{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3TQWANOPPHUYIFYELJS26D63AJ","short_pith_number":"pith:3TQWANOP","canonical_record":{"source":{"id":"2208.12097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-25T13:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"321a5d15e66812fa206d011ceeec6ce4991f0af7b20a2254a1d2adda8aa5ed74","abstract_canon_sha256":"4cabba5cfd56aa1894530e70521b9e36b3474a0d30c55263530cfb08841b81ba"},"schema_version":"1.0"},"canonical_sha256":"dce16035cf79e98417045a65af0fdb0243b97cddb66fca3ce0fabc7eed27eb25","source":{"kind":"arxiv","id":"2208.12097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12097","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12097v1","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12097","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"3TQWANOPPHUY","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"3TQWANOPPHUYIFYE","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"3TQWANOP","created_at":"2026-07-05T04:51:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3TQWANOPPHUYIFYELJS26D63AJ","target":"record","payload":{"canonical_record":{"source":{"id":"2208.12097","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-25T13:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"321a5d15e66812fa206d011ceeec6ce4991f0af7b20a2254a1d2adda8aa5ed74","abstract_canon_sha256":"4cabba5cfd56aa1894530e70521b9e36b3474a0d30c55263530cfb08841b81ba"},"schema_version":"1.0"},"canonical_sha256":"dce16035cf79e98417045a65af0fdb0243b97cddb66fca3ce0fabc7eed27eb25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:29.352361Z","signature_b64":"dTrVcPoGNbFAeQ49L+PgzOwGvHsjTp28Csp3Lo3/O9JrHRkx4BJG+tS04kzT1WIcgBaWysf0MgNLspR0Fo+CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dce16035cf79e98417045a65af0fdb0243b97cddb66fca3ce0fabc7eed27eb25","last_reissued_at":"2026-07-05T04:51:29.351870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:29.351870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.12097","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":"2026-07-05T04:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A7F7Je+fiCy4DLv+7ks0nwQqyZa+5qUZojzTbU4uk5kacXMn0aWSHJUFOzrLdsiiBvekS+EHYYxx1f+iF3SMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:23:55.362700Z"},"content_sha256":"49aadfea91b4401cb4b5112a2e12a9945e750ebc31ed3ad26814c6bc40aff8bb","schema_version":"1.0","event_id":"sha256:49aadfea91b4401cb4b5112a2e12a9945e750ebc31ed3ad26814c6bc40aff8bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3TQWANOPPHUYIFYELJS26D63AJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training a T5 Using Lab-sized Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Leon Derczynski, Manuel R. Ciosici","submitted_at":"2022-08-25T13:55:16Z","abstract_excerpt":"Training large neural language models on large datasets is resource- and time-intensive. These requirements create a barrier to entry, where those with fewer resources cannot build competitive models. This paper presents various techniques for making it possible to (a) train a large language model using resources that a modest research lab might have, and (b) train it in a reasonable amount of time. We provide concrete recommendations for practitioners, which we illustrate with a case study: a T5 model for Danish, the first for this language."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12097","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/2208.12097/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":"2026-07-05T04:51:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RAHvoomeSF2FX/rdy96i8Zo51/AedfbCBnXDvvQO1tDZYh87FCfCkbFs6WH/uCJ+jDEj6UjONftQC4HrVIc9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T21:23:55.363331Z"},"content_sha256":"c707410b0e12fda427cddbe90183f7f85765dee7674606a33cc225d57d4333a0","schema_version":"1.0","event_id":"sha256:c707410b0e12fda427cddbe90183f7f85765dee7674606a33cc225d57d4333a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TQWANOPPHUYIFYELJS26D63AJ/bundle.json","state_url":"https://pith.science/pith/3TQWANOPPHUYIFYELJS26D63AJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TQWANOPPHUYIFYELJS26D63AJ/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":"2026-08-14T21:23:55Z","links":{"resolver":"https://pith.science/pith/3TQWANOPPHUYIFYELJS26D63AJ","bundle":"https://pith.science/pith/3TQWANOPPHUYIFYELJS26D63AJ/bundle.json","state":"https://pith.science/pith/3TQWANOPPHUYIFYELJS26D63AJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TQWANOPPHUYIFYELJS26D63AJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3TQWANOPPHUYIFYELJS26D63AJ","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":"4cabba5cfd56aa1894530e70521b9e36b3474a0d30c55263530cfb08841b81ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-25T13:55:16Z","title_canon_sha256":"321a5d15e66812fa206d011ceeec6ce4991f0af7b20a2254a1d2adda8aa5ed74"},"schema_version":"1.0","source":{"id":"2208.12097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.12097","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"arxiv_version","alias_value":"2208.12097v1","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12097","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"pith_short_12","alias_value":"3TQWANOPPHUY","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"pith_short_16","alias_value":"3TQWANOPPHUYIFYE","created_at":"2026-07-05T04:51:29Z"},{"alias_kind":"pith_short_8","alias_value":"3TQWANOP","created_at":"2026-07-05T04:51:29Z"}],"graph_snapshots":[{"event_id":"sha256:c707410b0e12fda427cddbe90183f7f85765dee7674606a33cc225d57d4333a0","target":"graph","created_at":"2026-07-05T04:51:29Z","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/2208.12097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large neural language models on large datasets is resource- and time-intensive. These requirements create a barrier to entry, where those with fewer resources cannot build competitive models. This paper presents various techniques for making it possible to (a) train a large language model using resources that a modest research lab might have, and (b) train it in a reasonable amount of time. We provide concrete recommendations for practitioners, which we illustrate with a case study: a T5 model for Danish, the first for this language.","authors_text":"Leon Derczynski, Manuel R. Ciosici","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-25T13:55:16Z","title":"Training a T5 Using Lab-sized Resources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12097","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":"sha256:49aadfea91b4401cb4b5112a2e12a9945e750ebc31ed3ad26814c6bc40aff8bb","target":"record","created_at":"2026-07-05T04:51:29Z","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":"4cabba5cfd56aa1894530e70521b9e36b3474a0d30c55263530cfb08841b81ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-25T13:55:16Z","title_canon_sha256":"321a5d15e66812fa206d011ceeec6ce4991f0af7b20a2254a1d2adda8aa5ed74"},"schema_version":"1.0","source":{"id":"2208.12097","kind":"arxiv","version":1}},"canonical_sha256":"dce16035cf79e98417045a65af0fdb0243b97cddb66fca3ce0fabc7eed27eb25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dce16035cf79e98417045a65af0fdb0243b97cddb66fca3ce0fabc7eed27eb25","first_computed_at":"2026-07-05T04:51:29.351870Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:29.351870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dTrVcPoGNbFAeQ49L+PgzOwGvHsjTp28Csp3Lo3/O9JrHRkx4BJG+tS04kzT1WIcgBaWysf0MgNLspR0Fo+CCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:29.352361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.12097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49aadfea91b4401cb4b5112a2e12a9945e750ebc31ed3ad26814c6bc40aff8bb","sha256:c707410b0e12fda427cddbe90183f7f85765dee7674606a33cc225d57d4333a0"],"state_sha256":"7eb260585f15a0851d3ad5ad0dd4ac6317b09d41abb74d78030fbc74116d6897"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iZUTO68agErYiwXB8d7dyln5I7Qtyj4EYOgbKkVk8/DtyU2QKLiT8/2gvIn7UKEthVtcBkSfCSyYqI7tecvmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T21:23:55.367492Z","bundle_sha256":"7570b6998b2f2e8cc2a16354ccc97d5c41f90ad4082381207010a08db416ec0b"}}