{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6S3OIHA3FBDPGB2Z6GT2ZB7RBU","short_pith_number":"pith:6S3OIHA3","canonical_record":{"source":{"id":"2404.01856","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:34:12Z","cross_cats_sorted":[],"title_canon_sha256":"f0993df15c7c5ef1808c8d1f8f13f166e79e9d0b0e422ef083d34caeed1a4d7b","abstract_canon_sha256":"fd5568393f132d7c687bf4204e7e008ae16c817b2bb21abc4ff8282f12e36291"},"schema_version":"1.0"},"canonical_sha256":"f4b6e41c1b2846f30759f1a7ac87f10d0569faca748490d5fccb068de64a377d","source":{"kind":"arxiv","id":"2404.01856","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01856","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01856v3","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01856","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"6S3OIHA3FBDP","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_16","alias_value":"6S3OIHA3FBDPGB2Z","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_8","alias_value":"6S3OIHA3","created_at":"2026-07-05T11:18:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6S3OIHA3FBDPGB2Z6GT2ZB7RBU","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01856","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:34:12Z","cross_cats_sorted":[],"title_canon_sha256":"f0993df15c7c5ef1808c8d1f8f13f166e79e9d0b0e422ef083d34caeed1a4d7b","abstract_canon_sha256":"fd5568393f132d7c687bf4204e7e008ae16c817b2bb21abc4ff8282f12e36291"},"schema_version":"1.0"},"canonical_sha256":"f4b6e41c1b2846f30759f1a7ac87f10d0569faca748490d5fccb068de64a377d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:57.984267Z","signature_b64":"xO7zTc/1v1n81un1FPm4dZpOaynjKMSJOmZWzyDX/j1LCO8swMILTtIsgi1JNSBe0txEFqmr4xAWv9OaQHgFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b6e41c1b2846f30759f1a7ac87f10d0569faca748490d5fccb068de64a377d","last_reissued_at":"2026-07-05T11:18:57.983769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:57.983769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01856","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c3nzY5XyD64PtytarCbmzoHQrz6RAtVAqu+f4vv+2sgdsixT3jk491eYeNCaAOpQajajArq2kb4xmOl9i5uSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:00:15.925514Z"},"content_sha256":"085aadcf6c8f206c3e71a6eeafd23cffc0503d1616dc64a3236c42ad473f7d94","schema_version":"1.0","event_id":"sha256:085aadcf6c8f206c3e71a6eeafd23cffc0503d1616dc64a3236c42ad473f7d94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6S3OIHA3FBDPGB2Z6GT2ZB7RBU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Poro 34B and the Blessing of Multilinguality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aarne Talman, Elaine Zosa, Jonathan Burdge, Peter Sarlin, Risto Luukkonen, Sampo Pyysalo, V\\\"ain\\\"o Hatanp\\\"a\\\"a, Ville Komulainen","submitted_at":"2024-04-02T11:34:12Z","abstract_excerpt":"The pretraining of state-of-the-art large language models now requires trillions of words of text, which is orders of magnitude more than available for the vast majority of languages. While including text in more than one language is an obvious way to acquire more pretraining data, multilinguality is often seen as a curse, and most model training efforts continue to focus near-exclusively on individual large languages. We believe that multilinguality can be a blessing: when the lack of training data is a constraint for effectively training larger models for a target language, augmenting the da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01856","kind":"arxiv","version":3},"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/2404.01856/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":"2026-07-05T11:18:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tyUXuy1ibxqXJBsXyWOvdIZSm80rCYOC7u/ROkKwhMTQ6KWhAYkXE56EBTAdxBrspPEqbJVQ7CHwvZg1opnqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:00:15.925870Z"},"content_sha256":"35e6df5106857777d7124524d70349680bc9043e7cb56890fcf709706c0f1362","schema_version":"1.0","event_id":"sha256:35e6df5106857777d7124524d70349680bc9043e7cb56890fcf709706c0f1362"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6S3OIHA3FBDPGB2Z6GT2ZB7RBU/bundle.json","state_url":"https://pith.science/pith/6S3OIHA3FBDPGB2Z6GT2ZB7RBU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6S3OIHA3FBDPGB2Z6GT2ZB7RBU/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":"2026-08-23T21:00:15Z","links":{"resolver":"https://pith.science/pith/6S3OIHA3FBDPGB2Z6GT2ZB7RBU","bundle":"https://pith.science/pith/6S3OIHA3FBDPGB2Z6GT2ZB7RBU/bundle.json","state":"https://pith.science/pith/6S3OIHA3FBDPGB2Z6GT2ZB7RBU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6S3OIHA3FBDPGB2Z6GT2ZB7RBU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6S3OIHA3FBDPGB2Z6GT2ZB7RBU","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":"fd5568393f132d7c687bf4204e7e008ae16c817b2bb21abc4ff8282f12e36291","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:34:12Z","title_canon_sha256":"f0993df15c7c5ef1808c8d1f8f13f166e79e9d0b0e422ef083d34caeed1a4d7b"},"schema_version":"1.0","source":{"id":"2404.01856","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01856","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01856v3","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01856","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_12","alias_value":"6S3OIHA3FBDP","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_16","alias_value":"6S3OIHA3FBDPGB2Z","created_at":"2026-07-05T11:18:57Z"},{"alias_kind":"pith_short_8","alias_value":"6S3OIHA3","created_at":"2026-07-05T11:18:57Z"}],"graph_snapshots":[{"event_id":"sha256:35e6df5106857777d7124524d70349680bc9043e7cb56890fcf709706c0f1362","target":"graph","created_at":"2026-07-05T11:18:57Z","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/2404.01856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pretraining of state-of-the-art large language models now requires trillions of words of text, which is orders of magnitude more than available for the vast majority of languages. While including text in more than one language is an obvious way to acquire more pretraining data, multilinguality is often seen as a curse, and most model training efforts continue to focus near-exclusively on individual large languages. We believe that multilinguality can be a blessing: when the lack of training data is a constraint for effectively training larger models for a target language, augmenting the da","authors_text":"Aarne Talman, Elaine Zosa, Jonathan Burdge, Peter Sarlin, Risto Luukkonen, Sampo Pyysalo, V\\\"ain\\\"o Hatanp\\\"a\\\"a, Ville Komulainen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:34:12Z","title":"Poro 34B and the Blessing of Multilinguality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01856","kind":"arxiv","version":3},"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":"sha256:085aadcf6c8f206c3e71a6eeafd23cffc0503d1616dc64a3236c42ad473f7d94","target":"record","created_at":"2026-07-05T11:18:57Z","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":"fd5568393f132d7c687bf4204e7e008ae16c817b2bb21abc4ff8282f12e36291","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T11:34:12Z","title_canon_sha256":"f0993df15c7c5ef1808c8d1f8f13f166e79e9d0b0e422ef083d34caeed1a4d7b"},"schema_version":"1.0","source":{"id":"2404.01856","kind":"arxiv","version":3}},"canonical_sha256":"f4b6e41c1b2846f30759f1a7ac87f10d0569faca748490d5fccb068de64a377d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4b6e41c1b2846f30759f1a7ac87f10d0569faca748490d5fccb068de64a377d","first_computed_at":"2026-07-05T11:18:57.983769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:57.983769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xO7zTc/1v1n81un1FPm4dZpOaynjKMSJOmZWzyDX/j1LCO8swMILTtIsgi1JNSBe0txEFqmr4xAWv9OaQHgFAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:57.984267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01856","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:085aadcf6c8f206c3e71a6eeafd23cffc0503d1616dc64a3236c42ad473f7d94","sha256:35e6df5106857777d7124524d70349680bc9043e7cb56890fcf709706c0f1362"],"state_sha256":"5d386ba018a9bf4bcf4d574e5f9d93a1d4d330eb46769c59c03db5c8824f4856"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fzH979qP+Rq0WA3jzCoMNJGmZe/wRiUhVqWAqcSW6bshqiLC42sc5Vuj1JmwIoV6hPbJ9hKoBpKTPdPGorhoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T21:00:15.929267Z","bundle_sha256":"55b2f3800333f4c62aa5060629143dbe3c30bb47ba7544140d62ac634dcf2417"}}