{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NJIPUPWV3CWS5NMTQYCXYG7RBB","short_pith_number":"pith:NJIPUPWV","canonical_record":{"source":{"id":"2503.09407","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T13:58:43Z","cross_cats_sorted":[],"title_canon_sha256":"d7268f132c921f17859dcf77df0305e7b75f9a6e7a363c4a2df0331a09234600","abstract_canon_sha256":"6682988a235a7f468ae09992754a6446f506ed57fbf80e5ee7e7c86c4f7cbaac"},"schema_version":"1.0"},"canonical_sha256":"6a50fa3ed5d8ad2eb59386057c1bf10872b0487ca76242ffd2d23a4d50d05dd0","source":{"kind":"arxiv","id":"2503.09407","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09407","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09407v1","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09407","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"pith_short_12","alias_value":"NJIPUPWV3CWS","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"NJIPUPWV3CWS5NMT","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"NJIPUPWV","created_at":"2026-07-05T10:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NJIPUPWV3CWS5NMTQYCXYG7RBB","target":"record","payload":{"canonical_record":{"source":{"id":"2503.09407","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T13:58:43Z","cross_cats_sorted":[],"title_canon_sha256":"d7268f132c921f17859dcf77df0305e7b75f9a6e7a363c4a2df0331a09234600","abstract_canon_sha256":"6682988a235a7f468ae09992754a6446f506ed57fbf80e5ee7e7c86c4f7cbaac"},"schema_version":"1.0"},"canonical_sha256":"6a50fa3ed5d8ad2eb59386057c1bf10872b0487ca76242ffd2d23a4d50d05dd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:55.694891Z","signature_b64":"qs+j9bcmFlmcOAZeUm2PG0sPJJG0VvIbgYFCQEMP09OFGEhkKGYtz9jZpx3m1qJo95FM24Z933ihG4fQWJ1+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a50fa3ed5d8ad2eb59386057c1bf10872b0487ca76242ffd2d23a4d50d05dd0","last_reissued_at":"2026-07-05T10:29:55.694220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:55.694220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.09407","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":"2026-07-05T10:29:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKL+FfylZTjo+8iz7nSv/QLYS9VQ0ZrKFZjP9la4r99H3R6Xj1Bk9oKstOYV2WiQxunZ5oAuBTaUKMT9oNMjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:29:45.171168Z"},"content_sha256":"82bb5ede8a32d76c22e541f9d61dfecbcbafb55315e19b24cb9a388b7fbc3276","schema_version":"1.0","event_id":"sha256:82bb5ede8a32d76c22e541f9d61dfecbcbafb55315e19b24cb9a388b7fbc3276"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NJIPUPWV3CWS5NMTQYCXYG7RBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Got Compute, but No Data: Lessons From Post-training a Finnish LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elaine Zosa, Sampo Pyysalo, Ville Komulainen","submitted_at":"2025-03-12T13:58:43Z","abstract_excerpt":"As LLMs gain more popularity as chatbots and general assistants, methods have been developed to enable LLMs to follow instructions and align with human preferences. These methods have found success in the field, but their effectiveness has not been demonstrated outside of high-resource languages. In this work, we discuss our experiences in post-training an LLM for instruction-following for English and Finnish. We use a multilingual LLM to translate instruction and preference datasets from English to Finnish. We perform instruction tuning and preference optimization in English and Finnish and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09407","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/2503.09407/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":"2026-07-05T10:29:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHouCPkq3GVIzdwVP+kwWZKnvNu+viAXPGICpXU++fq30h19m5859JGlevc8VzEKEEQbjrIoUhLBRi5dHZdBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:29:45.171803Z"},"content_sha256":"b097a5053debb234c75ceea0c48e8d8a61f336fcca59b30f00cfd8f8e2c25b05","schema_version":"1.0","event_id":"sha256:b097a5053debb234c75ceea0c48e8d8a61f336fcca59b30f00cfd8f8e2c25b05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJIPUPWV3CWS5NMTQYCXYG7RBB/bundle.json","state_url":"https://pith.science/pith/NJIPUPWV3CWS5NMTQYCXYG7RBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJIPUPWV3CWS5NMTQYCXYG7RBB/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":"2026-08-04T04:29:45Z","links":{"resolver":"https://pith.science/pith/NJIPUPWV3CWS5NMTQYCXYG7RBB","bundle":"https://pith.science/pith/NJIPUPWV3CWS5NMTQYCXYG7RBB/bundle.json","state":"https://pith.science/pith/NJIPUPWV3CWS5NMTQYCXYG7RBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJIPUPWV3CWS5NMTQYCXYG7RBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NJIPUPWV3CWS5NMTQYCXYG7RBB","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":"6682988a235a7f468ae09992754a6446f506ed57fbf80e5ee7e7c86c4f7cbaac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T13:58:43Z","title_canon_sha256":"d7268f132c921f17859dcf77df0305e7b75f9a6e7a363c4a2df0331a09234600"},"schema_version":"1.0","source":{"id":"2503.09407","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09407","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09407v1","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09407","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"pith_short_12","alias_value":"NJIPUPWV3CWS","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"NJIPUPWV3CWS5NMT","created_at":"2026-07-05T10:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"NJIPUPWV","created_at":"2026-07-05T10:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:b097a5053debb234c75ceea0c48e8d8a61f336fcca59b30f00cfd8f8e2c25b05","target":"graph","created_at":"2026-07-05T10:29:55Z","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/2503.09407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As LLMs gain more popularity as chatbots and general assistants, methods have been developed to enable LLMs to follow instructions and align with human preferences. These methods have found success in the field, but their effectiveness has not been demonstrated outside of high-resource languages. In this work, we discuss our experiences in post-training an LLM for instruction-following for English and Finnish. We use a multilingual LLM to translate instruction and preference datasets from English to Finnish. We perform instruction tuning and preference optimization in English and Finnish and e","authors_text":"Elaine Zosa, Sampo Pyysalo, Ville Komulainen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T13:58:43Z","title":"Got Compute, but No Data: Lessons From Post-training a Finnish LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09407","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":"sha256:82bb5ede8a32d76c22e541f9d61dfecbcbafb55315e19b24cb9a388b7fbc3276","target":"record","created_at":"2026-07-05T10:29:55Z","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":"6682988a235a7f468ae09992754a6446f506ed57fbf80e5ee7e7c86c4f7cbaac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T13:58:43Z","title_canon_sha256":"d7268f132c921f17859dcf77df0305e7b75f9a6e7a363c4a2df0331a09234600"},"schema_version":"1.0","source":{"id":"2503.09407","kind":"arxiv","version":1}},"canonical_sha256":"6a50fa3ed5d8ad2eb59386057c1bf10872b0487ca76242ffd2d23a4d50d05dd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a50fa3ed5d8ad2eb59386057c1bf10872b0487ca76242ffd2d23a4d50d05dd0","first_computed_at":"2026-07-05T10:29:55.694220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:55.694220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qs+j9bcmFlmcOAZeUm2PG0sPJJG0VvIbgYFCQEMP09OFGEhkKGYtz9jZpx3m1qJo95FM24Z933ihG4fQWJ1+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:55.694891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09407","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82bb5ede8a32d76c22e541f9d61dfecbcbafb55315e19b24cb9a388b7fbc3276","sha256:b097a5053debb234c75ceea0c48e8d8a61f336fcca59b30f00cfd8f8e2c25b05"],"state_sha256":"9d1a1db6d1acfd021c6fe3441ad85b04aa521baca8a67988d4674336f61ed434"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ipgUMXLHu038fQpIcXdhjN1OIkchOkbLPBqVswGS2Yy3rWtQP2WyUbHEGDElHWR7Nz3zxEzGB9pprVTzdZ9AAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:29:45.177658Z","bundle_sha256":"285654c47c865517d8324250de49b0330e21d26f993be6ef3140a274c05fee10"}}