{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UPYJA4WKJ2FU7BBQGS6NMJPU7U","short_pith_number":"pith:UPYJA4WK","canonical_record":{"source":{"id":"2605.30265","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:27:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4bda0fe6d3035c3ada45f11d0f979a3c54d46af9f346daf31318ca469c096e32","abstract_canon_sha256":"4950ca4ff3b363952335a13675527877a734b4ea37eb41679ac45d58cca19f0f"},"schema_version":"1.0"},"canonical_sha256":"a3f09072ca4e8b4f843034bcd625f4fd1b65772cabf25211bfce278c49366a04","source":{"kind":"arxiv","id":"2605.30265","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30265","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30265v1","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30265","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"UPYJA4WKJ2FU","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"UPYJA4WKJ2FU7BBQ","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"UPYJA4WK","created_at":"2026-05-29T02:06:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UPYJA4WKJ2FU7BBQGS6NMJPU7U","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30265","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:27:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4bda0fe6d3035c3ada45f11d0f979a3c54d46af9f346daf31318ca469c096e32","abstract_canon_sha256":"4950ca4ff3b363952335a13675527877a734b4ea37eb41679ac45d58cca19f0f"},"schema_version":"1.0"},"canonical_sha256":"a3f09072ca4e8b4f843034bcd625f4fd1b65772cabf25211bfce278c49366a04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:14.522248Z","signature_b64":"847CsbVlZm14oOZMucRSZcECdyBGDfn0Bb0qCcNCtftu8Q/dAJ06hebNmmjkLvQCfqCHmUSR4FHrCywznx+bCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3f09072ca4e8b4f843034bcd625f4fd1b65772cabf25211bfce278c49366a04","last_reissued_at":"2026-05-29T02:06:14.521597Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:14.521597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30265","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":"2026-05-29T02:06:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O9evEfDjDId4224fIjDUvfhCha5ABHbiJcocfmXTqs6HDTHHQICJg5vCtfE5E6w3kcC7bd4SWgEbByGZ7bFGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:28:52.222077Z"},"content_sha256":"66364db965b8e944d889d5636cf76a387f9f1c22c58dad9f9f0e5c69cc8c53ca","schema_version":"1.0","event_id":"sha256:66364db965b8e944d889d5636cf76a387f9f1c22c58dad9f9f0e5c69cc8c53ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UPYJA4WKJ2FU7BBQGS6NMJPU7U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoMo: Local Modality Substitution for Deeper Vision-Language Fusion","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Feng Han, Jiaqi Wang, Yibin Wang, Zheming Liang, Zhixiong Zhang","submitted_at":"2026-05-28T17:27:55Z","abstract_excerpt":"Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its rendered-image counterpart should leave model performance essentially unaffected. In practice, however, such modality substitution induces dramatic performance degradation. We attribute this \"carrier sensitivity\" issue to an inherent bias in current training corpora. Across prevalent datasets such as image captioning, VQA, OCR, and web-sourced interleaved da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30265","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/2605.30265/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":"2026-05-29T02:06:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0GUtwfucdwPuojdn3ycBf2irkVSNfkPuW+0jomknmbm43KbL8i8eyJtiHS+YExah5NsPPmwRT/Yc/44fuE2hBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:28:52.222938Z"},"content_sha256":"ce55e4f4df555da3f1849935e8d64ba8b8f90878476d0362696bc4eddbdda4c7","schema_version":"1.0","event_id":"sha256:ce55e4f4df555da3f1849935e8d64ba8b8f90878476d0362696bc4eddbdda4c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPYJA4WKJ2FU7BBQGS6NMJPU7U/bundle.json","state_url":"https://pith.science/pith/UPYJA4WKJ2FU7BBQGS6NMJPU7U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPYJA4WKJ2FU7BBQGS6NMJPU7U/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":"2026-06-09T09:28:52Z","links":{"resolver":"https://pith.science/pith/UPYJA4WKJ2FU7BBQGS6NMJPU7U","bundle":"https://pith.science/pith/UPYJA4WKJ2FU7BBQGS6NMJPU7U/bundle.json","state":"https://pith.science/pith/UPYJA4WKJ2FU7BBQGS6NMJPU7U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPYJA4WKJ2FU7BBQGS6NMJPU7U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UPYJA4WKJ2FU7BBQGS6NMJPU7U","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":"4950ca4ff3b363952335a13675527877a734b4ea37eb41679ac45d58cca19f0f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:27:55Z","title_canon_sha256":"4bda0fe6d3035c3ada45f11d0f979a3c54d46af9f346daf31318ca469c096e32"},"schema_version":"1.0","source":{"id":"2605.30265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30265","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30265v1","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30265","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_12","alias_value":"UPYJA4WKJ2FU","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_16","alias_value":"UPYJA4WKJ2FU7BBQ","created_at":"2026-05-29T02:06:14Z"},{"alias_kind":"pith_short_8","alias_value":"UPYJA4WK","created_at":"2026-05-29T02:06:14Z"}],"graph_snapshots":[{"event_id":"sha256:ce55e4f4df555da3f1849935e8d64ba8b8f90878476d0362696bc4eddbdda4c7","target":"graph","created_at":"2026-05-29T02:06:14Z","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/2605.30265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its rendered-image counterpart should leave model performance essentially unaffected. In practice, however, such modality substitution induces dramatic performance degradation. We attribute this \"carrier sensitivity\" issue to an inherent bias in current training corpora. Across prevalent datasets such as image captioning, VQA, OCR, and web-sourced interleaved da","authors_text":"Feng Han, Jiaqi Wang, Yibin Wang, Zheming Liang, Zhixiong Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:27:55Z","title":"LoMo: Local Modality Substitution for Deeper Vision-Language Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30265","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":"sha256:66364db965b8e944d889d5636cf76a387f9f1c22c58dad9f9f0e5c69cc8c53ca","target":"record","created_at":"2026-05-29T02:06:14Z","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":"4950ca4ff3b363952335a13675527877a734b4ea37eb41679ac45d58cca19f0f","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:27:55Z","title_canon_sha256":"4bda0fe6d3035c3ada45f11d0f979a3c54d46af9f346daf31318ca469c096e32"},"schema_version":"1.0","source":{"id":"2605.30265","kind":"arxiv","version":1}},"canonical_sha256":"a3f09072ca4e8b4f843034bcd625f4fd1b65772cabf25211bfce278c49366a04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3f09072ca4e8b4f843034bcd625f4fd1b65772cabf25211bfce278c49366a04","first_computed_at":"2026-05-29T02:06:14.521597Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:14.521597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"847CsbVlZm14oOZMucRSZcECdyBGDfn0Bb0qCcNCtftu8Q/dAJ06hebNmmjkLvQCfqCHmUSR4FHrCywznx+bCQ==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:14.522248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66364db965b8e944d889d5636cf76a387f9f1c22c58dad9f9f0e5c69cc8c53ca","sha256:ce55e4f4df555da3f1849935e8d64ba8b8f90878476d0362696bc4eddbdda4c7"],"state_sha256":"51c9445b7a704a8dd88ab2103673aec34a943fb5d4a5ac979947d910b2554ffd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohrCC6gj0IT15/SPuHdDcZxXmpntKjkoFpzRNUvpVPGAwkRblN/zgmJ0sg5/KQw1Cw+b30t5HoLh++nWNZBQAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T09:28:52.227601Z","bundle_sha256":"fbd091d9724c622de0ec9729b465fb36b75bc37138788731f94b60f235c00997"}}