{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HXMSTDT75FZM4VLXRJO7YZTEAH","short_pith_number":"pith:HXMSTDT7","canonical_record":{"source":{"id":"2607.28640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T00:25:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"36564daa8fd7c2252b55fca36aa59a8b9a7e0f16fade69534973db7d3d6a63b4","abstract_canon_sha256":"cfc00a069f1c503882c263f3d3d489a94f3db5df9f5f67e8158200df12cfdee1"},"schema_version":"1.0"},"canonical_sha256":"3dd9298e7fe972ce55778a5dfc666401f467befb016892f44b646681bd966b10","source":{"kind":"arxiv","id":"2607.28640","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HXMSTDT75FZM4VLXRJO7YZTEAH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T00:25:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"36564daa8fd7c2252b55fca36aa59a8b9a7e0f16fade69534973db7d3d6a63b4","abstract_canon_sha256":"cfc00a069f1c503882c263f3d3d489a94f3db5df9f5f67e8158200df12cfdee1"},"schema_version":"1.0"},"canonical_sha256":"3dd9298e7fe972ce55778a5dfc666401f467befb016892f44b646681bd966b10","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T00:11:52.883081Z","signature_b64":"4pPwlq2rErvLiUNrfNpCo166T+8/9miCTo1iuOMhLABHkAIqZkTWZtFCbmVeM1VtaHXDer818tVuhMH/Cws5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dd9298e7fe972ce55778a5dfc666401f467befb016892f44b646681bd966b10","last_reissued_at":"2026-08-03T00:11:52.880902Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T00:11:52.880902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.28640","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":"2026-08-03T00:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yJIP7wG8eW1OZI3nOFwOJ8HwCvnDFNnJuYqa89ByYMJZiQj90k/Ly4pbRc+MTYxBIZDWNq+3dzgbjbcI82pMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:34:18.088685Z"},"content_sha256":"7f39ded3beb312d626feec89de0091b3df31b35479b73256f6f378b7b2855d33","schema_version":"1.0","event_id":"sha256:7f39ded3beb312d626feec89de0091b3df31b35479b73256f6f378b7b2855d33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HXMSTDT75FZM4VLXRJO7YZTEAH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Aleksandra Faust, Andong Hua, Arian Hosseini, Colton Bishop, Igor Mordatch, Jindong Gu, Rebecca Roelofs, Yao Qin","submitted_at":"2026-05-20T00:25:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28640","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/2607.28640/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":"2026-08-03T00:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ts2FfWu+5aFPlZ0hhEJeP/SuqLfC5snVOulZN/Df99Q9z2I8BKJ/bkSyfPjTGk3afKZKX97r/bkxRSrIXtyiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:34:18.089188Z"},"content_sha256":"5c037302ca7369b033cdeb37a237ea19d203d44d9aad5755361bdcd76d446f60","schema_version":"1.0","event_id":"sha256:5c037302ca7369b033cdeb37a237ea19d203d44d9aad5755361bdcd76d446f60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXMSTDT75FZM4VLXRJO7YZTEAH/bundle.json","state_url":"https://pith.science/pith/HXMSTDT75FZM4VLXRJO7YZTEAH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXMSTDT75FZM4VLXRJO7YZTEAH/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":"2026-08-06T09:34:18Z","links":{"resolver":"https://pith.science/pith/HXMSTDT75FZM4VLXRJO7YZTEAH","bundle":"https://pith.science/pith/HXMSTDT75FZM4VLXRJO7YZTEAH/bundle.json","state":"https://pith.science/pith/HXMSTDT75FZM4VLXRJO7YZTEAH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXMSTDT75FZM4VLXRJO7YZTEAH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3VkkLHHfkwY17+6zeUjm4UjCEmOBCzUOVo9sfg2Xd02NJW3mbNewaXXIXXhoSdgqVUzEkBd7Pxpn5B+I84HCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:34:18.093310Z","bundle_sha256":"25bae4bd904b7b66aea707f6dc59daa9ad9c197d292f235d6beecc368e3cb8ff"}}