{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OWTZRK4ERKHUHMPZDEYNVJOIAH","short_pith_number":"pith:OWTZRK4E","schema_version":"1.0","canonical_sha256":"75a798ab848a8f43b1f91930daa5c801c18f4eaf0f6ea6150eb20bbde62d263e","source":{"kind":"arxiv","id":"2507.04151","version":1},"attestation_state":"computed","paper":{"title":"Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fernando Gabriela Garcia, Hunter Young, Ryan Shaw, Spencer Burns","submitted_at":"2025-07-05T20:16:32Z","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"},"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":"2507.04151","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-05T20:16:32Z","cross_cats_sorted":[],"title_canon_sha256":"0a87593c1e4f0ee5c1b92a41582cb0c5afa64e5d929c5daa7e141d86850ceeb4","abstract_canon_sha256":"1c7e790374608d47ee03fa8838b0cafe84bf6b30223147e2050f78abe17cc944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:42.825796Z","signature_b64":"KRxZ1g/cUoXY8nP8LX8in0Vsfps3T4vnNCVTY2nw+pkj23Bso2CGk6PVEiHfZrifIgg0Dw7BOj59Vw4OnCpwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75a798ab848a8f43b1f91930daa5c801c18f4eaf0f6ea6150eb20bbde62d263e","last_reissued_at":"2026-07-05T11:32:42.825259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:42.825259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fernando Gabriela Garcia, Hunter Young, Ryan Shaw, Spencer Burns","submitted_at":"2025-07-05T20:16:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04151","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/2507.04151/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":"2507.04151","created_at":"2026-07-05T11:32:42.825355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04151v1","created_at":"2026-07-05T11:32:42.825355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04151","created_at":"2026-07-05T11:32:42.825355+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWTZRK4ERKHU","created_at":"2026-07-05T11:32:42.825355+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWTZRK4ERKHUHMPZ","created_at":"2026-07-05T11:32:42.825355+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWTZRK4E","created_at":"2026-07-05T11:32:42.825355+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/OWTZRK4ERKHUHMPZDEYNVJOIAH","json":"https://pith.science/pith/OWTZRK4ERKHUHMPZDEYNVJOIAH.json","graph_json":"https://pith.science/api/pith-number/OWTZRK4ERKHUHMPZDEYNVJOIAH/graph.json","events_json":"https://pith.science/api/pith-number/OWTZRK4ERKHUHMPZDEYNVJOIAH/events.json","paper":"https://pith.science/paper/OWTZRK4E"},"agent_actions":{"view_html":"https://pith.science/pith/OWTZRK4ERKHUHMPZDEYNVJOIAH","download_json":"https://pith.science/pith/OWTZRK4ERKHUHMPZDEYNVJOIAH.json","view_paper":"https://pith.science/paper/OWTZRK4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04151&json=true","fetch_graph":"https://pith.science/api/pith-number/OWTZRK4ERKHUHMPZDEYNVJOIAH/graph.json","fetch_events":"https://pith.science/api/pith-number/OWTZRK4ERKHUHMPZDEYNVJOIAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWTZRK4ERKHUHMPZDEYNVJOIAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWTZRK4ERKHUHMPZDEYNVJOIAH/action/storage_attestation","attest_author":"https://pith.science/pith/OWTZRK4ERKHUHMPZDEYNVJOIAH/action/author_attestation","sign_citation":"https://pith.science/pith/OWTZRK4ERKHUHMPZDEYNVJOIAH/action/citation_signature","submit_replication":"https://pith.science/pith/OWTZRK4ERKHUHMPZDEYNVJOIAH/action/replication_record"}},"created_at":"2026-07-05T11:32:42.825355+00:00","updated_at":"2026-07-05T11:32:42.825355+00:00"}