{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7PDS7IYJV3PAZSXAI3LGC7G6WX","short_pith_number":"pith:7PDS7IYJ","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"},"canonical_sha256":"fbc72fa309aede0ccae046d6617cdeb5d8741f1c0fb632b64fc6c9c1d04b7729","source":{"kind":"arxiv","id":"2407.03502","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03502","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03502v1","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03502","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"7PDS7IYJV3PA","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"7PDS7IYJV3PAZSXA","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"7PDS7IYJ","created_at":"2026-07-05T08:40:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7PDS7IYJV3PAZSXAI3LGC7G6WX","target":"record","payload":{"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"},"canonical_sha256":"fbc72fa309aede0ccae046d6617cdeb5d8741f1c0fb632b64fc6c9c1d04b7729","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"},"source_kind":"arxiv","source_id":"2407.03502","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jczDVs19Q+rDBCRfMWMz588kLHodo/49IRiFkdlwQS3kAwFMDiu5gfz5bYxdvY2cdwHiwxl+PkU8UFsN/yDtAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T21:41:32.994565Z"},"content_sha256":"e43f5ec403c50f162a82e5cdefeb975b1a9bc18cbe876f9acba2b7d2fbc7a314","schema_version":"1.0","event_id":"sha256:e43f5ec403c50f162a82e5cdefeb975b1a9bc18cbe876f9acba2b7d2fbc7a314"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7PDS7IYJV3PAZSXAI3LGC7G6WX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:40:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gUEg3lY10UuUGDWndafORPeywjkVYWSUla/QkjtuP5ISfzOz6CjEltWPpEJdiNBw1MoZ9oXE8qmQrg0biEjuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T21:41:32.994951Z"},"content_sha256":"25e5950d5892577c946c17090fbf144d324ee47ce48bffc20fa3a94ac2433e16","schema_version":"1.0","event_id":"sha256:25e5950d5892577c946c17090fbf144d324ee47ce48bffc20fa3a94ac2433e16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/bundle.json","state_url":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-15T21:41:32Z","links":{"resolver":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX","bundle":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/bundle.json","state":"https://pith.science/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7PDS7IYJV3PAZSXAI3LGC7G6WX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7PDS7IYJV3PAZSXAI3LGC7G6WX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f9833968423f9b671ce1c60b0d8a0d71a3bc89258dc3c59f7beec6f22bf6a646","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-03T21:01:12Z","title_canon_sha256":"13e768cfe516d9d049924782d5f28c4f01fc86aa64ae383dff37361e0f740b4e"},"schema_version":"1.0","source":{"id":"2407.03502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03502","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03502v1","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03502","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"pith_short_12","alias_value":"7PDS7IYJV3PA","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"pith_short_16","alias_value":"7PDS7IYJV3PAZSXA","created_at":"2026-07-05T08:40:20Z"},{"alias_kind":"pith_short_8","alias_value":"7PDS7IYJ","created_at":"2026-07-05T08:40:20Z"}],"graph_snapshots":[{"event_id":"sha256:25e5950d5892577c946c17090fbf144d324ee47ce48bffc20fa3a94ac2433e16","target":"graph","created_at":"2026-07-05T08:40:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.03502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-03T21:01:12Z","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03502","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e43f5ec403c50f162a82e5cdefeb975b1a9bc18cbe876f9acba2b7d2fbc7a314","target":"record","created_at":"2026-07-05T08:40:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f9833968423f9b671ce1c60b0d8a0d71a3bc89258dc3c59f7beec6f22bf6a646","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-03T21:01:12Z","title_canon_sha256":"13e768cfe516d9d049924782d5f28c4f01fc86aa64ae383dff37361e0f740b4e"},"schema_version":"1.0","source":{"id":"2407.03502","kind":"arxiv","version":1}},"canonical_sha256":"fbc72fa309aede0ccae046d6617cdeb5d8741f1c0fb632b64fc6c9c1d04b7729","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbc72fa309aede0ccae046d6617cdeb5d8741f1c0fb632b64fc6c9c1d04b7729","first_computed_at":"2026-07-05T08:40:20.920681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:20.920681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AGgnzOX+jIf7pVp6SYkuQmEO25c20wqVTy8yBww4taq1IXNs0efNR5Xdk9oXtefrv+jEBOX+Q5tm7c1Q5eQBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:20.921149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e43f5ec403c50f162a82e5cdefeb975b1a9bc18cbe876f9acba2b7d2fbc7a314","sha256:25e5950d5892577c946c17090fbf144d324ee47ce48bffc20fa3a94ac2433e16"],"state_sha256":"e904ecd591c445e14edfb12012c62bcf07fd804e648511d8b518d7e6f6aabc22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uO6Ia8Hld/D4LCNQz3oXCB0gllJwvElhecmbs88vpvTpXOK2WJ4iEHuuFB27/hNdftH+4Ze+PcD/ttHuM8QqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T21:41:32.997171Z","bundle_sha256":"60ba0fc069b02ed357ee62152b2c21537c2754e5ca778c2734d6ef85e4a8897e"}}