{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5LQ4XOHQLUXTP6LEBNXCNYU633","short_pith_number":"pith:5LQ4XOHQ","canonical_record":{"source":{"id":"2301.09626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T18:56:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41eea3c5fe4efc8131b69f9a17d9041cedf7a8714bc0ff8c24e0176ade7742c6","abstract_canon_sha256":"12dc8a38a9bf0640a6f769fe17de82d0b23141f79c1fd0dd384a01402c2a9d18"},"schema_version":"1.0"},"canonical_sha256":"eae1cbb8f05d2f37f9640b6e26e29edeea31758f391a7228f49166b4dcf197f2","source":{"kind":"arxiv","id":"2301.09626","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09626","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09626v1","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09626","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"5LQ4XOHQLUXT","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"pith_short_16","alias_value":"5LQ4XOHQLUXTP6LE","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"pith_short_8","alias_value":"5LQ4XOHQ","created_at":"2026-07-05T05:35:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5LQ4XOHQLUXTP6LEBNXCNYU633","target":"record","payload":{"canonical_record":{"source":{"id":"2301.09626","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T18:56:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41eea3c5fe4efc8131b69f9a17d9041cedf7a8714bc0ff8c24e0176ade7742c6","abstract_canon_sha256":"12dc8a38a9bf0640a6f769fe17de82d0b23141f79c1fd0dd384a01402c2a9d18"},"schema_version":"1.0"},"canonical_sha256":"eae1cbb8f05d2f37f9640b6e26e29edeea31758f391a7228f49166b4dcf197f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:02.609928Z","signature_b64":"9Z6Mc2k3ak55eswwkw7jTPluEDQhBiV94h5uAKokx7ZuJwDP9EmsjzGKlAmdfrrS79WQqIxpmej8vQbHMIznAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eae1cbb8f05d2f37f9640b6e26e29edeea31758f391a7228f49166b4dcf197f2","last_reissued_at":"2026-07-05T05:35:02.609431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:02.609431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.09626","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":"2026-07-05T05:35:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wT5zRxukb2JBvPvDeAjsmLCyjXh2dKSM6C9CdUonu6Fm0ckjwjGPRQOTR0w/JHolf1EVLb0cFI2HUfR2D2WfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:34:34.606778Z"},"content_sha256":"bb7b30ef063cfb6774ad7e17514cf89d1d0f561938478b0dd1c79bce04b780d9","schema_version":"1.0","event_id":"sha256:bb7b30ef063cfb6774ad7e17514cf89d1d0f561938478b0dd1c79bce04b780d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5LQ4XOHQLUXTP6LEBNXCNYU633","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Georg Rehm, Malte Ostendorff","submitted_at":"2023-01-23T18:56:12Z","abstract_excerpt":"Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources increases even further. Consequently, more resource-efficient training methods are needed to bridge the gap for languages with fewer resources available. To address this problem, we introduce a cross-lingual and progressive transfer learning approach, called CLP-Transfer, that transfers models from a source language, for which pretrained models are publicly availa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09626","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/2301.09626/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":"2026-07-05T05:35:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"heTwp5TrcSascEsQdN+vWjS/wZSdIqjDqyoeH+rid3a2pVTEiZpAArjqSf7LudUTU5Ghyt+lrptz3ARLBJulAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:34:34.607292Z"},"content_sha256":"81223079090e1ba1fcad0e72d8b117c4fc13e36664138c2b19bc08b04ef99ee2","schema_version":"1.0","event_id":"sha256:81223079090e1ba1fcad0e72d8b117c4fc13e36664138c2b19bc08b04ef99ee2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5LQ4XOHQLUXTP6LEBNXCNYU633/bundle.json","state_url":"https://pith.science/pith/5LQ4XOHQLUXTP6LEBNXCNYU633/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5LQ4XOHQLUXTP6LEBNXCNYU633/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":"2026-08-10T21:34:34Z","links":{"resolver":"https://pith.science/pith/5LQ4XOHQLUXTP6LEBNXCNYU633","bundle":"https://pith.science/pith/5LQ4XOHQLUXTP6LEBNXCNYU633/bundle.json","state":"https://pith.science/pith/5LQ4XOHQLUXTP6LEBNXCNYU633/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5LQ4XOHQLUXTP6LEBNXCNYU633/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5LQ4XOHQLUXTP6LEBNXCNYU633","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":"12dc8a38a9bf0640a6f769fe17de82d0b23141f79c1fd0dd384a01402c2a9d18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T18:56:12Z","title_canon_sha256":"41eea3c5fe4efc8131b69f9a17d9041cedf7a8714bc0ff8c24e0176ade7742c6"},"schema_version":"1.0","source":{"id":"2301.09626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09626","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09626v1","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09626","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"5LQ4XOHQLUXT","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"pith_short_16","alias_value":"5LQ4XOHQLUXTP6LE","created_at":"2026-07-05T05:35:02Z"},{"alias_kind":"pith_short_8","alias_value":"5LQ4XOHQ","created_at":"2026-07-05T05:35:02Z"}],"graph_snapshots":[{"event_id":"sha256:81223079090e1ba1fcad0e72d8b117c4fc13e36664138c2b19bc08b04ef99ee2","target":"graph","created_at":"2026-07-05T05:35:02Z","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/2301.09626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources increases even further. Consequently, more resource-efficient training methods are needed to bridge the gap for languages with fewer resources available. To address this problem, we introduce a cross-lingual and progressive transfer learning approach, called CLP-Transfer, that transfers models from a source language, for which pretrained models are publicly availa","authors_text":"Georg Rehm, Malte Ostendorff","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T18:56:12Z","title":"Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09626","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:bb7b30ef063cfb6774ad7e17514cf89d1d0f561938478b0dd1c79bce04b780d9","target":"record","created_at":"2026-07-05T05:35:02Z","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":"12dc8a38a9bf0640a6f769fe17de82d0b23141f79c1fd0dd384a01402c2a9d18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T18:56:12Z","title_canon_sha256":"41eea3c5fe4efc8131b69f9a17d9041cedf7a8714bc0ff8c24e0176ade7742c6"},"schema_version":"1.0","source":{"id":"2301.09626","kind":"arxiv","version":1}},"canonical_sha256":"eae1cbb8f05d2f37f9640b6e26e29edeea31758f391a7228f49166b4dcf197f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eae1cbb8f05d2f37f9640b6e26e29edeea31758f391a7228f49166b4dcf197f2","first_computed_at":"2026-07-05T05:35:02.609431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:35:02.609431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Z6Mc2k3ak55eswwkw7jTPluEDQhBiV94h5uAKokx7ZuJwDP9EmsjzGKlAmdfrrS79WQqIxpmej8vQbHMIznAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:35:02.609928Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.09626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb7b30ef063cfb6774ad7e17514cf89d1d0f561938478b0dd1c79bce04b780d9","sha256:81223079090e1ba1fcad0e72d8b117c4fc13e36664138c2b19bc08b04ef99ee2"],"state_sha256":"0a184f1fdb771b64ccf353fbc2f4c02179522ee4464504c1589d7c5bb92a5fe9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bcNMy2qMVgQXG8BZPYz6B0mvFpEk+uLB9SjQiqw5PNGH71IAYe7DoVxO3+AU1eNmArstHyxNmC+d7O5RkijmCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:34:34.612359Z","bundle_sha256":"1e173e78d2463cae55c5ab61fb9c2313f77a01d7175e923e9357b10cf39a7217"}}