{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CZHIZUUWWWOG2DCWSN4X7US4NZ","short_pith_number":"pith:CZHIZUUW","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"},"canonical_sha256":"164e8cd296b59c6d0c5693797fd25c6e4bdbed87870bdfda43843bf9f8447b85","source":{"kind":"arxiv","id":"2606.27376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27376","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27376v1","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27376","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"CZHIZUUWWWOG","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"CZHIZUUWWWOG2DCW","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"CZHIZUUW","created_at":"2026-06-26T01:16:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CZHIZUUWWWOG2DCWSN4X7US4NZ","target":"record","payload":{"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"},"canonical_sha256":"164e8cd296b59c6d0c5693797fd25c6e4bdbed87870bdfda43843bf9f8447b85","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"},"source_kind":"arxiv","source_id":"2606.27376","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":"2026-06-26T01:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+ZxgL0Lf6aVTllu5IeZYlnGEKn8pLMH82s3PhRtRzwnr7hRuFMR2jhBPDvaM0XRbqi4aqo2FX6bvnOGPaVvDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T11:36:49.504268Z"},"content_sha256":"430fce274bbc3234d14ecf374164e4b0419ea5b728c99a783a832209439419a1","schema_version":"1.0","event_id":"sha256:430fce274bbc3234d14ecf374164e4b0419ea5b728c99a783a832209439419a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CZHIZUUWWWOG2DCWSN4X7US4NZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T01:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aMzyuLFoX0AhE7yLPyW4pTU82aSpFLB9+J1+ngzgIrKgyc9lawu6iYZBLXoV53zLN33+a1tCzJzDnk98QvACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T11:36:49.504668Z"},"content_sha256":"5989ca90bf3428581fd37e98f5dc1204f547f3c24594bc941ae00efa6b75276c","schema_version":"1.0","event_id":"sha256:5989ca90bf3428581fd37e98f5dc1204f547f3c24594bc941ae00efa6b75276c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/bundle.json","state_url":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/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":"2026-06-26T11:36:49Z","links":{"resolver":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ","bundle":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/bundle.json","state":"https://pith.science/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZHIZUUWWWOG2DCWSN4X7US4NZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CZHIZUUWWWOG2DCWSN4X7US4NZ","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":"05e853ff8ef66130641cd7a0d8d9983943ebb65db1620ab059c454fb26d22db7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T17:59:57Z","title_canon_sha256":"414c927aecebf60f7285931daca132d75fe93b312e40810281a4ff249beeb083"},"schema_version":"1.0","source":{"id":"2606.27376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27376","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27376v1","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27376","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"CZHIZUUWWWOG","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"CZHIZUUWWWOG2DCW","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"CZHIZUUW","created_at":"2026-06-26T01:16:20Z"}],"graph_snapshots":[{"event_id":"sha256:5989ca90bf3428581fd37e98f5dc1204f547f3c24594bc941ae00efa6b75276c","target":"graph","created_at":"2026-06-26T01:16:20Z","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/2606.27376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdelrahman Shaker, Fahad Khan, Hisham Cholakkal, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Shravan Venkatraman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T17:59:57Z","title":"Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27376","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":"sha256:430fce274bbc3234d14ecf374164e4b0419ea5b728c99a783a832209439419a1","target":"record","created_at":"2026-06-26T01:16:20Z","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":"05e853ff8ef66130641cd7a0d8d9983943ebb65db1620ab059c454fb26d22db7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T17:59:57Z","title_canon_sha256":"414c927aecebf60f7285931daca132d75fe93b312e40810281a4ff249beeb083"},"schema_version":"1.0","source":{"id":"2606.27376","kind":"arxiv","version":1}},"canonical_sha256":"164e8cd296b59c6d0c5693797fd25c6e4bdbed87870bdfda43843bf9f8447b85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"164e8cd296b59c6d0c5693797fd25c6e4bdbed87870bdfda43843bf9f8447b85","first_computed_at":"2026-06-26T01:16:20.328105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:20.328105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WUN0ewZerUjC45alXuLon/k1N47lMQQUy0vasbh7lW3YMi5aI0b8OOw3dN5D9D+rfS2ll3FrXPDcH686AAmrBw==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:20.328512Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:430fce274bbc3234d14ecf374164e4b0419ea5b728c99a783a832209439419a1","sha256:5989ca90bf3428581fd37e98f5dc1204f547f3c24594bc941ae00efa6b75276c"],"state_sha256":"6df729148d500debdf96816d5c6bcf03fed599a68175270072f9fedfc963e335"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t9dPKCG41KOk/fMCOLxVCeA/C6VksH3IxlFM6kYXQC0Ha3iqXlHm3mis7g3pZWbqpAD9SazPaO22VaSteogeAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T11:36:49.506766Z","bundle_sha256":"e010e45d826de8c30710c9bd930809196d1fefb3b89e992b67c15c5cf015baff"}}