{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R7BX4S2PZJ3OTJDNH3NAUSHQET","short_pith_number":"pith:R7BX4S2P","schema_version":"1.0","canonical_sha256":"8fc37e4b4fca76e9a46d3eda0a48f024d2c402dd98ede0ddb444ce9b20133eba","source":{"kind":"arxiv","id":"2412.19638","version":1},"attestation_state":"computed","paper":{"title":"Xmodel-2 Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiang Ling, Lin Qingquan, Liu Yang, Qu Zhijiu, Wang Qun","submitted_at":"2024-12-27T13:32:10Z","abstract_excerpt":"Xmodel-2 is a 1.2-billion-parameter large language model designed specifically for reasoning tasks. Its architecture enables different model scales to share a unified set of hyperparameters, allowing for extensive experimentation on smaller models and seamless transfer of optimal configurations to larger models. To maximize training efficiency and stability, Xmodel-2 employs the WSD learning rate scheduler from MiniCPM. Pretrained on 1.5 trillion tokens from diverse sources, Xmodel-2 achieves state-of-the-art performance in complex reasoning and agent-based tasks, while maintaining low trainin"},"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":"2412.19638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-27T13:32:10Z","cross_cats_sorted":[],"title_canon_sha256":"b8b79ecd6a95694d89b1f8ac7f900a0d657288de75f2fcb03adb9f903e8c8247","abstract_canon_sha256":"130e0f6f4037f921a5600116ff86458c3d444102bd49f47f71d0a2c7f6096a49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:39.010640Z","signature_b64":"0oXYPNDxlD8BRgKk/x+N+WHZphh8WD6lF0zFbAKSPSXXwCTF+wadiJVSBFJIHvBfhaqhkbDVsPWjfAA3TLboDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fc37e4b4fca76e9a46d3eda0a48f024d2c402dd98ede0ddb444ce9b20133eba","last_reissued_at":"2026-07-05T09:54:39.010185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:39.010185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Xmodel-2 Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiang Ling, Lin Qingquan, Liu Yang, Qu Zhijiu, Wang Qun","submitted_at":"2024-12-27T13:32:10Z","abstract_excerpt":"Xmodel-2 is a 1.2-billion-parameter large language model designed specifically for reasoning tasks. Its architecture enables different model scales to share a unified set of hyperparameters, allowing for extensive experimentation on smaller models and seamless transfer of optimal configurations to larger models. To maximize training efficiency and stability, Xmodel-2 employs the WSD learning rate scheduler from MiniCPM. Pretrained on 1.5 trillion tokens from diverse sources, Xmodel-2 achieves state-of-the-art performance in complex reasoning and agent-based tasks, while maintaining low trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19638","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/2412.19638/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":"2412.19638","created_at":"2026-07-05T09:54:39.010240+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19638v1","created_at":"2026-07-05T09:54:39.010240+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19638","created_at":"2026-07-05T09:54:39.010240+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7BX4S2PZJ3O","created_at":"2026-07-05T09:54:39.010240+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7BX4S2PZJ3OTJDN","created_at":"2026-07-05T09:54:39.010240+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7BX4S2P","created_at":"2026-07-05T09:54:39.010240+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05330","citing_title":"MindFlow: Revolutionizing E-commerce Customer Support with Multimodal LLM Agents","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET","json":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET.json","graph_json":"https://pith.science/api/pith-number/R7BX4S2PZJ3OTJDNH3NAUSHQET/graph.json","events_json":"https://pith.science/api/pith-number/R7BX4S2PZJ3OTJDNH3NAUSHQET/events.json","paper":"https://pith.science/paper/R7BX4S2P"},"agent_actions":{"view_html":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET","download_json":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET.json","view_paper":"https://pith.science/paper/R7BX4S2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19638&json=true","fetch_graph":"https://pith.science/api/pith-number/R7BX4S2PZJ3OTJDNH3NAUSHQET/graph.json","fetch_events":"https://pith.science/api/pith-number/R7BX4S2PZJ3OTJDNH3NAUSHQET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET/action/storage_attestation","attest_author":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET/action/author_attestation","sign_citation":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET/action/citation_signature","submit_replication":"https://pith.science/pith/R7BX4S2PZJ3OTJDNH3NAUSHQET/action/replication_record"}},"created_at":"2026-07-05T09:54:39.010240+00:00","updated_at":"2026-07-05T09:54:39.010240+00:00"}