{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HKPVHLL26EQJUMANQ6C6NYCKEI","short_pith_number":"pith:HKPVHLL2","canonical_record":{"source":{"id":"2311.05640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T08:05:04Z","cross_cats_sorted":[],"title_canon_sha256":"8757a14fd494dafd3bb7a1dc32536fc39499fd67f20df80fc7783e089f3d8785","abstract_canon_sha256":"d9dd96088d45e37d4328df7087ab3f4622724f2cbdd1c35955ba0e28af60e11f"},"schema_version":"1.0"},"canonical_sha256":"3a9f53ad7af1209a300d8785e6e04a2205d81bb57d15da1445185728f102e713","source":{"kind":"arxiv","id":"2311.05640","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05640","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05640v1","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05640","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"HKPVHLL26EQJ","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"HKPVHLL26EQJUMAN","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"HKPVHLL2","created_at":"2026-07-05T07:11:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HKPVHLL26EQJUMANQ6C6NYCKEI","target":"record","payload":{"canonical_record":{"source":{"id":"2311.05640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T08:05:04Z","cross_cats_sorted":[],"title_canon_sha256":"8757a14fd494dafd3bb7a1dc32536fc39499fd67f20df80fc7783e089f3d8785","abstract_canon_sha256":"d9dd96088d45e37d4328df7087ab3f4622724f2cbdd1c35955ba0e28af60e11f"},"schema_version":"1.0"},"canonical_sha256":"3a9f53ad7af1209a300d8785e6e04a2205d81bb57d15da1445185728f102e713","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:20.777519Z","signature_b64":"+3ZCpet5WqVodtA2Hm/B4cdmA9osfllNFR3hhrZB1oVJlE3EDDSy5/y3q2b9ArOhgdLt6YPMK7dRRdEc+EjuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a9f53ad7af1209a300d8785e6e04a2205d81bb57d15da1445185728f102e713","last_reissued_at":"2026-07-05T07:11:20.777028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:20.777028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.05640","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":"2026-07-05T07:11:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cMD0i4WpGgLQ8K73PA/BUmYbi5gkvablC5+ARiG6KyS5HGhX3jJTZGm1kFv06o2KpaFJY8HO/6WWU9V7clHNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:02:51.808028Z"},"content_sha256":"719c7c8a310baae327e5a9b363f7efb107d4ffc1ad6656ebb2d49765ea737204","schema_version":"1.0","event_id":"sha256:719c7c8a310baae327e5a9b363f7efb107d4ffc1ad6656ebb2d49765ea737204"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HKPVHLL26EQJUMANQ6C6NYCKEI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FinGPT: Large Generative Models for a Small Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aija Vahtola, Aleksandra Piktus, Anni Eskelinen, Filip Ginter, Hanna-Mari Kupari, Jenna Kanerva, Jouni Luoma, Jyrki Heinonen, Mikko Merioksa, Niklas Muennighoff, Nouamane Tazi, Osma Suominen, Risto Luukkonen, Sampo Pyysalo, Samuel Antao, Samuli Sairanen, Teven Le Scao, Thomas Wang, Thomas Wolf, Veronika Laippala, Ville Komulainen","submitted_at":"2023-11-03T08:05:04Z","abstract_excerpt":"Large language models (LLMs) excel in many tasks in NLP and beyond, but most open models have very limited coverage of smaller languages and LLM work tends to focus on languages where nearly unlimited data is available for pretraining. In this work, we study the challenges of creating LLMs for Finnish, a language spoken by less than 0.1% of the world population. We compile an extensive dataset of Finnish combining web crawls, news, social media and eBooks. We pursue two approaches to pretrain models: 1) we train seven monolingual models from scratch (186M to 13B parameters) dubbed FinGPT, 2) w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05640","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/2311.05640/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":"2026-07-05T07:11:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"46NPR653uN3Ye1ZAH0Lbegxb8q1CIW2Eb7ql0T3rS7Sav4dHqRqL6By7KEu6xhvPR0JdU7eTD9yDmH8tb3VAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T16:02:51.808446Z"},"content_sha256":"c13403d67c475438561bbe41f24bb81b260b1a20956d88dce262580bbea2260f","schema_version":"1.0","event_id":"sha256:c13403d67c475438561bbe41f24bb81b260b1a20956d88dce262580bbea2260f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKPVHLL26EQJUMANQ6C6NYCKEI/bundle.json","state_url":"https://pith.science/pith/HKPVHLL26EQJUMANQ6C6NYCKEI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKPVHLL26EQJUMANQ6C6NYCKEI/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":"2026-08-05T16:02:51Z","links":{"resolver":"https://pith.science/pith/HKPVHLL26EQJUMANQ6C6NYCKEI","bundle":"https://pith.science/pith/HKPVHLL26EQJUMANQ6C6NYCKEI/bundle.json","state":"https://pith.science/pith/HKPVHLL26EQJUMANQ6C6NYCKEI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKPVHLL26EQJUMANQ6C6NYCKEI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HKPVHLL26EQJUMANQ6C6NYCKEI","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":"d9dd96088d45e37d4328df7087ab3f4622724f2cbdd1c35955ba0e28af60e11f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T08:05:04Z","title_canon_sha256":"8757a14fd494dafd3bb7a1dc32536fc39499fd67f20df80fc7783e089f3d8785"},"schema_version":"1.0","source":{"id":"2311.05640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05640","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05640v1","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05640","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"HKPVHLL26EQJ","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"HKPVHLL26EQJUMAN","created_at":"2026-07-05T07:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"HKPVHLL2","created_at":"2026-07-05T07:11:20Z"}],"graph_snapshots":[{"event_id":"sha256:c13403d67c475438561bbe41f24bb81b260b1a20956d88dce262580bbea2260f","target":"graph","created_at":"2026-07-05T07:11:20Z","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/2311.05640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel in many tasks in NLP and beyond, but most open models have very limited coverage of smaller languages and LLM work tends to focus on languages where nearly unlimited data is available for pretraining. In this work, we study the challenges of creating LLMs for Finnish, a language spoken by less than 0.1% of the world population. We compile an extensive dataset of Finnish combining web crawls, news, social media and eBooks. We pursue two approaches to pretrain models: 1) we train seven monolingual models from scratch (186M to 13B parameters) dubbed FinGPT, 2) w","authors_text":"Aija Vahtola, Aleksandra Piktus, Anni Eskelinen, Filip Ginter, Hanna-Mari Kupari, Jenna Kanerva, Jouni Luoma, Jyrki Heinonen, Mikko Merioksa, Niklas Muennighoff, Nouamane Tazi, Osma Suominen, Risto Luukkonen, Sampo Pyysalo, Samuel Antao, Samuli Sairanen, Teven Le Scao, Thomas Wang, Thomas Wolf, Veronika Laippala, Ville Komulainen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T08:05:04Z","title":"FinGPT: Large Generative Models for a Small Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05640","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":"sha256:719c7c8a310baae327e5a9b363f7efb107d4ffc1ad6656ebb2d49765ea737204","target":"record","created_at":"2026-07-05T07:11:20Z","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":"d9dd96088d45e37d4328df7087ab3f4622724f2cbdd1c35955ba0e28af60e11f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T08:05:04Z","title_canon_sha256":"8757a14fd494dafd3bb7a1dc32536fc39499fd67f20df80fc7783e089f3d8785"},"schema_version":"1.0","source":{"id":"2311.05640","kind":"arxiv","version":1}},"canonical_sha256":"3a9f53ad7af1209a300d8785e6e04a2205d81bb57d15da1445185728f102e713","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a9f53ad7af1209a300d8785e6e04a2205d81bb57d15da1445185728f102e713","first_computed_at":"2026-07-05T07:11:20.777028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:20.777028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+3ZCpet5WqVodtA2Hm/B4cdmA9osfllNFR3hhrZB1oVJlE3EDDSy5/y3q2b9ArOhgdLt6YPMK7dRRdEc+EjuBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:20.777519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:719c7c8a310baae327e5a9b363f7efb107d4ffc1ad6656ebb2d49765ea737204","sha256:c13403d67c475438561bbe41f24bb81b260b1a20956d88dce262580bbea2260f"],"state_sha256":"a4afc775bf8d3a166b9c9212b0913dc1fc8ffc1ff5a14d858afae7e6bb36dfd1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2AFrhsck18TbUCa6F/sTVb+U4xihj7G6TyKJ55pDXMkHwvRSJcFEnlJsKe6Sw6nIZFboKwcy08JeGTJvKZThBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T16:02:51.811086Z","bundle_sha256":"48d8dbdfa3b68fea4afb632fc91e05eda10cfd9e552e194d0ac441d76991ffe3"}}