{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7PDS7IYJV3PAZSXAI3LGC7G6WX","short_pith_number":"pith:7PDS7IYJ","schema_version":"1.0","canonical_sha256":"fbc72fa309aede0ccae046d6617cdeb5d8741f1c0fb632b64fc6c9c1d04b7729","source":{"kind":"arxiv","id":"2407.03502","version":1},"attestation_state":"computed","paper":{"title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ahmed Awadallah, Andres Codas, Arindam Mitra, Corby Rosset, Dany Rouhana, Fillipe Silva, Guoqing Zheng, Hamed Khanpour, Luciano Del Corro, Olga Vrousgos, Shweti Mahajan, Wei-Ge Chen, Yadong Lu, Yash Lara","submitted_at":"2024-07-03T21:01:12Z","abstract_excerpt":"Synthetic data is becoming increasingly important for accelerating the development of language models, both large and small. Despite several successful use cases, researchers also raised concerns around model collapse and drawbacks of imitating other models. This discrepancy can be attributed to the fact that synthetic data varies in quality and diversity. Effective use of synthetic data usually requires significant human effort in curating the data. We focus on using synthetic data for post-training, specifically creating data by powerful models to teach a new skill or behavior to another mod"},"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":"2407.03502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-03T21:01:12Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"13e768cfe516d9d049924782d5f28c4f01fc86aa64ae383dff37361e0f740b4e","abstract_canon_sha256":"f9833968423f9b671ce1c60b0d8a0d71a3bc89258dc3c59f7beec6f22bf6a646"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:20.921149Z","signature_b64":"AGgnzOX+jIf7pVp6SYkuQmEO25c20wqVTy8yBww4taq1IXNs0efNR5Xdk9oXtefrv+jEBOX+Q5tm7c1Q5eQBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbc72fa309aede0ccae046d6617cdeb5d8741f1c0fb632b64fc6c9c1d04b7729","last_reissued_at":"2026-07-05T08:40:20.920681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:20.920681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ahmed Awadallah, Andres Codas, Arindam Mitra, Corby Rosset, Dany Rouhana, Fillipe Silva, Guoqing Zheng, Hamed Khanpour, Luciano Del Corro, Olga Vrousgos, Shweti Mahajan, Wei-Ge Chen, Yadong Lu, Yash Lara","submitted_at":"2024-07-03T21:01:12Z","abstract_excerpt":"Synthetic data is becoming increasingly important for accelerating the development of language models, both large and small. Despite several successful use cases, researchers also raised concerns around model collapse and drawbacks of imitating other models. This discrepancy can be attributed to the fact that synthetic data varies in quality and diversity. Effective use of synthetic data usually requires significant human effort in curating the data. We focus on using synthetic data for post-training, specifically creating data by powerful models to teach a new skill or behavior to another mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03502","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/2407.03502/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":"2407.03502","created_at":"2026-07-05T08:40:20.920736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03502v1","created_at":"2026-07-05T08:40:20.920736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03502","created_at":"2026-07-05T08:40:20.920736+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PDS7IYJV3PA","created_at":"2026-07-05T08:40:20.920736+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PDS7IYJV3PAZSXA","created_at":"2026-07-05T08:40:20.920736+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PDS7IYJ","created_at":"2026-07-05T08:40:20.920736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25996","citing_title":"Autodata: An agentic data scientist to create high quality synthetic data","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25996","citing_title":"Autodata: An agentic data scientist to create high quality synthetic data","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21337","citing_title":"DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11520","citing_title":"ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11127","citing_title":"Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09138","citing_title":"Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07710","citing_title":"WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02908","citing_title":"WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10832","citing_title":"Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06638","citing_title":"Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2504.21318","citing_title":"Phi-4-reasoning Technical Report","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2501.06322","citing_title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10999","citing_title":"SkillGen: Verified Inference-Time Agent Skill Synthesis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10832","citing_title":"Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06638","citing_title":"Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06638","citing_title":"Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14116","citing_title":"TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2507.20534","citing_title":"Kimi K2: Open Agentic Intelligence","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX","json":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX.json","graph_json":"https://pith.science/api/pith-number/7PDS7IYJV3PAZSXAI3LGC7G6WX/graph.json","events_json":"https://pith.science/api/pith-number/7PDS7IYJV3PAZSXAI3LGC7G6WX/events.json","paper":"https://pith.science/paper/7PDS7IYJ"},"agent_actions":{"view_html":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX","download_json":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX.json","view_paper":"https://pith.science/paper/7PDS7IYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03502&json=true","fetch_graph":"https://pith.science/api/pith-number/7PDS7IYJV3PAZSXAI3LGC7G6WX/graph.json","fetch_events":"https://pith.science/api/pith-number/7PDS7IYJV3PAZSXAI3LGC7G6WX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/action/storage_attestation","attest_author":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/action/author_attestation","sign_citation":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/action/citation_signature","submit_replication":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/action/replication_record"}},"created_at":"2026-07-05T08:40:20.920736+00:00","updated_at":"2026-07-05T08:40:20.920736+00:00"}