{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RW52MPL5ED325SK2FHLZJD6OE5","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":"d442c833a0705db3f13df83c63e4082c0906423831841a94912c45d5e3130fdc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-20T18:59:54Z","title_canon_sha256":"34a3166dfc4c413fdbbe12dee39bbca1c9e6b8f39333b28521225a25a631476d"},"schema_version":"1.0","source":{"id":"2511.16672","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.16672","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"arxiv_version","alias_value":"2511.16672v4","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16672","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"pith_short_12","alias_value":"RW52MPL5ED32","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"pith_short_16","alias_value":"RW52MPL5ED325SK2","created_at":"2026-06-11T01:09:22Z"},{"alias_kind":"pith_short_8","alias_value":"RW52MPL5","created_at":"2026-06-11T01:09:22Z"}],"graph_snapshots":[{"event_id":"sha256:eb35192909a492de7b865dbd36d763103d8d084b8e319a46d2d514e2d7ccf016","target":"graph","created_at":"2026-06-11T01:09:22Z","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/2511.16672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their autonomy and scalability. In this work, we strive to improve LMM reasoning capabilities in a purely unsupervised fashion (without any annotated data or reward distillation). To this end, we propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model: a Proposer, which generates diverse, image-grounded que","authors_text":"Abdelrahman Shaker, Fahad Khan, Hisham Cholakkal, Omkar Thawakar, Rao Muhammad Anwer, Ritesh Thawkar, Salman Khan, Shravan Venkatraman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-20T18:59:54Z","title":"EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.16672","kind":"arxiv","version":4},"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":"sha256:1bfede1f2c108a83f18b68b542339d8fb32e72f6a532b030dd90a87bbc134290","target":"record","created_at":"2026-06-11T01:09:22Z","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":"d442c833a0705db3f13df83c63e4082c0906423831841a94912c45d5e3130fdc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-11-20T18:59:54Z","title_canon_sha256":"34a3166dfc4c413fdbbe12dee39bbca1c9e6b8f39333b28521225a25a631476d"},"schema_version":"1.0","source":{"id":"2511.16672","kind":"arxiv","version":4}},"canonical_sha256":"8dbba63d7d20f7aec95a29d7948fce2766d8b2f7d677acdc873e3e84a6593b53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dbba63d7d20f7aec95a29d7948fce2766d8b2f7d677acdc873e3e84a6593b53","first_computed_at":"2026-06-11T01:09:22.200556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:22.200556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jygJ45hV0N1R9kIm/R241kkjucY64kd/WlwRaKFM40FbpwrTXSsWEMFNeEaL0d4Oed9PgY+oxxbrDmLnpZJ7Cw==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:22.201704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.16672","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bfede1f2c108a83f18b68b542339d8fb32e72f6a532b030dd90a87bbc134290","sha256:eb35192909a492de7b865dbd36d763103d8d084b8e319a46d2d514e2d7ccf016"],"state_sha256":"32dc25e65eb21912129e5f5c718ea35e6dcbd4a6c8fceba506b2e1130fe82893"}