{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XHM2JMJV2LSCW6QNEPIWZOI3AM","short_pith_number":"pith:XHM2JMJV","schema_version":"1.0","canonical_sha256":"b9d9a4b135d2e42b7a0d23d16cb91b031885cbae0b9d457a06e9a7b0c3fd644c","source":{"kind":"arxiv","id":"2606.26671","version":1},"attestation_state":"computed","paper":{"title":"NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chen Zhong, Muqing Li, Qiaobo Hao, Shunyi Wang, Yangqian Wu, Yayin He, Zhongjian Zhang, Ziqun Li","submitted_at":"2026-06-25T07:03:25Z","abstract_excerpt":"Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization. This work presents NebulaExp, a fully transparent, ablation-driven post-training pipeline built on Qwen3-8B-base, covering two orthogonal model branches: general instruct model and complex reasoning-specialized model. We curate a raw corpus of 3.84M multi-source SFT samples and a 200K verifiable RL candid"},"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":"2606.26671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T07:03:25Z","cross_cats_sorted":[],"title_canon_sha256":"b03487ae9e9c53944087e67c6d2b595d357d40d33423b42a6bf00d96d36fcccf","abstract_canon_sha256":"55b0cd5c5077215855983757b04553af594a369d11ab7639b7d18ce1eff7f947"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:56.416340Z","signature_b64":"UYa7/j8wTzjE4O3819BE7m+cFWp9/SdItLGXSNyVl/N2MStWPDgpLwWKezUK3cCRIuzrdrZJFc3faLK8kIAQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9d9a4b135d2e42b7a0d23d16cb91b031885cbae0b9d457a06e9a7b0c3fd644c","last_reissued_at":"2026-06-26T01:15:56.415856Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:56.415856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chen Zhong, Muqing Li, Qiaobo Hao, Shunyi Wang, Yangqian Wu, Yayin He, Zhongjian Zhang, Ziqun Li","submitted_at":"2026-06-25T07:03:25Z","abstract_excerpt":"Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization. This work presents NebulaExp, a fully transparent, ablation-driven post-training pipeline built on Qwen3-8B-base, covering two orthogonal model branches: general instruct model and complex reasoning-specialized model. We curate a raw corpus of 3.84M multi-source SFT samples and a 200K verifiable RL candid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26671","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/2606.26671/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":"2606.26671","created_at":"2026-06-26T01:15:56.415919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26671v1","created_at":"2026-06-26T01:15:56.415919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26671","created_at":"2026-06-26T01:15:56.415919+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHM2JMJV2LSC","created_at":"2026-06-26T01:15:56.415919+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHM2JMJV2LSCW6QN","created_at":"2026-06-26T01:15:56.415919+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHM2JMJV","created_at":"2026-06-26T01:15:56.415919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM","json":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM.json","graph_json":"https://pith.science/api/pith-number/XHM2JMJV2LSCW6QNEPIWZOI3AM/graph.json","events_json":"https://pith.science/api/pith-number/XHM2JMJV2LSCW6QNEPIWZOI3AM/events.json","paper":"https://pith.science/paper/XHM2JMJV"},"agent_actions":{"view_html":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM","download_json":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM.json","view_paper":"https://pith.science/paper/XHM2JMJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26671&json=true","fetch_graph":"https://pith.science/api/pith-number/XHM2JMJV2LSCW6QNEPIWZOI3AM/graph.json","fetch_events":"https://pith.science/api/pith-number/XHM2JMJV2LSCW6QNEPIWZOI3AM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM/action/storage_attestation","attest_author":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM/action/author_attestation","sign_citation":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM/action/citation_signature","submit_replication":"https://pith.science/pith/XHM2JMJV2LSCW6QNEPIWZOI3AM/action/replication_record"}},"created_at":"2026-06-26T01:15:56.415919+00:00","updated_at":"2026-06-26T01:15:56.415919+00:00"}