OWTZRK4ERKHUHMPZ","created_at":"2026-07-05T11:32:42Z"},{"alias_kind":"pith_short_8","alias_value":"OWTZRK4E","created_at":"2026-07-05T11:32:42Z"}],"graph_snapshots":[{"event_id":"sha256:c969a57cb7b76e705d3016f21924bbff530fb6f038be868cf142769aee8d209f","target":"graph","created_at":"2026-07-05T11:32:42Z","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/2507.04151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Hierarchical Self-Supervised LVLM (Hi-SSLVLM), a novel generative model designed to significantly advance text-to-image synthesis, particularly for complex and compositionally challenging prompts. Traditional methods often grapple with the high cost of meticulously curated paired image-text datasets and struggle with precise control over fine-grained visual attributes and intricate spatial relationships. Our Hi-SSLVLM addresses these limitations through a unique two-stage self-supervised learning strategy. The first stage, Multi-Granularity Visual-Language Grounding, enab","authors_text":"Fernando Gabriela Garcia, Hunter Young, Ryan Shaw, Spencer Burns","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T20:16:32Z","title":"Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04151","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":"sha256:18392a6f044e09a512e74c4a70d9756ee74167ac2ade35a852c5a76b3c8761f6","target":"record","created_at":"2026-07-05T11:32:42Z","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":"1c7e790374608d47ee03fa8838b0cafe84bf6b30223147e2050f78abe17cc944","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T20:16:32Z","title_canon_sha256":"0a87593c1e4f0ee5c1b92a41582cb0c5afa64e5d929c5daa7e141d86850ceeb4"},"schema_version":"1.0","source":{"id":"2507.04151","kind":"arxiv","version":1}},"canonical_sha256":"75a798ab848a8f43b1f91930daa5c801c18f4eaf0f6ea6150eb20bbde62d263e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75a798ab848a8f43b1f91930daa5c801c18f4eaf0f6ea6150eb20bbde62d263e","first_computed_at":"2026-07-05T11:32:42.825259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:42.825259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KRxZ1g/cUoXY8nP8LX8in0Vsfps3T4vnNCVTY2nw+pkj23Bso2CGk6PVEiHfZrifIgg0Dw7BOj59Vw4OnCpwAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:42.825796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04151","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18392a6f044e09a512e74c4a70d9756ee74167ac2ade35a852c5a76b3c8761f6","sha256:c969a57cb7b76e705d3016f21924bbff530fb6f038be868cf142769aee8d209f"],"state_sha256":"35dd31e8db16f9c93028382c4e2a8ae8d31aae16ed17e385b999ca75b9610d54"}