{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2JLTHYKDJIYCAF34KFMHT244XY","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":"97d0810375bcf87d39326be6f6b6015e772d131daa96798130b962e08ee5b62a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:52:42Z","title_canon_sha256":"6a2ab98c24a0dcb28732f4de062978a6b193957834788d88ac217a18610cc29c"},"schema_version":"1.0","source":{"id":"2506.09026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09026","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09026v2","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09026","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_12","alias_value":"2JLTHYKDJIYC","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_16","alias_value":"2JLTHYKDJIYCAF34","created_at":"2026-07-05T11:20:56Z"},{"alias_kind":"pith_short_8","alias_value":"2JLTHYKD","created_at":"2026-07-05T11:20:56Z"}],"graph_snapshots":[{"event_id":"sha256:0ef9022c7d66f4869f315242811d93c8c6326c53e6edd2cb295919e69148806e","target":"graph","created_at":"2026-07-05T11:20:56Z","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/2506.09026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-time scaling offers a promising path to improve LLM reasoning by utilizing more compute at inference time; however, the true promise of this paradigm lies in extrapolation (i.e., improvement in performance on hard problems as LLMs keep \"thinking\" for longer, beyond the maximum token budget they were trained on). Surprisingly, we find that most existing reasoning models do not extrapolate well. We show that one way to enable extrapolation is by training the LLM to perform in-context exploration: training the LLM to effectively spend its test time budget by chaining operations (such as gene","authors_text":"Amrith Setlur, Aviral Kumar, Charlie Snell, Ian Wu, Jeremy Greer, Matthew Y. R. Yang, Max Simchowitz, Virginia Smith","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:52:42Z","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09026","kind":"arxiv","version":2},"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":"sha256:926db0a2b04bcf5408505a7733d605d50b2b765ecee2270b443ddba743c5fbd7","target":"record","created_at":"2026-07-05T11:20:56Z","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":"97d0810375bcf87d39326be6f6b6015e772d131daa96798130b962e08ee5b62a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:52:42Z","title_canon_sha256":"6a2ab98c24a0dcb28732f4de062978a6b193957834788d88ac217a18610cc29c"},"schema_version":"1.0","source":{"id":"2506.09026","kind":"arxiv","version":2}},"canonical_sha256":"d25733e1434a3020177c515879eb9cbe348307b389bed5d79765572fe0cf8f99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d25733e1434a3020177c515879eb9cbe348307b389bed5d79765572fe0cf8f99","first_computed_at":"2026-07-05T11:20:56.447045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:56.447045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S9aUuSB50NE2pGxKukose/PlMuXBZMdatAmYCq9knzAw8hCbrtkIUA/hFBvLYY/YXl5yPTFRjlVCLhv/LZFiDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:56.447593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:926db0a2b04bcf5408505a7733d605d50b2b765ecee2270b443ddba743c5fbd7","sha256:0ef9022c7d66f4869f315242811d93c8c6326c53e6edd2cb295919e69148806e"],"state_sha256":"0165294c25c87936ea332950119611b5e5fbfbad75eca71fcd61651a4f08e58c"}