{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XKVI3JTBG6VMOAOSRSKUB333JQ","short_pith_number":"pith:XKVI3JTB","schema_version":"1.0","canonical_sha256":"baaa8da66137aac701d28c9540ef7b4c15efc1d4cd56a87b2adcbf8f5bd5bff8","source":{"kind":"arxiv","id":"2505.00551","version":3},"attestation_state":"computed","paper":{"title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Wang, Chong Zhang, Dianwen Ng, Hai Ye, Lidong Bing, Qi Zhang, Xiang Lin, Xingxuan Li, Yao Xiao, Yue Deng, Zhanfeng Mo","submitted_at":"2025-05-01T14:28:35Z","abstract_excerpt":"The recent development of reasoning language models (RLMs) represents a novel evolution in large language models. In particular, the recent release of DeepSeek-R1 has generated widespread social impact and sparked enthusiasm in the research community for exploring the explicit reasoning paradigm of language models. However, the implementation details of the released models have not been fully open-sourced by DeepSeek, including DeepSeek-R1-Zero, DeepSeek-R1, and the distilled small models. As a result, many replication studies have emerged aiming to reproduce the strong performance achieved by"},"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":"2505.00551","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-01T14:28:35Z","cross_cats_sorted":[],"title_canon_sha256":"2b17d787b0c45f374994fddf66eb9c3d2b99fa844389ef8757d300443dd880f5","abstract_canon_sha256":"b93cc03fbc79398f715d91b70e6e3761f2cc2c16537bb2a02054dfd89112dbce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:23.939413Z","signature_b64":"ADKICBgxTt92lkaPTMLlgKp7zqpokCgaq86o2BtOUgNV2WKcDfrl1jQKOlAolCaUcsWriwNUgmba/241Qe9ACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baaa8da66137aac701d28c9540ef7b4c15efc1d4cd56a87b2adcbf8f5bd5bff8","last_reissued_at":"2026-07-05T11:03:23.939010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:23.939010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Wang, Chong Zhang, Dianwen Ng, Hai Ye, Lidong Bing, Qi Zhang, Xiang Lin, Xingxuan Li, Yao Xiao, Yue Deng, Zhanfeng Mo","submitted_at":"2025-05-01T14:28:35Z","abstract_excerpt":"The recent development of reasoning language models (RLMs) represents a novel evolution in large language models. In particular, the recent release of DeepSeek-R1 has generated widespread social impact and sparked enthusiasm in the research community for exploring the explicit reasoning paradigm of language models. However, the implementation details of the released models have not been fully open-sourced by DeepSeek, including DeepSeek-R1-Zero, DeepSeek-R1, and the distilled small models. As a result, many replication studies have emerged aiming to reproduce the strong performance achieved by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00551","kind":"arxiv","version":3},"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/2505.00551/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":"2505.00551","created_at":"2026-07-05T11:03:23.939067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00551v3","created_at":"2026-07-05T11:03:23.939067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00551","created_at":"2026-07-05T11:03:23.939067+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKVI3JTBG6VM","created_at":"2026-07-05T11:03:23.939067+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKVI3JTBG6VMOAOS","created_at":"2026-07-05T11:03:23.939067+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKVI3JTB","created_at":"2026-07-05T11:03:23.939067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08268","citing_title":"Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01249","citing_title":"Trust Region On-Policy Distillation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31446","citing_title":"Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Triplet Extraction","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08905","citing_title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ","json":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ.json","graph_json":"https://pith.science/api/pith-number/XKVI3JTBG6VMOAOSRSKUB333JQ/graph.json","events_json":"https://pith.science/api/pith-number/XKVI3JTBG6VMOAOSRSKUB333JQ/events.json","paper":"https://pith.science/paper/XKVI3JTB"},"agent_actions":{"view_html":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ","download_json":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ.json","view_paper":"https://pith.science/paper/XKVI3JTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00551&json=true","fetch_graph":"https://pith.science/api/pith-number/XKVI3JTBG6VMOAOSRSKUB333JQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XKVI3JTBG6VMOAOSRSKUB333JQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ/action/storage_attestation","attest_author":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ/action/author_attestation","sign_citation":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ/action/citation_signature","submit_replication":"https://pith.science/pith/XKVI3JTBG6VMOAOSRSKUB333JQ/action/replication_record"}},"created_at":"2026-07-05T11:03:23.939067+00:00","updated_at":"2026-07-05T11:03:23.939067+00:00"}