{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HXMSTDT75FZM4VLXRJO7YZTEAH","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":"cfc00a069f1c503882c263f3d3d489a94f3db5df9f5f67e8158200df12cfdee1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T00:25:52Z","title_canon_sha256":"36564daa8fd7c2252b55fca36aa59a8b9a7e0f16fade69534973db7d3d6a63b4"},"schema_version":"1.0","source":{"id":"2607.28640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28640","created_at":"2026-08-03T00:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28640v1","created_at":"2026-08-03T00:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28640","created_at":"2026-08-03T00:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"HXMSTDT75FZM","created_at":"2026-08-03T00:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"HXMSTDT75FZM4VLX","created_at":"2026-08-03T00:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"HXMSTDT7","created_at":"2026-08-03T00:11:52Z"}],"graph_snapshots":[{"event_id":"sha256:5c037302ca7369b033cdeb37a237ea19d203d44d9aad5755361bdcd76d446f60","target":"graph","created_at":"2026-08-03T00:11:52Z","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/2607.28640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) should generate consistent responses given semantically equivalent inputs across modalities. However, we observe a systematic discrepancy in model predictions under such cross-modal variations. Specifically, we define the modality gap as the difference in model performance under semantically equivalent textual and multimodal inputs. We introduce TokenSwap, a method that constructs such inputs by replacing textual concepts with semantically aligned images, resulting in sequences where visual tokens are interleaved with text tokens. Based on TokenSwap, we","authors_text":"Aleksandra Faust, Andong Hua, Arian Hosseini, Colton Bishop, Igor Mordatch, Jindong Gu, Rebecca Roelofs, Yao Qin","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T00:25:52Z","title":"TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28640","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":"sha256:7f39ded3beb312d626feec89de0091b3df31b35479b73256f6f378b7b2855d33","target":"record","created_at":"2026-08-03T00:11:52Z","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":"cfc00a069f1c503882c263f3d3d489a94f3db5df9f5f67e8158200df12cfdee1","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T00:25:52Z","title_canon_sha256":"36564daa8fd7c2252b55fca36aa59a8b9a7e0f16fade69534973db7d3d6a63b4"},"schema_version":"1.0","source":{"id":"2607.28640","kind":"arxiv","version":1}},"canonical_sha256":"3dd9298e7fe972ce55778a5dfc666401f467befb016892f44b646681bd966b10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dd9298e7fe972ce55778a5dfc666401f467befb016892f44b646681bd966b10","first_computed_at":"2026-08-03T00:11:52.880902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T00:11:52.880902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4pPwlq2rErvLiUNrfNpCo166T+8/9miCTo1iuOMhLABHkAIqZkTWZtFCbmVeM1VtaHXDer818tVuhMH/Cws5BA==","signature_status":"signed_v1","signed_at":"2026-08-03T00:11:52.883081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.28640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f39ded3beb312d626feec89de0091b3df31b35479b73256f6f378b7b2855d33","sha256:5c037302ca7369b033cdeb37a237ea19d203d44d9aad5755361bdcd76d446f60"],"state_sha256":"61ee8de0041e3149079b7a420e4c38c654366ad1f404246bfc827a53611835d6"}