{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K4AA6FHMXXVBRFCHX6FBUSIKFA","short_pith_number":"pith:K4AA6FHM","canonical_record":{"source":{"id":"2506.13044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T02:21:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78d680478c7cafa016a6b4ce7d92d83396602fb44c8067636f4c5d79c6ba2551","abstract_canon_sha256":"21e77511570e9cd3e6f19fd7450cc28b11f4159ddb04be4ceb9534fa22f1e50c"},"schema_version":"1.0"},"canonical_sha256":"57000f14ecbdea189447bf8a1a490a283d0beb6e174334f77f53725e473bae4a","source":{"kind":"arxiv","id":"2506.13044","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13044","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13044v1","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13044","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"K4AA6FHMXXVB","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"K4AA6FHMXXVBRFCH","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"K4AA6FHM","created_at":"2026-07-05T11:22:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K4AA6FHMXXVBRFCHX6FBUSIKFA","target":"record","payload":{"canonical_record":{"source":{"id":"2506.13044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T02:21:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78d680478c7cafa016a6b4ce7d92d83396602fb44c8067636f4c5d79c6ba2551","abstract_canon_sha256":"21e77511570e9cd3e6f19fd7450cc28b11f4159ddb04be4ceb9534fa22f1e50c"},"schema_version":"1.0"},"canonical_sha256":"57000f14ecbdea189447bf8a1a490a283d0beb6e174334f77f53725e473bae4a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:04.262448Z","signature_b64":"S7SFaHaJ9Yue4LP5Y64I+/IV+khtLpH08kpZpCAVAkQVklFiWSocJfW3jNNo30ZIpZjwN2piCi/616wHUuZQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57000f14ecbdea189447bf8a1a490a283d0beb6e174334f77f53725e473bae4a","last_reissued_at":"2026-07-05T11:22:04.261959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:04.261959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.13044","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":"2026-07-05T11:22:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lfn1mgVL2yeT89J1aicHVL3yeI5kgUbjpFM9WBO8u8RNm0XdSJo2szkG33ToOny6XAhWTYiHpVRFEsk5JH0OCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:38:43.443161Z"},"content_sha256":"7cc97e46cd7982924097c635493692346f642779ea7895fa11184bed791cae32","schema_version":"1.0","event_id":"sha256:7cc97e46cd7982924097c635493692346f642779ea7895fa11184bed791cae32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K4AA6FHMXXVBRFCHX6FBUSIKFA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hwee Tou Ng, Junyi Li, Muhammad Reza Qorib","submitted_at":"2025-06-16T02:21:15Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive translation capabilities even without being explicitly trained on parallel data. This remarkable property has led some to believe that parallel data is no longer necessary for building multilingual language models. While some attribute this to the emergent abilities of LLMs due to scale, recent work suggests that it is actually caused by incidental bilingual signals present in the training data. Various methods have been proposed to maximize the utility of parallel data to enhance the multilingual capabilities of multilingual encoder-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13044","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/2506.13044/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":"2026-07-05T11:22:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"53hd4G5nXgGatNJ81u5TY44xcZ5xD/s/UgUXuPBnVDySPyHS224buR7Pwb/yddylpqZb63tUtnqBTqlUrocoCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:38:43.443879Z"},"content_sha256":"1b56571abca7b07914454aa8a8d20d736e9129ce177006d8754732030a41c287","schema_version":"1.0","event_id":"sha256:1b56571abca7b07914454aa8a8d20d736e9129ce177006d8754732030a41c287"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4AA6FHMXXVBRFCHX6FBUSIKFA/bundle.json","state_url":"https://pith.science/pith/K4AA6FHMXXVBRFCHX6FBUSIKFA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4AA6FHMXXVBRFCHX6FBUSIKFA/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":"2026-08-18T11:38:43Z","links":{"resolver":"https://pith.science/pith/K4AA6FHMXXVBRFCHX6FBUSIKFA","bundle":"https://pith.science/pith/K4AA6FHMXXVBRFCHX6FBUSIKFA/bundle.json","state":"https://pith.science/pith/K4AA6FHMXXVBRFCHX6FBUSIKFA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4AA6FHMXXVBRFCHX6FBUSIKFA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K4AA6FHMXXVBRFCHX6FBUSIKFA","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":"21e77511570e9cd3e6f19fd7450cc28b11f4159ddb04be4ceb9534fa22f1e50c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T02:21:15Z","title_canon_sha256":"78d680478c7cafa016a6b4ce7d92d83396602fb44c8067636f4c5d79c6ba2551"},"schema_version":"1.0","source":{"id":"2506.13044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13044","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13044v1","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13044","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"pith_short_12","alias_value":"K4AA6FHMXXVB","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"pith_short_16","alias_value":"K4AA6FHMXXVBRFCH","created_at":"2026-07-05T11:22:04Z"},{"alias_kind":"pith_short_8","alias_value":"K4AA6FHM","created_at":"2026-07-05T11:22:04Z"}],"graph_snapshots":[{"event_id":"sha256:1b56571abca7b07914454aa8a8d20d736e9129ce177006d8754732030a41c287","target":"graph","created_at":"2026-07-05T11:22:04Z","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/2506.13044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated impressive translation capabilities even without being explicitly trained on parallel data. This remarkable property has led some to believe that parallel data is no longer necessary for building multilingual language models. While some attribute this to the emergent abilities of LLMs due to scale, recent work suggests that it is actually caused by incidental bilingual signals present in the training data. Various methods have been proposed to maximize the utility of parallel data to enhance the multilingual capabilities of multilingual encoder-ba","authors_text":"Hwee Tou Ng, Junyi Li, Muhammad Reza Qorib","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T02:21:15Z","title":"Just Go Parallel: Improving the Multilingual Capabilities of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13044","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":"sha256:7cc97e46cd7982924097c635493692346f642779ea7895fa11184bed791cae32","target":"record","created_at":"2026-07-05T11:22:04Z","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":"21e77511570e9cd3e6f19fd7450cc28b11f4159ddb04be4ceb9534fa22f1e50c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T02:21:15Z","title_canon_sha256":"78d680478c7cafa016a6b4ce7d92d83396602fb44c8067636f4c5d79c6ba2551"},"schema_version":"1.0","source":{"id":"2506.13044","kind":"arxiv","version":1}},"canonical_sha256":"57000f14ecbdea189447bf8a1a490a283d0beb6e174334f77f53725e473bae4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57000f14ecbdea189447bf8a1a490a283d0beb6e174334f77f53725e473bae4a","first_computed_at":"2026-07-05T11:22:04.261959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:04.261959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S7SFaHaJ9Yue4LP5Y64I+/IV+khtLpH08kpZpCAVAkQVklFiWSocJfW3jNNo30ZIpZjwN2piCi/616wHUuZQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:04.262448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cc97e46cd7982924097c635493692346f642779ea7895fa11184bed791cae32","sha256:1b56571abca7b07914454aa8a8d20d736e9129ce177006d8754732030a41c287"],"state_sha256":"c28a29a7def6eb6d4079d9308a97f045ee8dfadadd85435d67d2f861c00c4560"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EPM0lxrcXZK97U3WZesjrERRhKSID/IJ9Q2il0OwH6ONBkygWoDXTMx3BZtGFDBBQ1HMuYTh8/swGMIg4PWrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:38:43.449622Z","bundle_sha256":"ca5d2d9738a2adebe3b9fd6b94dc4d4ead50949dcea2e114606cc9c508d3f1d1"}}