{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BTBNQMG6SNVDUIAZD3EDGVGYNE","short_pith_number":"pith:BTBNQMG6","schema_version":"1.0","canonical_sha256":"0cc2d830de936a3a20191ec83354d8690d644a8d4a5fe6f05e4da5de8bbc65a3","source":{"kind":"arxiv","id":"2404.01657","version":1},"attestation_state":"computed","paper":{"title":"Release of Pre-Trained Models for the Japanese Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Akio Kaga, Kei Sawada, Kentaro Mitsui, Koh Mitsuda, Makoto Shing, Tianyu Zhao, Toshiaki Wakatsuki, Yukiya Hono","submitted_at":"2024-04-02T05:59:43Z","abstract_excerpt":"AI democratization aims to create a world in which the average person can utilize AI techniques. To achieve this goal, numerous research institutes have attempted to make their results accessible to the public. In particular, large pre-trained models trained on large-scale data have shown unprecedented potential, and their release has had a significant impact. However, most of the released models specialize in the English language, and thus, AI democratization in non-English-speaking communities is lagging significantly. To reduce this gap in AI access, we released Generative Pre-trained Trans"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.01657","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-02T05:59:43Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"83850575fb51f0fef48a38d404e42a4d96d34359b730dc0076e499b003e97e25","abstract_canon_sha256":"76cc7dedac169f7c21ae452acfa0e13fa1b5eb9818972ae9cb5e604fb843145c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:17.771384Z","signature_b64":"Wr7WcBtXW2ydDGV+BsvTq92LSOnoIs+h4oGKXdASO8WHnGAPXcwzz8hp7bb5lj9u3pBw63S/L/pnKtp+HMuDCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cc2d830de936a3a20191ec83354d8690d644a8d4a5fe6f05e4da5de8bbc65a3","last_reissued_at":"2026-07-05T08:03:17.770872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:17.770872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Release of Pre-Trained Models for the Japanese Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Akio Kaga, Kei Sawada, Kentaro Mitsui, Koh Mitsuda, Makoto Shing, Tianyu Zhao, Toshiaki Wakatsuki, Yukiya Hono","submitted_at":"2024-04-02T05:59:43Z","abstract_excerpt":"AI democratization aims to create a world in which the average person can utilize AI techniques. To achieve this goal, numerous research institutes have attempted to make their results accessible to the public. In particular, large pre-trained models trained on large-scale data have shown unprecedented potential, and their release has had a significant impact. However, most of the released models specialize in the English language, and thus, AI democratization in non-English-speaking communities is lagging significantly. To reduce this gap in AI access, we released Generative Pre-trained Trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01657","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/2404.01657/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.01657","created_at":"2026-07-05T08:03:17.770934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01657v1","created_at":"2026-07-05T08:03:17.770934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01657","created_at":"2026-07-05T08:03:17.770934+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTBNQMG6SNVD","created_at":"2026-07-05T08:03:17.770934+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTBNQMG6SNVDUIAZ","created_at":"2026-07-05T08:03:17.770934+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTBNQMG6","created_at":"2026-07-05T08:03:17.770934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11875","citing_title":"I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2408.11349","citing_title":"Image Score: Learning and Evaluating Human Preferences for Mercari Search","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15353","citing_title":"Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20237","citing_title":"Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE","json":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE.json","graph_json":"https://pith.science/api/pith-number/BTBNQMG6SNVDUIAZD3EDGVGYNE/graph.json","events_json":"https://pith.science/api/pith-number/BTBNQMG6SNVDUIAZD3EDGVGYNE/events.json","paper":"https://pith.science/paper/BTBNQMG6"},"agent_actions":{"view_html":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE","download_json":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE.json","view_paper":"https://pith.science/paper/BTBNQMG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01657&json=true","fetch_graph":"https://pith.science/api/pith-number/BTBNQMG6SNVDUIAZD3EDGVGYNE/graph.json","fetch_events":"https://pith.science/api/pith-number/BTBNQMG6SNVDUIAZD3EDGVGYNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE/action/storage_attestation","attest_author":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE/action/author_attestation","sign_citation":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE/action/citation_signature","submit_replication":"https://pith.science/pith/BTBNQMG6SNVDUIAZD3EDGVGYNE/action/replication_record"}},"created_at":"2026-07-05T08:03:17.770934+00:00","updated_at":"2026-07-05T08:03:17.770934+00:00"}