{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IOEDV6OBPROAPFTUHP24PBPKLC","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":"ea14bb6f668c8616d3835b5dfad95af5396cf7e470f27f1b3b04d8c5b1f989c3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T02:12:06Z","title_canon_sha256":"f4086f42b04270460b8d650545fb054592276287c6b102e28e170baed488bc7a"},"schema_version":"1.0","source":{"id":"2406.02856","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02856","created_at":"2026-07-05T09:37:08Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02856v5","created_at":"2026-07-05T09:37:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02856","created_at":"2026-07-05T09:37:08Z"},{"alias_kind":"pith_short_12","alias_value":"IOEDV6OBPROA","created_at":"2026-07-05T09:37:08Z"},{"alias_kind":"pith_short_16","alias_value":"IOEDV6OBPROAPFTU","created_at":"2026-07-05T09:37:08Z"},{"alias_kind":"pith_short_8","alias_value":"IOEDV6OB","created_at":"2026-07-05T09:37:08Z"}],"graph_snapshots":[{"event_id":"sha256:61c68ffd2c3f7651bb7051c455dde5b35f1c2a8204ece5e7cb20df6c581169a4","target":"graph","created_at":"2026-07-05T09:37:08Z","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/2406.02856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Xmodel-LM, a compact and efficient 1.1B language model pre-trained on around 2 trillion tokens. Trained on our self-built dataset (Xdata), which balances Chinese and English corpora based on downstream task optimization, Xmodel-LM exhibits remarkable performance despite its smaller size. It notably surpasses existing open-source language models of similar scale. Our model checkpoints and code are publicly accessible on GitHub at https://github.com/XiaoduoAILab/XmodelLM.","authors_text":"Ling Jiang, Qun Wang, Xucheng Huang, Yang Liu, Yichuan Wang, Yu Yan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T02:12:06Z","title":"Xmodel-LM Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02856","kind":"arxiv","version":5},"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":"sha256:035b9ac8ddad69f6309ecebc911b20070d17bfae5813d8c8e160f85295b56b23","target":"record","created_at":"2026-07-05T09:37:08Z","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":"ea14bb6f668c8616d3835b5dfad95af5396cf7e470f27f1b3b04d8c5b1f989c3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-05T02:12:06Z","title_canon_sha256":"f4086f42b04270460b8d650545fb054592276287c6b102e28e170baed488bc7a"},"schema_version":"1.0","source":{"id":"2406.02856","kind":"arxiv","version":5}},"canonical_sha256":"43883af9c17c5c0796743bf5c785ea58b773094180b93e5fab5041afa2a8da90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43883af9c17c5c0796743bf5c785ea58b773094180b93e5fab5041afa2a8da90","first_computed_at":"2026-07-05T09:37:08.604615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:08.604615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"feWFLNVEw3lZQTuHqP3tdOP/mqYzluHa9Ef39zZmDlnYtGwd/UnroF09G3PXKj0EmnSDFV+8S4Wb8Mq29CSUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:08.605094Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02856","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:035b9ac8ddad69f6309ecebc911b20070d17bfae5813d8c8e160f85295b56b23","sha256:61c68ffd2c3f7651bb7051c455dde5b35f1c2a8204ece5e7cb20df6c581169a4"],"state_sha256":"38cabab4b061c0d7b5f814249dba190cb99d4e0de96bfd625d453cacb78423d7"}