{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HRI5GMROER7UP3XKHWIXZ4V7NW","short_pith_number":"pith:HRI5GMRO","canonical_record":{"source":{"id":"2504.15544","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:45:19Z","cross_cats_sorted":[],"title_canon_sha256":"c1eb59c5abf968e542f299e2dcf4df8caff5287858a4b48daa97e865a4a92198","abstract_canon_sha256":"42a22773708601e339d09f87232f2399ea741ce0852ea69178740cc1ff4947d1"},"schema_version":"1.0"},"canonical_sha256":"3c51d3322e247f47eeea3d917cf2bf6db766e9a93f97127ee5d6aa15518b14b7","source":{"kind":"arxiv","id":"2504.15544","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15544","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15544v1","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15544","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_12","alias_value":"HRI5GMROER7U","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_16","alias_value":"HRI5GMROER7UP3XK","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_8","alias_value":"HRI5GMRO","created_at":"2026-07-05T10:52:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HRI5GMROER7UP3XKHWIXZ4V7NW","target":"record","payload":{"canonical_record":{"source":{"id":"2504.15544","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:45:19Z","cross_cats_sorted":[],"title_canon_sha256":"c1eb59c5abf968e542f299e2dcf4df8caff5287858a4b48daa97e865a4a92198","abstract_canon_sha256":"42a22773708601e339d09f87232f2399ea741ce0852ea69178740cc1ff4947d1"},"schema_version":"1.0"},"canonical_sha256":"3c51d3322e247f47eeea3d917cf2bf6db766e9a93f97127ee5d6aa15518b14b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:26.295194Z","signature_b64":"l5b/NRMyZzcntVp/Omiwc4/msfyFvOBY0poATUY7cdBMsDL53XoTMrgTlNajyXU5qWw/cThMz8aQeHifaq1yAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c51d3322e247f47eeea3d917cf2bf6db766e9a93f97127ee5d6aa15518b14b7","last_reissued_at":"2026-07-05T10:52:26.294713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:26.294713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.15544","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":"2026-07-05T10:52:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aAMSSilPeKcxs8WrxASh1bLUY06JqQxQq5AjkK2SIqfb7+/FJIS8yTlwNTqbgJ3C08/RQ27XU+bu7y+eC87TBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:14:47.340689Z"},"content_sha256":"62f745819f144c3036633a60062cac43db6e3c94878138253cb12d9a216083ba","schema_version":"1.0","event_id":"sha256:62f745819f144c3036633a60062cac43db6e3c94878138253cb12d9a216083ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HRI5GMROER7UP3XKHWIXZ4V7NW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"llm-jp-modernbert: A ModernBERT Model Trained on a Large-Scale Japanese Corpus with Long Context Length","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Issa Sugiura, Kouta Nakayama, Yusuke Oda","submitted_at":"2025-04-22T02:45:19Z","abstract_excerpt":"Encoder-only transformer models like BERT are widely adopted as a pre-trained backbone for tasks like sentence classification and retrieval. However, pretraining of encoder models with large-scale corpora and long contexts has been relatively underexplored compared to decoder-only transformers. In this work, we present llm-jp-modernbert, a ModernBERT model trained on a publicly available, massive Japanese corpus with a context length of 8192 tokens. While our model does not surpass existing baselines on downstream tasks, it achieves good results on fill-mask test evaluations. We also analyze t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15544","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/2504.15544/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":"2026-07-05T10:52:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"addjoUmDcryvRIji05xLEinuR4n6c3PnT7frkrrjGvVm4bZm7mYFPssOnWIpdo5IemfaLpNJPHRvKnxvQkDVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:14:47.341193Z"},"content_sha256":"7cd4cbc31b73839be09c19460420144f00cacd15050088d5ddddd8fd47323a7c","schema_version":"1.0","event_id":"sha256:7cd4cbc31b73839be09c19460420144f00cacd15050088d5ddddd8fd47323a7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRI5GMROER7UP3XKHWIXZ4V7NW/bundle.json","state_url":"https://pith.science/pith/HRI5GMROER7UP3XKHWIXZ4V7NW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRI5GMROER7UP3XKHWIXZ4V7NW/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":"2026-08-19T18:14:47Z","links":{"resolver":"https://pith.science/pith/HRI5GMROER7UP3XKHWIXZ4V7NW","bundle":"https://pith.science/pith/HRI5GMROER7UP3XKHWIXZ4V7NW/bundle.json","state":"https://pith.science/pith/HRI5GMROER7UP3XKHWIXZ4V7NW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRI5GMROER7UP3XKHWIXZ4V7NW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HRI5GMROER7UP3XKHWIXZ4V7NW","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":"42a22773708601e339d09f87232f2399ea741ce0852ea69178740cc1ff4947d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:45:19Z","title_canon_sha256":"c1eb59c5abf968e542f299e2dcf4df8caff5287858a4b48daa97e865a4a92198"},"schema_version":"1.0","source":{"id":"2504.15544","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.15544","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"arxiv_version","alias_value":"2504.15544v1","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15544","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_12","alias_value":"HRI5GMROER7U","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_16","alias_value":"HRI5GMROER7UP3XK","created_at":"2026-07-05T10:52:26Z"},{"alias_kind":"pith_short_8","alias_value":"HRI5GMRO","created_at":"2026-07-05T10:52:26Z"}],"graph_snapshots":[{"event_id":"sha256:7cd4cbc31b73839be09c19460420144f00cacd15050088d5ddddd8fd47323a7c","target":"graph","created_at":"2026-07-05T10:52:26Z","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/2504.15544/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Encoder-only transformer models like BERT are widely adopted as a pre-trained backbone for tasks like sentence classification and retrieval. However, pretraining of encoder models with large-scale corpora and long contexts has been relatively underexplored compared to decoder-only transformers. In this work, we present llm-jp-modernbert, a ModernBERT model trained on a publicly available, massive Japanese corpus with a context length of 8192 tokens. While our model does not surpass existing baselines on downstream tasks, it achieves good results on fill-mask test evaluations. We also analyze t","authors_text":"Issa Sugiura, Kouta Nakayama, Yusuke Oda","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:45:19Z","title":"llm-jp-modernbert: A ModernBERT Model Trained on a Large-Scale Japanese Corpus with Long Context Length"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15544","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":"sha256:62f745819f144c3036633a60062cac43db6e3c94878138253cb12d9a216083ba","target":"record","created_at":"2026-07-05T10:52:26Z","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":"42a22773708601e339d09f87232f2399ea741ce0852ea69178740cc1ff4947d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-22T02:45:19Z","title_canon_sha256":"c1eb59c5abf968e542f299e2dcf4df8caff5287858a4b48daa97e865a4a92198"},"schema_version":"1.0","source":{"id":"2504.15544","kind":"arxiv","version":1}},"canonical_sha256":"3c51d3322e247f47eeea3d917cf2bf6db766e9a93f97127ee5d6aa15518b14b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c51d3322e247f47eeea3d917cf2bf6db766e9a93f97127ee5d6aa15518b14b7","first_computed_at":"2026-07-05T10:52:26.294713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:26.294713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l5b/NRMyZzcntVp/Omiwc4/msfyFvOBY0poATUY7cdBMsDL53XoTMrgTlNajyXU5qWw/cThMz8aQeHifaq1yAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:26.295194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.15544","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62f745819f144c3036633a60062cac43db6e3c94878138253cb12d9a216083ba","sha256:7cd4cbc31b73839be09c19460420144f00cacd15050088d5ddddd8fd47323a7c"],"state_sha256":"95a47b3e29bfc95cc76b510cb9efa0eb1f7ae736b5f133bfa061434cdb30d221"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/gRYanTflSrO+H1Pel8pIp2GGu1168PNyEKeetUr+x0+odw2tWncLPLhr6JoWPdPbROq1sozOZeuokii0tSAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T18:14:47.345332Z","bundle_sha256":"725a9d5adfefe50374bf7ebce7a46770f1066c43c7f3edadcb1a306933fcf5d1"}}