{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XYEK7QTKBGE5KHEQOBUEULRMCK","short_pith_number":"pith:XYEK7QTK","canonical_record":{"source":{"id":"2505.17063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T05:35:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3411af2244fa1e14f1d1abd3a996b86119d309e189231289efe6a887d753db54","abstract_canon_sha256":"d3eee70e547742c058e289b9acfb765947f442fa2dcf9564a9b0759e02392813"},"schema_version":"1.0"},"canonical_sha256":"be08afc26a0989d51c9070684a2e2c128c46fe1f3a35d6e4933f4cf32b9dd6d7","source":{"kind":"arxiv","id":"2505.17063","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17063","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17063v1","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17063","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_12","alias_value":"XYEK7QTKBGE5","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_16","alias_value":"XYEK7QTKBGE5KHEQ","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_8","alias_value":"XYEK7QTK","created_at":"2026-07-05T11:07:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XYEK7QTKBGE5KHEQOBUEULRMCK","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T05:35:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3411af2244fa1e14f1d1abd3a996b86119d309e189231289efe6a887d753db54","abstract_canon_sha256":"d3eee70e547742c058e289b9acfb765947f442fa2dcf9564a9b0759e02392813"},"schema_version":"1.0"},"canonical_sha256":"be08afc26a0989d51c9070684a2e2c128c46fe1f3a35d6e4933f4cf32b9dd6d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:46.466439Z","signature_b64":"VopCd5hPp3SJOP7at3raVJqAysvhNaE0kXQIPTGEhsKy7ifwZlQCn/NMd/XiH/E2RuXZe26gMq93RaNF2c0uBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be08afc26a0989d51c9070684a2e2c128c46fe1f3a35d6e4933f4cf32b9dd6d7","last_reissued_at":"2026-07-05T11:07:46.465813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:46.465813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17063","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":"2026-07-05T11:07:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jR1Bj3VbqjlEIU1udWR5jPK8mkh9kvgZon93rZZAwVmkyowqBh56hGvlkx4teTeW0/aNtX8HuX3RXdGp352tDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:16:43.809344Z"},"content_sha256":"7c50701ff850c15cc3abcf2820582678aae8f9bb085877eeb538d29bbe404ab3","schema_version":"1.0","event_id":"sha256:7c50701ff850c15cc3abcf2820582678aae8f9bb085877eeb538d29bbe404ab3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XYEK7QTKBGE5KHEQOBUEULRMCK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic Data RL: Task Definition Is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chuanwei Huang, Haofei Yu, Huishuai Zhang, Yiduo Guo, Yikang Shen, Zekai Zhang, Zhen Guo, Zi-ang Wang","submitted_at":"2025-05-18T05:35:13Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful way to adapt foundation models to specialized tasks, but its reliance on large-scale human-labeled data limits broad adoption. We introduce Synthetic Data RL, a simple and general framework that reinforcement fine-tunes models using only synthetic data generated from a task definition. Our method first generates question and answer pairs from the task definition and retrieved documents, then adapts the difficulty of the question based on model solvability, and selects questions using the average pass rate of the model across samples for RL training. On"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17063","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/2505.17063/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":"2026-07-05T11:07:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r5hoJ+H+C70PK0w743RYGIPmnkY7+evR8g0he8MbfbtFbRVnMXqepMVIFUNNA+ZLQh3onwtDRna5Cof8Ut5XDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:16:43.809937Z"},"content_sha256":"b6ee6dcd355884ed926b2900343801f6c6cd4f748d9b01b4c9191d5e39d55ec2","schema_version":"1.0","event_id":"sha256:b6ee6dcd355884ed926b2900343801f6c6cd4f748d9b01b4c9191d5e39d55ec2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYEK7QTKBGE5KHEQOBUEULRMCK/bundle.json","state_url":"https://pith.science/pith/XYEK7QTKBGE5KHEQOBUEULRMCK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYEK7QTKBGE5KHEQOBUEULRMCK/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":"2026-08-05T09:16:43Z","links":{"resolver":"https://pith.science/pith/XYEK7QTKBGE5KHEQOBUEULRMCK","bundle":"https://pith.science/pith/XYEK7QTKBGE5KHEQOBUEULRMCK/bundle.json","state":"https://pith.science/pith/XYEK7QTKBGE5KHEQOBUEULRMCK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYEK7QTKBGE5KHEQOBUEULRMCK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XYEK7QTKBGE5KHEQOBUEULRMCK","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":"d3eee70e547742c058e289b9acfb765947f442fa2dcf9564a9b0759e02392813","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T05:35:13Z","title_canon_sha256":"3411af2244fa1e14f1d1abd3a996b86119d309e189231289efe6a887d753db54"},"schema_version":"1.0","source":{"id":"2505.17063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17063","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17063v1","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17063","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_12","alias_value":"XYEK7QTKBGE5","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_16","alias_value":"XYEK7QTKBGE5KHEQ","created_at":"2026-07-05T11:07:46Z"},{"alias_kind":"pith_short_8","alias_value":"XYEK7QTK","created_at":"2026-07-05T11:07:46Z"}],"graph_snapshots":[{"event_id":"sha256:b6ee6dcd355884ed926b2900343801f6c6cd4f748d9b01b4c9191d5e39d55ec2","target":"graph","created_at":"2026-07-05T11:07:46Z","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/2505.17063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a powerful way to adapt foundation models to specialized tasks, but its reliance on large-scale human-labeled data limits broad adoption. We introduce Synthetic Data RL, a simple and general framework that reinforcement fine-tunes models using only synthetic data generated from a task definition. Our method first generates question and answer pairs from the task definition and retrieved documents, then adapts the difficulty of the question based on model solvability, and selects questions using the average pass rate of the model across samples for RL training. On","authors_text":"Chuanwei Huang, Haofei Yu, Huishuai Zhang, Yiduo Guo, Yikang Shen, Zekai Zhang, Zhen Guo, Zi-ang Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T05:35:13Z","title":"Synthetic Data RL: Task Definition Is All You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17063","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":"sha256:7c50701ff850c15cc3abcf2820582678aae8f9bb085877eeb538d29bbe404ab3","target":"record","created_at":"2026-07-05T11:07:46Z","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":"d3eee70e547742c058e289b9acfb765947f442fa2dcf9564a9b0759e02392813","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T05:35:13Z","title_canon_sha256":"3411af2244fa1e14f1d1abd3a996b86119d309e189231289efe6a887d753db54"},"schema_version":"1.0","source":{"id":"2505.17063","kind":"arxiv","version":1}},"canonical_sha256":"be08afc26a0989d51c9070684a2e2c128c46fe1f3a35d6e4933f4cf32b9dd6d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be08afc26a0989d51c9070684a2e2c128c46fe1f3a35d6e4933f4cf32b9dd6d7","first_computed_at":"2026-07-05T11:07:46.465813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:46.465813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VopCd5hPp3SJOP7at3raVJqAysvhNaE0kXQIPTGEhsKy7ifwZlQCn/NMd/XiH/E2RuXZe26gMq93RaNF2c0uBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:46.466439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c50701ff850c15cc3abcf2820582678aae8f9bb085877eeb538d29bbe404ab3","sha256:b6ee6dcd355884ed926b2900343801f6c6cd4f748d9b01b4c9191d5e39d55ec2"],"state_sha256":"1d71e0de3c6815c3e621a704bbceac40a34a567a5d2fc79063d453f20f28333d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPj4bZ+GU8juZXIZxnskS4cKAt7FGM8B68eW8BhDaU3UI+TCjyxdra9cPs9PGdvcrrUOL/KVSb3nH6S/tvo7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:16:43.818976Z","bundle_sha256":"033a00088b0df04f4b9d9996f415a7bde97e2d31da574aa9fde5489adf04b6a8"}}