{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UQW6Q5KOWC7KSD7VPJVVIO72D4","short_pith_number":"pith:UQW6Q5KO","canonical_record":{"source":{"id":"2307.06018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-12T09:00:37Z","cross_cats_sorted":[],"title_canon_sha256":"ab12f3e0fee24341b892b87c64a7ad73eb4e5233b0808a21b819fa3b6ca1acb3","abstract_canon_sha256":"dc653a9ae580b180677e3b85281f39ad94ce4e5defdb366bc0874bf2ac647d43"},"schema_version":"1.0"},"canonical_sha256":"a42de8754eb0bea90ff57a6b543bfa1f0476acf38c5fcad2658cee9b4beed660","source":{"kind":"arxiv","id":"2307.06018","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06018","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06018v1","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06018","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"UQW6Q5KOWC7K","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"UQW6Q5KOWC7KSD7V","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"UQW6Q5KO","created_at":"2026-07-05T06:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UQW6Q5KOWC7KSD7VPJVVIO72D4","target":"record","payload":{"canonical_record":{"source":{"id":"2307.06018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-12T09:00:37Z","cross_cats_sorted":[],"title_canon_sha256":"ab12f3e0fee24341b892b87c64a7ad73eb4e5233b0808a21b819fa3b6ca1acb3","abstract_canon_sha256":"dc653a9ae580b180677e3b85281f39ad94ce4e5defdb366bc0874bf2ac647d43"},"schema_version":"1.0"},"canonical_sha256":"a42de8754eb0bea90ff57a6b543bfa1f0476acf38c5fcad2658cee9b4beed660","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:15.539264Z","signature_b64":"JlrWX+lV9mew3dC8vDVxnSXKGp+Ah19A0YmJsAt3YMXNkDptRN7BucXdkKYC34vZLMWFWzReSTQivLW2r49vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a42de8754eb0bea90ff57a6b543bfa1f0476acf38c5fcad2658cee9b4beed660","last_reissued_at":"2026-07-05T06:30:15.538704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:15.538704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.06018","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":"2026-07-05T06:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beH6lqZKbrcoBT0HXKvwUxifA/oaqLh0dfltYijSyo/84cWcPcjfIM9g3vpI+mggEy3ry6jStpOE2EiZTpP7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:17:25.085832Z"},"content_sha256":"3cfb6706ab1a2f38a5384ef5292d1e48100830ae2b4b802373d6e8eb3be0c99a","schema_version":"1.0","event_id":"sha256:3cfb6706ab1a2f38a5384ef5292d1e48100830ae2b4b802373d6e8eb3be0c99a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UQW6Q5KOWC7KSD7VPJVVIO72D4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PolyLM: An Open Source Polyglot Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baosong Yang, Binbin Xie, Binyuan Hui, Bowen Yu, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jun Xie, Mei Li, Pei Zhang, Shangjie Li, Tianhao Li, Tianxiang Hu, Xiangpeng Wei, Xingzhang Ren, Yu Wan, Zhiwei Cao","submitted_at":"2023-07-12T09:00:37Z","abstract_excerpt":"Large language models (LLMs) demonstrate remarkable ability to comprehend, reason, and generate following nature language instructions. However, the development of LLMs has been primarily focused on high-resource languages, such as English, thereby limiting their applicability and research in other languages. Consequently, we present PolyLM, a multilingual LLM trained on 640 billion (B) tokens, avaliable in two model sizes: 1.7B and 13B. To enhance its multilingual capabilities, we 1) integrate bilingual data into training data; and 2) adopt a curriculum learning strategy that increases the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06018","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/2307.06018/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":"2026-07-05T06:30:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0V0QSby/qYKlDlIai7DJGur2NFnlM1gDVJGZODZZU2q8Nvg2gNb3zYrEcor/VA2onmbZ75gPFP9I9i16QlP6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:17:25.086353Z"},"content_sha256":"dfa7cd77b0809f16d44ce1fd87004445ad313716e756d478c3b8a3a50a435625","schema_version":"1.0","event_id":"sha256:dfa7cd77b0809f16d44ce1fd87004445ad313716e756d478c3b8a3a50a435625"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQW6Q5KOWC7KSD7VPJVVIO72D4/bundle.json","state_url":"https://pith.science/pith/UQW6Q5KOWC7KSD7VPJVVIO72D4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQW6Q5KOWC7KSD7VPJVVIO72D4/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":"2026-08-07T11:17:25Z","links":{"resolver":"https://pith.science/pith/UQW6Q5KOWC7KSD7VPJVVIO72D4","bundle":"https://pith.science/pith/UQW6Q5KOWC7KSD7VPJVVIO72D4/bundle.json","state":"https://pith.science/pith/UQW6Q5KOWC7KSD7VPJVVIO72D4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQW6Q5KOWC7KSD7VPJVVIO72D4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UQW6Q5KOWC7KSD7VPJVVIO72D4","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":"dc653a9ae580b180677e3b85281f39ad94ce4e5defdb366bc0874bf2ac647d43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-12T09:00:37Z","title_canon_sha256":"ab12f3e0fee24341b892b87c64a7ad73eb4e5233b0808a21b819fa3b6ca1acb3"},"schema_version":"1.0","source":{"id":"2307.06018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06018","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06018v1","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06018","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_12","alias_value":"UQW6Q5KOWC7K","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"UQW6Q5KOWC7KSD7V","created_at":"2026-07-05T06:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"UQW6Q5KO","created_at":"2026-07-05T06:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:dfa7cd77b0809f16d44ce1fd87004445ad313716e756d478c3b8a3a50a435625","target":"graph","created_at":"2026-07-05T06:30:15Z","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/2307.06018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) demonstrate remarkable ability to comprehend, reason, and generate following nature language instructions. However, the development of LLMs has been primarily focused on high-resource languages, such as English, thereby limiting their applicability and research in other languages. Consequently, we present PolyLM, a multilingual LLM trained on 640 billion (B) tokens, avaliable in two model sizes: 1.7B and 13B. To enhance its multilingual capabilities, we 1) integrate bilingual data into training data; and 2) adopt a curriculum learning strategy that increases the pr","authors_text":"Baosong Yang, Binbin Xie, Binyuan Hui, Bowen Yu, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jun Xie, Mei Li, Pei Zhang, Shangjie Li, Tianhao Li, Tianxiang Hu, Xiangpeng Wei, Xingzhang Ren, Yu Wan, Zhiwei Cao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-12T09:00:37Z","title":"PolyLM: An Open Source Polyglot Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06018","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":"sha256:3cfb6706ab1a2f38a5384ef5292d1e48100830ae2b4b802373d6e8eb3be0c99a","target":"record","created_at":"2026-07-05T06:30:15Z","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":"dc653a9ae580b180677e3b85281f39ad94ce4e5defdb366bc0874bf2ac647d43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-12T09:00:37Z","title_canon_sha256":"ab12f3e0fee24341b892b87c64a7ad73eb4e5233b0808a21b819fa3b6ca1acb3"},"schema_version":"1.0","source":{"id":"2307.06018","kind":"arxiv","version":1}},"canonical_sha256":"a42de8754eb0bea90ff57a6b543bfa1f0476acf38c5fcad2658cee9b4beed660","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a42de8754eb0bea90ff57a6b543bfa1f0476acf38c5fcad2658cee9b4beed660","first_computed_at":"2026-07-05T06:30:15.538704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:15.538704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JlrWX+lV9mew3dC8vDVxnSXKGp+Ah19A0YmJsAt3YMXNkDptRN7BucXdkKYC34vZLMWFWzReSTQivLW2r49vDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:15.539264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cfb6706ab1a2f38a5384ef5292d1e48100830ae2b4b802373d6e8eb3be0c99a","sha256:dfa7cd77b0809f16d44ce1fd87004445ad313716e756d478c3b8a3a50a435625"],"state_sha256":"07c65dcdfcc97f3009952eb2f3e3451b119d70824f1417162951f8f66736b563"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mB5SwgYfaxJMupRBCEq02ky13AdHKCDTS+WPtv5RsyuaY7hU+x58E38wWCaTIxOTuxV/Zd171vwOmEkpd7a8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T11:17:25.090458Z","bundle_sha256":"5f7e731768c1833ce384484d9126130e67ad754efc3b40e591c39ed3d495b6e4"}}