{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C7Y3M7G4XKCWKFMLDGOISJJKNX","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":"6f4f561a01ded9716eeeb40f87ff4b3fb14a5d398fe514248c57dd4a58fd4c93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-02T05:01:05Z","title_canon_sha256":"1f01da6397752e8cb232c781c825d0d88c42bc368335cebbbc1daf20146ac842"},"schema_version":"1.0","source":{"id":"2605.01248","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01248","created_at":"2026-06-10T01:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01248v3","created_at":"2026-06-10T01:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01248","created_at":"2026-06-10T01:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"C7Y3M7G4XKCW","created_at":"2026-06-10T01:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"C7Y3M7G4XKCWKFML","created_at":"2026-06-10T01:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"C7Y3M7G4","created_at":"2026-06-10T01:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:2cffe02c43898b16cd401d385534db96dc16b9c4ac3aeb1dfcbf2d9cb0c242e6","target":"graph","created_at":"2026-06-10T01:08:36Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our evaluations show that S^3-R1 outperforms existing baselines by learning more effective search and synthesis strategies, yielding up to a 10% improvement in robust generalization on out-of-domain datasets."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The synthetic generation and retrieval-based verification pipeline produces questions of genuinely intermediate difficulty that transfer to real user queries without introducing distribution shift or annotation artifacts that inflate measured gains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"S^3-R1 generates synthetic intermediate-difficulty multi-hop questions and applies dense rewards for search quality plus answer correctness, yielding up to 10% better out-of-domain generalization than baselines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Coupling synthetic multi-hop questions with rewards for search steps and answers enables models to learn effective retrieval strategies and generalize up to 10% better out of domain."}],"snapshot_sha256":"1e0be816271a93b5b2ce8a405475b9b96d5fd22abc48d355f12fbd768549b879"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T18:36:11.355256Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T17:28:38.166668Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.01248/integrity.json","findings":[],"snapshot_sha256":"304b5c8b06090ffc52ef51d631cf34569b03302993c92030bfeae2c01d150f4b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) post-training has enabled newer capabilities in models, such as agentic tool-use for search. However, these models struggle primarily due to limitations with sparse outcome-based rewards and a lack of training data that encapsulates questions of differing hardness, which results in models not performing deeper searches with tools to collect evidence for question-answering. To address these limitations, we introduce S^3-R1 (Synthetic data and stabilized Search R1), a framework that couples a data-centric approach with denser learning signals. We first develop a synth","authors_text":"Akhil Udathu, Atharva Parulekar, Harsh Goel, Pradnesh Kalkar, Susmija Jabbireddy","cross_cats":[],"headline":"Coupling synthetic multi-hop questions with rewards for search steps and answers enables models to learn effective retrieval strategies and generalize up to 10% better out of domain.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-02T05:01:05Z","title":"$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.01248","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-09T15:05:21.542628Z","id":"5a42145d-1340-44a4-9004-dae1b835fed5","model_set":{"reader":"grok-4.3"},"one_line_summary":"S^3-R1 generates synthetic intermediate-difficulty multi-hop questions and applies dense rewards for search quality plus answer correctness, yielding up to 10% better out-of-domain generalization than baselines.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Coupling synthetic multi-hop questions with rewards for search steps and answers enables models to learn effective retrieval strategies and generalize up to 10% better out of domain.","strongest_claim":"Our evaluations show that S^3-R1 outperforms existing baselines by learning more effective search and synthesis strategies, yielding up to a 10% improvement in robust generalization on out-of-domain datasets.","weakest_assumption":"The synthetic generation and retrieval-based verification pipeline produces questions of genuinely intermediate difficulty that transfer to real user queries without introducing distribution shift or annotation artifacts that inflate measured gains."}},"verdict_id":"5a42145d-1340-44a4-9004-dae1b835fed5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:74c3a950859f512ab52f9e640cc8fd3baac03c46daeb9cf2d2ea5606f1f2024e","target":"record","created_at":"2026-06-10T01:08:36Z","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":"6f4f561a01ded9716eeeb40f87ff4b3fb14a5d398fe514248c57dd4a58fd4c93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-02T05:01:05Z","title_canon_sha256":"1f01da6397752e8cb232c781c825d0d88c42bc368335cebbbc1daf20146ac842"},"schema_version":"1.0","source":{"id":"2605.01248","kind":"arxiv","version":3}},"canonical_sha256":"17f1b67cdcba8565158b199c89252a6df2339321e26e07bde1637fe1b0acbbd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17f1b67cdcba8565158b199c89252a6df2339321e26e07bde1637fe1b0acbbd4","first_computed_at":"2026-06-10T01:08:36.073608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:08:36.073608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r2Io5K5J+/Jk0hOCkjBE0rmWLcxbVLODEY9w1HSfKBSVuWImrNK6DlameTCIfUh5dS5W/2AJW81Fs2xduQ1rBw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:08:36.074547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01248","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74c3a950859f512ab52f9e640cc8fd3baac03c46daeb9cf2d2ea5606f1f2024e","sha256:2cffe02c43898b16cd401d385534db96dc16b9c4ac3aeb1dfcbf2d9cb0c242e6"],"state_sha256":"d1876495d8b09b3481816f5556f6da343336f65018ac6b2a5f31328bba12382a"}