{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UT35UZFUVKPUJ2JT5A5KC3CM6D","short_pith_number":"pith:UT35UZFU","canonical_record":{"source":{"id":"2507.18791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T20:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"bb9be00e620ce29dc3a6182ed20117522b55e3b596ebf197020be8ae04295b75","abstract_canon_sha256":"c33722aa8115e01850dc62926165b166216f22c99028bae3f179ebbbe648c3a9"},"schema_version":"1.0"},"canonical_sha256":"a4f7da64b4aa9f44e933e83aa16c4cf0c4fad29b7a2dcc3b395dd86b9d38a263","source":{"kind":"arxiv","id":"2507.18791","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18791","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18791v2","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18791","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"UT35UZFUVKPU","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"UT35UZFUVKPUJ2JT","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"UT35UZFU","created_at":"2026-07-05T12:06:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UT35UZFUVKPUJ2JT5A5KC3CM6D","target":"record","payload":{"canonical_record":{"source":{"id":"2507.18791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T20:24:33Z","cross_cats_sorted":[],"title_canon_sha256":"bb9be00e620ce29dc3a6182ed20117522b55e3b596ebf197020be8ae04295b75","abstract_canon_sha256":"c33722aa8115e01850dc62926165b166216f22c99028bae3f179ebbbe648c3a9"},"schema_version":"1.0"},"canonical_sha256":"a4f7da64b4aa9f44e933e83aa16c4cf0c4fad29b7a2dcc3b395dd86b9d38a263","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:16.702835Z","signature_b64":"21gKR61+4UEoedSdPa/FHndPoZAp18OfJLgSzAIrQLMOtgR2uuTyZgEiztrNXUPYnCj8CaDj2d6CcG/Ik+wiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4f7da64b4aa9f44e933e83aa16c4cf0c4fad29b7a2dcc3b395dd86b9d38a263","last_reissued_at":"2026-07-05T12:06:16.702342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:16.702342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.18791","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T4O0I/4ESyOyiZULBxlCB0QhBAlHqwa2Y6j4bhpXBDv3DoQlKrubvw/6eySfxNLuko+SvDRjybs9SzqIO/CqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:42:44.169353Z"},"content_sha256":"999ffe3f0ce5cee8e80276868a74c88b53320e2f4a62ec2d3735b543ad5bdb2d","schema_version":"1.0","event_id":"sha256:999ffe3f0ce5cee8e80276868a74c88b53320e2f4a62ec2d3735b543ad5bdb2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UT35UZFUVKPUJ2JT5A5KC3CM6D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yekun Chai, Yilun Yang","submitted_at":"2025-07-24T20:24:33Z","abstract_excerpt":"Code-mixing, the practice of switching between languages within a conversation, poses unique challenges for traditional NLP. Existing benchmarks are limited by their narrow language pairs and tasks, failing to adequately assess large language models' (LLMs) code-mixing abilities. Despite the recognized importance of code-mixing for multilingual users, research on LLMs in this context remains sparse. Additionally, current techniques for synthesizing code-mixed data are underdeveloped to generate code-mixing. In response, we introduce CodeMixBench, a comprehensive benchmark covering eight tasks,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18791","kind":"arxiv","version":2},"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/2507.18791/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":"2026-07-05T12:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ueJNjGf+WUyhF0EYY3KxKy+eNg9oU3AkaY/WM/e4rbJNU0AF6aAmysr3gzzY+UIGUXSNmu+Iqy9ZmMG/ZxU1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:42:44.169731Z"},"content_sha256":"d19a3a49c81085db3942f8ff3c8f03d6ef6a2058ceb4f83e1caa7b8c62f565f7","schema_version":"1.0","event_id":"sha256:d19a3a49c81085db3942f8ff3c8f03d6ef6a2058ceb4f83e1caa7b8c62f565f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UT35UZFUVKPUJ2JT5A5KC3CM6D/bundle.json","state_url":"https://pith.science/pith/UT35UZFUVKPUJ2JT5A5KC3CM6D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UT35UZFUVKPUJ2JT5A5KC3CM6D/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":"2026-07-07T09:42:44Z","links":{"resolver":"https://pith.science/pith/UT35UZFUVKPUJ2JT5A5KC3CM6D","bundle":"https://pith.science/pith/UT35UZFUVKPUJ2JT5A5KC3CM6D/bundle.json","state":"https://pith.science/pith/UT35UZFUVKPUJ2JT5A5KC3CM6D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UT35UZFUVKPUJ2JT5A5KC3CM6D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UT35UZFUVKPUJ2JT5A5KC3CM6D","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":"c33722aa8115e01850dc62926165b166216f22c99028bae3f179ebbbe648c3a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T20:24:33Z","title_canon_sha256":"bb9be00e620ce29dc3a6182ed20117522b55e3b596ebf197020be8ae04295b75"},"schema_version":"1.0","source":{"id":"2507.18791","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18791","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18791v2","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18791","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"UT35UZFUVKPU","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"UT35UZFUVKPUJ2JT","created_at":"2026-07-05T12:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"UT35UZFU","created_at":"2026-07-05T12:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:d19a3a49c81085db3942f8ff3c8f03d6ef6a2058ceb4f83e1caa7b8c62f565f7","target":"graph","created_at":"2026-07-05T12:06:16Z","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/2507.18791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-mixing, the practice of switching between languages within a conversation, poses unique challenges for traditional NLP. Existing benchmarks are limited by their narrow language pairs and tasks, failing to adequately assess large language models' (LLMs) code-mixing abilities. Despite the recognized importance of code-mixing for multilingual users, research on LLMs in this context remains sparse. Additionally, current techniques for synthesizing code-mixed data are underdeveloped to generate code-mixing. In response, we introduce CodeMixBench, a comprehensive benchmark covering eight tasks,","authors_text":"Yekun Chai, Yilun Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T20:24:33Z","title":"CodeMixBench: Evaluating Code-Mixing Capabilities of LLMs Across 18 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18791","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":"sha256:999ffe3f0ce5cee8e80276868a74c88b53320e2f4a62ec2d3735b543ad5bdb2d","target":"record","created_at":"2026-07-05T12:06:16Z","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":"c33722aa8115e01850dc62926165b166216f22c99028bae3f179ebbbe648c3a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T20:24:33Z","title_canon_sha256":"bb9be00e620ce29dc3a6182ed20117522b55e3b596ebf197020be8ae04295b75"},"schema_version":"1.0","source":{"id":"2507.18791","kind":"arxiv","version":2}},"canonical_sha256":"a4f7da64b4aa9f44e933e83aa16c4cf0c4fad29b7a2dcc3b395dd86b9d38a263","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4f7da64b4aa9f44e933e83aa16c4cf0c4fad29b7a2dcc3b395dd86b9d38a263","first_computed_at":"2026-07-05T12:06:16.702342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:16.702342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"21gKR61+4UEoedSdPa/FHndPoZAp18OfJLgSzAIrQLMOtgR2uuTyZgEiztrNXUPYnCj8CaDj2d6CcG/Ik+wiAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:16.702835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18791","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:999ffe3f0ce5cee8e80276868a74c88b53320e2f4a62ec2d3735b543ad5bdb2d","sha256:d19a3a49c81085db3942f8ff3c8f03d6ef6a2058ceb4f83e1caa7b8c62f565f7"],"state_sha256":"a59c3c0410af656d8d5c48bd65b060e9967128c9c98887a93d1a24f253fa82f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8uHFuF9mqH2UNf2YR8XOtbhjLtmisFfs0ueXwBJWzAEXfGeU1dy0Xg55MjixOiL3CP9imj9xDbmzBeoOcwoIDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:42:44.171719Z","bundle_sha256":"60469aef3ab1247c138674ab835d6015695cd709d5b7b2ca4fc3108163dfe41b"}}