{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BLQD2IGJ4J6ZEKDN6PFSVUYHKQ","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":"a3ad02453bbc09a9bbb179b7dd8a202cfba0031247af8c753ac74c6f1370c0d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T17:59:55Z","title_canon_sha256":"ea026418409db0eb3c2fa2b5bff6a8f378d128dfa936a54eac0e5b8ffd417c46"},"schema_version":"1.0","source":{"id":"2606.27373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27373","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27373v1","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27373","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"BLQD2IGJ4J6Z","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"BLQD2IGJ4J6ZEKDN","created_at":"2026-06-26T01:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"BLQD2IGJ","created_at":"2026-06-26T01:16:20Z"}],"graph_snapshots":[{"event_id":"sha256:f34835b6a3cb4a147298376bb9d13f8f886e2ac231586fd6158cd9d741ee55ac","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/2606.27373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, self-evolving large multimodal models (LMMs) have received attention for improving visual reasoning in a purely unsupervised setting. However, multi-role self-play and self-consistency reward schemes in existing self-evolving LMMs optimize answer agreement without ensuring the decoder attends to visual content, relying instead on statistical language priors to produce self consistent outputs. This leads to a persistent failure mode we term visual under-conditioning, where the decoder relies on language priors rather than the image during generation, manifesting as insufficient attent","authors_text":"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":"2026-06-25T17:59:55Z","title":"Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27373","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:e7944c75dd9292668a6636d97c6a3e76570f5dd2f41ccbbeab9fc8d0417f25f1","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":"a3ad02453bbc09a9bbb179b7dd8a202cfba0031247af8c753ac74c6f1370c0d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T17:59:55Z","title_canon_sha256":"ea026418409db0eb3c2fa2b5bff6a8f378d128dfa936a54eac0e5b8ffd417c46"},"schema_version":"1.0","source":{"id":"2606.27373","kind":"arxiv","version":1}},"canonical_sha256":"0ae03d20c9e27d92286df3cb2ad307543c6d4a69849dbb0a5afd5cf6f89d1948","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ae03d20c9e27d92286df3cb2ad307543c6d4a69849dbb0a5afd5cf6f89d1948","first_computed_at":"2026-06-26T01:16:20.192125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:20.192125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LYY2buXL0c+G3VG7VGgMj4NDqzOr+Yxw/2FlxLiv8z+6Yt2sKfXrfGYyUNzpF68ctD/4B48R7W3Jr4hPOdwpCQ==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:20.192531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7944c75dd9292668a6636d97c6a3e76570f5dd2f41ccbbeab9fc8d0417f25f1","sha256:f34835b6a3cb4a147298376bb9d13f8f886e2ac231586fd6158cd9d741ee55ac"],"state_sha256":"641347a5f52bc1849af4cee6542a73dc8bc165ea31034ededd41cb8510b088cb"}