{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2N3RDPOOOPNRN2GTW2JOK4KIRZ","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":"38d815672282cd594ee39cb7568845d9ab6168b398cf9f33c8a45e0c93b68401","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T09:12:21Z","title_canon_sha256":"f2a691b26e048d6c97be60dd201ca1233254fef2ac03fc7ca8c1fc0d7e448444"},"schema_version":"1.0","source":{"id":"2602.17186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17186","created_at":"2026-05-22T01:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17186v2","created_at":"2026-05-22T01:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17186","created_at":"2026-05-22T01:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"2N3RDPOOOPNR","created_at":"2026-05-22T01:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"2N3RDPOOOPNRN2GT","created_at":"2026-05-22T01:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"2N3RDPOO","created_at":"2026-05-22T01:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:c4c04b2a9dc1308196abb5b3bfb706d877c0b8b0fa4b1d9686d36ffa95a2f4b2","target":"graph","created_at":"2026-05-22T01:03:58Z","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/2602.17186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models (LVLMs) have achieved remarkable progress, yet they often suffer from language bias, producing answers without relying on visual evidence. While prior work attempts to mitigate this issue through decoding strategies, architectural modifications, or curated instruction data, they typically lack a quantitative measure of how much individual training samples or tokens actually benefit from the image. In this work, we introduce Visual Information Gain (VIG), a perplexity-based metric that measures the reduction in prediction uncertainty provided by visual input. VIG en","authors_text":"Sangheum Hwang, Seulbi Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T09:12:21Z","title":"Focusing Where Vision Matters: Selective Training for Large Vision Language Models via Visual Information Gain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.17186","kind":"arxiv","version":2},"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":"sha256:0c4b526952f866cf7b1d496122cd7078d6ede2b08d5d8c4ff5d07e3dc469d1aa","target":"record","created_at":"2026-05-22T01:03:58Z","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":"38d815672282cd594ee39cb7568845d9ab6168b398cf9f33c8a45e0c93b68401","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-19T09:12:21Z","title_canon_sha256":"f2a691b26e048d6c97be60dd201ca1233254fef2ac03fc7ca8c1fc0d7e448444"},"schema_version":"1.0","source":{"id":"2602.17186","kind":"arxiv","version":2}},"canonical_sha256":"d37711bdce73db16e8d3b692e571488e47b0724dab0f2fd7720c0ee6f54d9880","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d37711bdce73db16e8d3b692e571488e47b0724dab0f2fd7720c0ee6f54d9880","first_computed_at":"2026-05-22T01:03:58.014389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:58.014389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J4yVv+Ip6fZRL4g47ZLBj7Q2yZlvUpnMm/TJO/BLJxJauDD3tnIBhyr0dJWa7cGuwVLBMes831imU89aASEVBw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:58.015174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c4b526952f866cf7b1d496122cd7078d6ede2b08d5d8c4ff5d07e3dc469d1aa","sha256:c4c04b2a9dc1308196abb5b3bfb706d877c0b8b0fa4b1d9686d36ffa95a2f4b2"],"state_sha256":"5c31a485373a0a34b1811b8d1456e353934384fad2f5537870ca374c7693fd86"}