{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TNATPACAPSHL4DDQEHJS754STS","short_pith_number":"pith:TNATPACA","schema_version":"1.0","canonical_sha256":"9b413780407c8ebe0c7021d32ff7929c8950b7ff8b314c7b1d035633f43567a7","source":{"kind":"arxiv","id":"2503.19633","version":1},"attestation_state":"computed","paper":{"title":"1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Zhao, Haotian Wang, Shuaiting Chen, Sitong Zhao, Xiangang Li, Xiaoyu Tian, Yiping Peng, Yunjie Ji","submitted_at":"2025-03-25T13:19:46Z","abstract_excerpt":"The AM-DeepSeek-R1-Distilled is a large-scale dataset with thinking traces for general reasoning tasks, composed of high-quality and challenging reasoning problems. These problems are collected from a multitude of open-source datasets, subjected to semantic deduplication and meticulous cleaning to eliminate test set contamination. All responses within the dataset are distilled from reasoning models (predominantly DeepSeek-R1) and have undergone rigorous verification procedures. Mathematical problems are validated by checking against reference answers, code problems are verified using test case"},"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":"2503.19633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-25T13:19:46Z","cross_cats_sorted":[],"title_canon_sha256":"630fd94d3355dc7b7acdf29de7eb16890190657290295d70af663a3970be3282","abstract_canon_sha256":"f220bc308442fa2907cb23669042c60f507cc2c5f9e34f60bc8768c43edd1f79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:58.770126Z","signature_b64":"tSaNUAGlTB//GJrzUjyK/H6PjtSalVkBt7EWaGbNbQvC9n05WLobpyIW56ggXVXV9PjuwOUZHqZQpr9+Xe/XAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b413780407c8ebe0c7021d32ff7929c8950b7ff8b314c7b1d035633f43567a7","last_reissued_at":"2026-07-05T10:38:58.769621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:58.769621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Zhao, Haotian Wang, Shuaiting Chen, Sitong Zhao, Xiangang Li, Xiaoyu Tian, Yiping Peng, Yunjie Ji","submitted_at":"2025-03-25T13:19:46Z","abstract_excerpt":"The AM-DeepSeek-R1-Distilled is a large-scale dataset with thinking traces for general reasoning tasks, composed of high-quality and challenging reasoning problems. These problems are collected from a multitude of open-source datasets, subjected to semantic deduplication and meticulous cleaning to eliminate test set contamination. All responses within the dataset are distilled from reasoning models (predominantly DeepSeek-R1) and have undergone rigorous verification procedures. Mathematical problems are validated by checking against reference answers, code problems are verified using test case"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19633","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/2503.19633/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":"2503.19633","created_at":"2026-07-05T10:38:58.769686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19633v1","created_at":"2026-07-05T10:38:58.769686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19633","created_at":"2026-07-05T10:38:58.769686+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNATPACAPSHL","created_at":"2026-07-05T10:38:58.769686+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNATPACAPSHL4DDQ","created_at":"2026-07-05T10:38:58.769686+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNATPACA","created_at":"2026-07-05T10:38:58.769686+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28146","citing_title":"Cybersecurity AI (CAI) Dataset","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04062","citing_title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2512.11470","citing_title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13981","citing_title":"Towards Resource-Efficient LLMs: End-to-End Energy Accounting of Distillation Pipelines","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09100","citing_title":"GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09100","citing_title":"GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11627","citing_title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08477","citing_title":"SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04062","citing_title":"EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14029","citing_title":"POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02035","citing_title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS","json":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS.json","graph_json":"https://pith.science/api/pith-number/TNATPACAPSHL4DDQEHJS754STS/graph.json","events_json":"https://pith.science/api/pith-number/TNATPACAPSHL4DDQEHJS754STS/events.json","paper":"https://pith.science/paper/TNATPACA"},"agent_actions":{"view_html":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS","download_json":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS.json","view_paper":"https://pith.science/paper/TNATPACA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19633&json=true","fetch_graph":"https://pith.science/api/pith-number/TNATPACAPSHL4DDQEHJS754STS/graph.json","fetch_events":"https://pith.science/api/pith-number/TNATPACAPSHL4DDQEHJS754STS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS/action/storage_attestation","attest_author":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS/action/author_attestation","sign_citation":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS/action/citation_signature","submit_replication":"https://pith.science/pith/TNATPACAPSHL4DDQEHJS754STS/action/replication_record"}},"created_at":"2026-07-05T10:38:58.769686+00:00","updated_at":"2026-07-05T10:38:58.769686+00:00"}