{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:I66WEYEATLYNFVQUCHJCBGN3FJ","short_pith_number":"pith:I66WEYEA","schema_version":"1.0","canonical_sha256":"47bd6260809af0d2d61411d22099bb2a4ca5731970cf1d1462726e103dc70c48","source":{"kind":"arxiv","id":"2606.23595","version":1},"attestation_state":"computed","paper":{"title":"SPIRAL: Learning to Search and Aggregate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chelsea Finn, Dorsa Sadigh, Ifdita Hasan Orney, Jubayer Ibn Hamid, Michael Y. Li, Noah Goodman, Omar Shaikh, Yoonho Lee","submitted_at":"2026-06-22T17:02:09Z","abstract_excerpt":"Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -- sequential reasoning within a trace, independently sampled parallel traces, and aggregation of multiple reasoning traces into a final response. During post-training, however, language models are optimized only for sequential reasoning within a single trace. We introduce Sequential-Parallel-Aggregative Reinforcement Learning (SPIRAL), a framework in which a language model is trained to use all three primitives, as part of a unified inference compute pipel"},"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":"2606.23595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T17:02:09Z","cross_cats_sorted":[],"title_canon_sha256":"a7c49ebb354bd7fa4050263af96f5a0a4284c25836ec0fe3d4b131b7414b9207","abstract_canon_sha256":"0073d6748c18d2b58d46774393abffd6d555ff001d70d8313379eae4d9993d77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:31.865424Z","signature_b64":"6Y/UVB6OLjagWQiXZdGCz1VLDQZcG4s4fJGItAJgTBBIvL+Y3ztzS8C0mIl+JH8ggtHAzK2vZhldgNYLxHj1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47bd6260809af0d2d61411d22099bb2a4ca5731970cf1d1462726e103dc70c48","last_reissued_at":"2026-06-23T03:14:31.865058Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:31.865058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPIRAL: Learning to Search and Aggregate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chelsea Finn, Dorsa Sadigh, Ifdita Hasan Orney, Jubayer Ibn Hamid, Michael Y. Li, Noah Goodman, Omar Shaikh, Yoonho Lee","submitted_at":"2026-06-22T17:02:09Z","abstract_excerpt":"Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -- sequential reasoning within a trace, independently sampled parallel traces, and aggregation of multiple reasoning traces into a final response. During post-training, however, language models are optimized only for sequential reasoning within a single trace. We introduce Sequential-Parallel-Aggregative Reinforcement Learning (SPIRAL), a framework in which a language model is trained to use all three primitives, as part of a unified inference compute pipel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23595","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/2606.23595/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":"2606.23595","created_at":"2026-06-23T03:14:31.865117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23595v1","created_at":"2026-06-23T03:14:31.865117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23595","created_at":"2026-06-23T03:14:31.865117+00:00"},{"alias_kind":"pith_short_12","alias_value":"I66WEYEATLYN","created_at":"2026-06-23T03:14:31.865117+00:00"},{"alias_kind":"pith_short_16","alias_value":"I66WEYEATLYNFVQU","created_at":"2026-06-23T03:14:31.865117+00:00"},{"alias_kind":"pith_short_8","alias_value":"I66WEYEA","created_at":"2026-06-23T03:14:31.865117+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/I66WEYEATLYNFVQUCHJCBGN3FJ","json":"https://pith.science/pith/I66WEYEATLYNFVQUCHJCBGN3FJ.json","graph_json":"https://pith.science/api/pith-number/I66WEYEATLYNFVQUCHJCBGN3FJ/graph.json","events_json":"https://pith.science/api/pith-number/I66WEYEATLYNFVQUCHJCBGN3FJ/events.json","paper":"https://pith.science/paper/I66WEYEA"},"agent_actions":{"view_html":"https://pith.science/pith/I66WEYEATLYNFVQUCHJCBGN3FJ","download_json":"https://pith.science/pith/I66WEYEATLYNFVQUCHJCBGN3FJ.json","view_paper":"https://pith.science/paper/I66WEYEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23595&json=true","fetch_graph":"https://pith.science/api/pith-number/I66WEYEATLYNFVQUCHJCBGN3FJ/graph.json","fetch_events":"https://pith.science/api/pith-number/I66WEYEATLYNFVQUCHJCBGN3FJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I66WEYEATLYNFVQUCHJCBGN3FJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I66WEYEATLYNFVQUCHJCBGN3FJ/action/storage_attestation","attest_author":"https://pith.science/pith/I66WEYEATLYNFVQUCHJCBGN3FJ/action/author_attestation","sign_citation":"https://pith.science/pith/I66WEYEATLYNFVQUCHJCBGN3FJ/action/citation_signature","submit_replication":"https://pith.science/pith/I66WEYEATLYNFVQUCHJCBGN3FJ/action/replication_record"}},"created_at":"2026-06-23T03:14:31.865117+00:00","updated_at":"2026-06-23T03:14:31.865117+00:00"}