{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KALDCBDNNOWWQKIFZ6QLKDARYW","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":"d2d19e0cfad04bf93083b02bbf35b3dd7b7a3a8ee519c522b805f8829da13682","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T15:53:42Z","title_canon_sha256":"90fffceffa4c2b839cfadc9a6b1464c9ea5fb7a61e48a50b55dd0bd1d226d92b"},"schema_version":"1.0","source":{"id":"2601.05877","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.05877","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2601.05877v3","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05877","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"KALDCBDNNOWW","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"KALDCBDNNOWWQKIF","created_at":"2026-05-21T01:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"KALDCBDN","created_at":"2026-05-21T01:04:20Z"}],"graph_snapshots":[{"event_id":"sha256:b7302dd2e91f480d5e04b8665e811ea8fb96f57922f7b2976c8ad2f9e9f05fa5","target":"graph","created_at":"2026-05-21T01:04:20Z","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/2601.05877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work shows that large multimodal models (LMMs) can self-improve from unlabeled data via self-play and intrinsic feedback. Yet existing self-evolving frameworks mainly reward final outcomes, leaving intermediate reasoning weakly constrained despite its importance for visually grounded decision making. We propose iReasoner, a self-evolving framework that improves an LMM's implicit reasoning by explicitly eliciting chain-of-thought (CoT) and rewarding its internal agreement. In a Proposer--Solver loop over unlabeled images, iReasoner augments outcome-level intrinsic rewards with a trajecto","authors_text":"Manikandarajan Venmathimaran, Meghana Sunil, Muthu Subash Kavitha","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T15:53:42Z","title":"iReasoner: Trajectory-Aware Intrinsic Reasoning Supervision for Self-Evolving Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05877","kind":"arxiv","version":3},"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:df84aa2e3fc525544e8811e6b6932a261fdb6b11c1541b410a9b9fa995ef4e90","target":"record","created_at":"2026-05-21T01:04:20Z","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":"d2d19e0cfad04bf93083b02bbf35b3dd7b7a3a8ee519c522b805f8829da13682","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-09T15:53:42Z","title_canon_sha256":"90fffceffa4c2b839cfadc9a6b1464c9ea5fb7a61e48a50b55dd0bd1d226d92b"},"schema_version":"1.0","source":{"id":"2601.05877","kind":"arxiv","version":3}},"canonical_sha256":"501631046d6bad682905cfa0b50c11c58e1f03890ce95375f2f6427d71a887f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"501631046d6bad682905cfa0b50c11c58e1f03890ce95375f2f6427d71a887f6","first_computed_at":"2026-05-21T01:04:20.763994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:20.763994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LjdpU23Ki4bZo3J+OyDRilT0kfhLfRufFnXx45JvbGyQ3Ux815RCE2/Xhy/rYr13VbZorx//DVSWlR4q8OduBA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:20.764899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.05877","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df84aa2e3fc525544e8811e6b6932a261fdb6b11c1541b410a9b9fa995ef4e90","sha256:b7302dd2e91f480d5e04b8665e811ea8fb96f57922f7b2976c8ad2f9e9f05fa5"],"state_sha256":"29017cbebeece7cf3af057041ce894fe1e51292c3d3e2c69c7b70abcf7da699c"}