{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZQUQ656QOYLLHR2KOY7IPONUPS","short_pith_number":"pith:ZQUQ656Q","canonical_record":{"source":{"id":"2303.17183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-30T06:42:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2469d072bdad64733430ca99806331fdebb4ae5d88692b278db74ddb6fce6b1e","abstract_canon_sha256":"79030723059583945bc4e047af56f060ad9da2cf74761b08a6e1952a82a89638"},"schema_version":"1.0"},"canonical_sha256":"cc290f77d07616b3c74a763e87b9b47ca225e3b637407789079b6f6ad8cd4b38","source":{"kind":"arxiv","id":"2303.17183","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17183","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17183v1","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17183","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZQUQ656QOYLL","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZQUQ656QOYLLHR2K","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZQUQ656Q","created_at":"2026-07-05T05:56:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZQUQ656QOYLLHR2KOY7IPONUPS","target":"record","payload":{"canonical_record":{"source":{"id":"2303.17183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-30T06:42:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2469d072bdad64733430ca99806331fdebb4ae5d88692b278db74ddb6fce6b1e","abstract_canon_sha256":"79030723059583945bc4e047af56f060ad9da2cf74761b08a6e1952a82a89638"},"schema_version":"1.0"},"canonical_sha256":"cc290f77d07616b3c74a763e87b9b47ca225e3b637407789079b6f6ad8cd4b38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:20.582053Z","signature_b64":"mAwvQyLLEkoxrYjglsWkx/zh77PgPyv2coqXeE17eeT3s73n2N/xR/k4oaJ4R3LxUkqwuNUGLRS7DrPWIXIuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc290f77d07616b3c74a763e87b9b47ca225e3b637407789079b6f6ad8cd4b38","last_reissued_at":"2026-07-05T05:56:20.581653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:20.581653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.17183","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":"2026-07-05T05:56:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wOoV2sIvhDUpjxzqAnsov2Sr0WT71DaYvHxGfTaLtAJztaI3jhogKG2CphOc2w95AUdVoPU0x5WU+oHvj+4TCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:06:11.294147Z"},"content_sha256":"5c0b27175a1ae32b8f0e73d0c6aaee692731246332728112a55d82daa3ef2552","schema_version":"1.0","event_id":"sha256:5c0b27175a1ae32b8f0e73d0c6aaee692731246332728112a55d82daa3ef2552"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZQUQ656QOYLLHR2KOY7IPONUPS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Nordic Pile: A 1.2TB Nordic Dataset for Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amaru Cuba Gyllensten, Ariel Ekgren, Evangelia Gogoulou, Fredrik Carlsson, Joey \\\"Ohman, Magnus Sahlgren, Severine Verlinden, Tim Isbister","submitted_at":"2023-03-30T06:42:22Z","abstract_excerpt":"Pre-training Large Language Models (LLMs) require massive amounts of text data, and the performance of the LLMs typically correlates with the scale and quality of the datasets. This means that it may be challenging to build LLMs for smaller languages such as Nordic ones, where the availability of text corpora is limited. In order to facilitate the development of the LLMS in the Nordic languages, we curate a high-quality dataset consisting of 1.2TB of text, in all of the major North Germanic languages (Danish, Icelandic, Norwegian, and Swedish), as well as some high-quality English data. This p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17183","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/2303.17183/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":"2026-07-05T05:56:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HBGqQ+zBh9Ey4WzjSOR/3ucIwxWoxoUcpP8Z1W6oORwHygYfTQX4oHQlm36eu/kxT2/jkoabpd/BdbGmr+mrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:06:11.295164Z"},"content_sha256":"02a2c32f7eaa6836cef1ecc20308f75207991ef0bff05fdb2a37c835cc3c2cc1","schema_version":"1.0","event_id":"sha256:02a2c32f7eaa6836cef1ecc20308f75207991ef0bff05fdb2a37c835cc3c2cc1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQUQ656QOYLLHR2KOY7IPONUPS/bundle.json","state_url":"https://pith.science/pith/ZQUQ656QOYLLHR2KOY7IPONUPS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQUQ656QOYLLHR2KOY7IPONUPS/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":"2026-08-19T10:06:11Z","links":{"resolver":"https://pith.science/pith/ZQUQ656QOYLLHR2KOY7IPONUPS","bundle":"https://pith.science/pith/ZQUQ656QOYLLHR2KOY7IPONUPS/bundle.json","state":"https://pith.science/pith/ZQUQ656QOYLLHR2KOY7IPONUPS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQUQ656QOYLLHR2KOY7IPONUPS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZQUQ656QOYLLHR2KOY7IPONUPS","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":"79030723059583945bc4e047af56f060ad9da2cf74761b08a6e1952a82a89638","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-30T06:42:22Z","title_canon_sha256":"2469d072bdad64733430ca99806331fdebb4ae5d88692b278db74ddb6fce6b1e"},"schema_version":"1.0","source":{"id":"2303.17183","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.17183","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.17183v1","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17183","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZQUQ656QOYLL","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZQUQ656QOYLLHR2K","created_at":"2026-07-05T05:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZQUQ656Q","created_at":"2026-07-05T05:56:20Z"}],"graph_snapshots":[{"event_id":"sha256:02a2c32f7eaa6836cef1ecc20308f75207991ef0bff05fdb2a37c835cc3c2cc1","target":"graph","created_at":"2026-07-05T05:56:20Z","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/2303.17183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training Large Language Models (LLMs) require massive amounts of text data, and the performance of the LLMs typically correlates with the scale and quality of the datasets. This means that it may be challenging to build LLMs for smaller languages such as Nordic ones, where the availability of text corpora is limited. In order to facilitate the development of the LLMS in the Nordic languages, we curate a high-quality dataset consisting of 1.2TB of text, in all of the major North Germanic languages (Danish, Icelandic, Norwegian, and Swedish), as well as some high-quality English data. This p","authors_text":"Amaru Cuba Gyllensten, Ariel Ekgren, Evangelia Gogoulou, Fredrik Carlsson, Joey \\\"Ohman, Magnus Sahlgren, Severine Verlinden, Tim Isbister","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-30T06:42:22Z","title":"The Nordic Pile: A 1.2TB Nordic Dataset for Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17183","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":"sha256:5c0b27175a1ae32b8f0e73d0c6aaee692731246332728112a55d82daa3ef2552","target":"record","created_at":"2026-07-05T05:56:20Z","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":"79030723059583945bc4e047af56f060ad9da2cf74761b08a6e1952a82a89638","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-30T06:42:22Z","title_canon_sha256":"2469d072bdad64733430ca99806331fdebb4ae5d88692b278db74ddb6fce6b1e"},"schema_version":"1.0","source":{"id":"2303.17183","kind":"arxiv","version":1}},"canonical_sha256":"cc290f77d07616b3c74a763e87b9b47ca225e3b637407789079b6f6ad8cd4b38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc290f77d07616b3c74a763e87b9b47ca225e3b637407789079b6f6ad8cd4b38","first_computed_at":"2026-07-05T05:56:20.581653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:20.581653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mAwvQyLLEkoxrYjglsWkx/zh77PgPyv2coqXeE17eeT3s73n2N/xR/k4oaJ4R3LxUkqwuNUGLRS7DrPWIXIuCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:20.582053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.17183","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c0b27175a1ae32b8f0e73d0c6aaee692731246332728112a55d82daa3ef2552","sha256:02a2c32f7eaa6836cef1ecc20308f75207991ef0bff05fdb2a37c835cc3c2cc1"],"state_sha256":"4296d8079b4b8cb7432df50b30a359f8adb4baa03dc4f386a1f16322cd382fda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qb9zX5M5biIXhAAawxRwxx1mNS41ElnkoKrtXINaGnzGbn+Tqduk6hhiPROAXWgmdR/Q1gICkd09fhFbEvnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:06:11.300021Z","bundle_sha256":"89618a044d1561bd50d414d89ded3b906e2284092fbac78e4f3bf26dbd52c57a"}}