{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T5QJFT6E65H3I7WM3R6E3PKMWO","short_pith_number":"pith:T5QJFT6E","canonical_record":{"source":{"id":"2608.11167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T17:28:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5ad4e158670645044e1e9ed4921a4ec67e9cc5893f4a55bedb662bceb61040db","abstract_canon_sha256":"b13f58ce07d7c8f6e72ae1738699c1efd7131cac79aba022bc9b9e9010b377f4"},"schema_version":"1.0"},"canonical_sha256":"9f6092cfc4f74fb47eccdc7c4dbd4cb3b06b6b4b89a7f88b4904066e0196263c","source":{"kind":"arxiv","id":"2608.11167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11167","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11167v1","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11167","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"pith_short_12","alias_value":"T5QJFT6E65H3","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"pith_short_16","alias_value":"T5QJFT6E65H3I7WM","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"pith_short_8","alias_value":"T5QJFT6E","created_at":"2026-08-12T01:24:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T5QJFT6E65H3I7WM3R6E3PKMWO","target":"record","payload":{"canonical_record":{"source":{"id":"2608.11167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T17:28:52Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5ad4e158670645044e1e9ed4921a4ec67e9cc5893f4a55bedb662bceb61040db","abstract_canon_sha256":"b13f58ce07d7c8f6e72ae1738699c1efd7131cac79aba022bc9b9e9010b377f4"},"schema_version":"1.0"},"canonical_sha256":"9f6092cfc4f74fb47eccdc7c4dbd4cb3b06b6b4b89a7f88b4904066e0196263c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:24:44.378518Z","signature_b64":"T6WE5udxdBuKTx6AX4Bg/esCJEZnmKcBpXlXs2aAWUrWki6WmwLci8M84WCm0gyn1/hLmiMtQk/FXvVaG+ToCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f6092cfc4f74fb47eccdc7c4dbd4cb3b06b6b4b89a7f88b4904066e0196263c","last_reissued_at":"2026-08-12T01:24:44.376620Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:24:44.376620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.11167","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":"2026-08-12T01:24:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"35od1l2xdyv5FderrIs/owrMEwYSL/t0Rbn1+V+7XctzkYu0RFJVnVSY/zGVx0784wAj5EHtdcuAfWUJix26AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:56:52.357707Z"},"content_sha256":"0ef6afc83064b940672c4801f29a74fb609751a34da2a32a6ac46fcfd59f1269","schema_version":"1.0","event_id":"sha256:0ef6afc83064b940672c4801f29a74fb609751a34da2a32a6ac46fcfd59f1269"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T5QJFT6E65H3I7WM3R6E3PKMWO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Changhao Xiang, Jianbing Zhang, Shangyu Xing, Xinyu Dai, Zhen Wu","submitted_at":"2026-08-11T17:28:52Z","abstract_excerpt":"Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual descriptions. However, this image-level alignment suffers from referential ambiguity: models struggle to infer the correspondences between multiple visual objects and textual entities from the global representation, leading to data inefficiency and suboptimal semantic grounding. To address this, we propose MultiModal Code-Switching (MMCS), a novel pretraining paradigm that provides explicit object-level supervision. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11167","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/2608.11167/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":"2026-08-12T01:24:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ixrLJvDEktkaxdLb7UgeOXSW/qhzDTgyiYdAh5UkSjKa2miZyd23A4w/OPWUMLv3NCMMojPX6CtMurwqfRV7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:56:52.358221Z"},"content_sha256":"9f8b8a84e0f2958f192eae7d3b0bf2f302fb442663c7fd16c0286dc24af664e2","schema_version":"1.0","event_id":"sha256:9f8b8a84e0f2958f192eae7d3b0bf2f302fb442663c7fd16c0286dc24af664e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T5QJFT6E65H3I7WM3R6E3PKMWO/bundle.json","state_url":"https://pith.science/pith/T5QJFT6E65H3I7WM3R6E3PKMWO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T5QJFT6E65H3I7WM3R6E3PKMWO/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":"2026-08-14T21:56:52Z","links":{"resolver":"https://pith.science/pith/T5QJFT6E65H3I7WM3R6E3PKMWO","bundle":"https://pith.science/pith/T5QJFT6E65H3I7WM3R6E3PKMWO/bundle.json","state":"https://pith.science/pith/T5QJFT6E65H3I7WM3R6E3PKMWO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T5QJFT6E65H3I7WM3R6E3PKMWO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T5QJFT6E65H3I7WM3R6E3PKMWO","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":"b13f58ce07d7c8f6e72ae1738699c1efd7131cac79aba022bc9b9e9010b377f4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T17:28:52Z","title_canon_sha256":"5ad4e158670645044e1e9ed4921a4ec67e9cc5893f4a55bedb662bceb61040db"},"schema_version":"1.0","source":{"id":"2608.11167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11167","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11167v1","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11167","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"pith_short_12","alias_value":"T5QJFT6E65H3","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"pith_short_16","alias_value":"T5QJFT6E65H3I7WM","created_at":"2026-08-12T01:24:44Z"},{"alias_kind":"pith_short_8","alias_value":"T5QJFT6E","created_at":"2026-08-12T01:24:44Z"}],"graph_snapshots":[{"event_id":"sha256:9f8b8a84e0f2958f192eae7d3b0bf2f302fb442663c7fd16c0286dc24af664e2","target":"graph","created_at":"2026-08-12T01:24:44Z","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/2608.11167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long textual descriptions. However, this image-level alignment suffers from referential ambiguity: models struggle to infer the correspondences between multiple visual objects and textual entities from the global representation, leading to data inefficiency and suboptimal semantic grounding. To address this, we propose MultiModal Code-Switching (MMCS), a novel pretraining paradigm that provides explicit object-level supervision. In","authors_text":"Changhao Xiang, Jianbing Zhang, Shangyu Xing, Xinyu Dai, Zhen Wu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T17:28:52Z","title":"MultiModal Code-Switching: Interleaving Visual Objects into Language for Explicit Object-Level Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11167","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":"sha256:0ef6afc83064b940672c4801f29a74fb609751a34da2a32a6ac46fcfd59f1269","target":"record","created_at":"2026-08-12T01:24:44Z","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":"b13f58ce07d7c8f6e72ae1738699c1efd7131cac79aba022bc9b9e9010b377f4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T17:28:52Z","title_canon_sha256":"5ad4e158670645044e1e9ed4921a4ec67e9cc5893f4a55bedb662bceb61040db"},"schema_version":"1.0","source":{"id":"2608.11167","kind":"arxiv","version":1}},"canonical_sha256":"9f6092cfc4f74fb47eccdc7c4dbd4cb3b06b6b4b89a7f88b4904066e0196263c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f6092cfc4f74fb47eccdc7c4dbd4cb3b06b6b4b89a7f88b4904066e0196263c","first_computed_at":"2026-08-12T01:24:44.376620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:24:44.376620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T6WE5udxdBuKTx6AX4Bg/esCJEZnmKcBpXlXs2aAWUrWki6WmwLci8M84WCm0gyn1/hLmiMtQk/FXvVaG+ToCw==","signature_status":"signed_v1","signed_at":"2026-08-12T01:24:44.378518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ef6afc83064b940672c4801f29a74fb609751a34da2a32a6ac46fcfd59f1269","sha256:9f8b8a84e0f2958f192eae7d3b0bf2f302fb442663c7fd16c0286dc24af664e2"],"state_sha256":"53ff19d263abad81331d04e1fc108648984dc44eb18da7cfb7a6cc03f94e49e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z1ApFe0VKmDdBIlBeReICnFoySy8DZhJ5TfTGtPtxQt+Ce3s2dZgyn/yvf06587ssbgtkCb3UZRylHl0u7JbBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T21:56:52.363593Z","bundle_sha256":"6899503b7246a65c81a0c3140db01376c9c21a90751010b7d79574a57221080a"}}