{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CZHIZUUWWWOG2DCWSN4X7US4NZ","short_pith_number":"pith:CZHIZUUW","schema_version":"1.0","canonical_sha256":"164e8cd296b59c6d0c5693797fd25c6e4bdbed87870bdfda43843bf9f8447b85","source":{"kind":"arxiv","id":"2606.27376","version":1},"attestation_state":"computed","paper":{"title":"Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Khan, Hisham Cholakkal, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Shravan Venkatraman","submitted_at":"2026-06-25T17:59:57Z","abstract_excerpt":"Most unified large multimodal models (LMMs) that support both visual understanding and image generation still rely on curated post-training supervision, such as human annotations, preference labels, or external reward models. We ask whether a unified LMM can improve both abilities autonomously using only unlabeled images. We propose a self-evolving training framework with three internal roles: a Proposer that generates visual questions, a Solver that answers and evaluates them, and a Generator that synthesizes images. Training uses only self-derived consistency signals, without human annotatio"},"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":"2606.27376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T17:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"414c927aecebf60f7285931daca132d75fe93b312e40810281a4ff249beeb083","abstract_canon_sha256":"05e853ff8ef66130641cd7a0d8d9983943ebb65db1620ab059c454fb26d22db7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:20.328512Z","signature_b64":"WUN0ewZerUjC45alXuLon/k1N47lMQQUy0vasbh7lW3YMi5aI0b8OOw3dN5D9D+rfS2ll3FrXPDcH686AAmrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"164e8cd296b59c6d0c5693797fd25c6e4bdbed87870bdfda43843bf9f8447b85","last_reissued_at":"2026-06-26T01:16:20.328105Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:20.328105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Khan, Hisham Cholakkal, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Shravan Venkatraman","submitted_at":"2026-06-25T17:59:57Z","abstract_excerpt":"Most unified large multimodal models (LMMs) that support both visual understanding and image generation still rely on curated post-training supervision, such as human annotations, preference labels, or external reward models. We ask whether a unified LMM can improve both abilities autonomously using only unlabeled images. We propose a self-evolving training framework with three internal roles: a Proposer that generates visual questions, a Solver that answers and evaluates them, and a Generator that synthesizes images. Training uses only self-derived consistency signals, without human annotatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27376","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/2606.27376/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":"2606.27376","created_at":"2026-06-26T01:16:20.328162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27376v1","created_at":"2026-06-26T01:16:20.328162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27376","created_at":"2026-06-26T01:16:20.328162+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZHIZUUWWWOG","created_at":"2026-06-26T01:16:20.328162+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZHIZUUWWWOG2DCW","created_at":"2026-06-26T01:16:20.328162+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZHIZUUW","created_at":"2026-06-26T01:16:20.328162+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/CZHIZUUWWWOG2DCWSN4X7US4NZ","json":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ.json","graph_json":"https://pith.science/api/pith-number/CZHIZUUWWWOG2DCWSN4X7US4NZ/graph.json","events_json":"https://pith.science/api/pith-number/CZHIZUUWWWOG2DCWSN4X7US4NZ/events.json","paper":"https://pith.science/paper/CZHIZUUW"},"agent_actions":{"view_html":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ","download_json":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ.json","view_paper":"https://pith.science/paper/CZHIZUUW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27376&json=true","fetch_graph":"https://pith.science/api/pith-number/CZHIZUUWWWOG2DCWSN4X7US4NZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CZHIZUUWWWOG2DCWSN4X7US4NZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/action/storage_attestation","attest_author":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/action/author_attestation","sign_citation":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/action/citation_signature","submit_replication":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/action/replication_record"}},"created_at":"2026-06-26T01:16:20.328162+00:00","updated_at":"2026-06-26T01:16:20.328162+00:00"}