{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3HJXFK2TZWZXYCIKDKAOADFO2L","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":"0eca8639d8ae9de6bf5784563888314debc4f078593b865cca5e5818312e4420","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T07:46:39Z","title_canon_sha256":"2bfcf241d0bc60a93932934b8cd1c9ec3d962c5398174324e84468fd663267c2"},"schema_version":"1.0","source":{"id":"2605.03460","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.03460","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.03460v2","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03460","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"3HJXFK2TZWZX","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"3HJXFK2TZWZXYCIK","created_at":"2026-05-26T01:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"3HJXFK2T","created_at":"2026-05-26T01:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:94020ac77b9d7f799c11b785eaa3113c46cb1143bb50cd576dc7294f6f3dc13c","target":"graph","created_at":"2026-05-26T01:03:32Z","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":"The proposed method achieves 78.9% average accuracy on FinTSR-Bench, substantially outperforming LLM and TSRM baselines. Furthermore, we show that the four capability categories are complementary and mutually reinforcing through joint training, and that Scenario-Aware CoT consistently improves prediction accuracy over standard CoT."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the ten tasks constructed from S&P stocks adequately capture the distinctive challenges of financial reasoning and that the deterministic-versus-stochastic distinction is the primary reason current models underperform."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FinSTaR reaches 78.9% accuracy on a new financial time series reasoning benchmark by applying Compute-in-CoT for deterministic assessments and Scenario-Aware CoT for stochastic predictions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A 2x2 taxonomy of time series capabilities with tailored chain-of-thought strategies enables 78.9 percent accuracy on financial reasoning tasks from S&P stocks."}],"snapshot_sha256":"9e643edef0ce0de4df87f401f8add687028b68cde690bdcca2893d52b84e7a1e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T13:40:49.333291Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T01:01:21.890033Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:23:21.754179Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.03460/integrity.json","findings":[],"snapshot_sha256":"931eeaeb87e60099f7fd16af8722e29263ba4a58d0a71c144438dfc378345c36","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail on financial domain, which exhibit unique characteristics. We propose a general 2x2 capability taxonomy for TSRMs by crossing 1) single-entity vs. multi-entity analysis with 2) assessment of the current state vs. prediction of future behavior. We instantiate this taxonomy in the financial domain -- where the distinction between deterministic assessment and stochastic prediction is particularly critical -- as ten financial reasoning tasks, forming the FinTSR-Bench benchmark","authors_text":"Dongwan Kang, Hwanil Choi, Jaehoon Lee, Jun Seo, Minjae Kim, Seunghan Lee, Soonyoung Lee, Sungdong Yoo, Tae Yoon Lim, Wonbin Ahn","cross_cats":["cs.LG"],"headline":"A 2x2 taxonomy of time series capabilities with tailored chain-of-thought strategies enables 78.9 percent accuracy on financial reasoning tasks from S&P stocks.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T07:46:39Z","title":"FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.03460","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T16:47:45.280055Z","id":"43461c49-c64c-4b6e-a79d-0e695271a4f2","model_set":{"reader":"grok-4.3"},"one_line_summary":"FinSTaR reaches 78.9% accuracy on a new financial time series reasoning benchmark by applying Compute-in-CoT for deterministic assessments and Scenario-Aware CoT for stochastic predictions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A 2x2 taxonomy of time series capabilities with tailored chain-of-thought strategies enables 78.9 percent accuracy on financial reasoning tasks from S&P stocks.","strongest_claim":"The proposed method achieves 78.9% average accuracy on FinTSR-Bench, substantially outperforming LLM and TSRM baselines. Furthermore, we show that the four capability categories are complementary and mutually reinforcing through joint training, and that Scenario-Aware CoT consistently improves prediction accuracy over standard CoT.","weakest_assumption":"That the ten tasks constructed from S&P stocks adequately capture the distinctive challenges of financial reasoning and that the deterministic-versus-stochastic distinction is the primary reason current models underperform."}},"verdict_id":"43461c49-c64c-4b6e-a79d-0e695271a4f2"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e9393920eaf867e3c4a0a798ae0af20adad4bc496ebe4c5760cd008887e03f0d","target":"record","created_at":"2026-05-26T01:03:32Z","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":"0eca8639d8ae9de6bf5784563888314debc4f078593b865cca5e5818312e4420","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-05T07:46:39Z","title_canon_sha256":"2bfcf241d0bc60a93932934b8cd1c9ec3d962c5398174324e84468fd663267c2"},"schema_version":"1.0","source":{"id":"2605.03460","kind":"arxiv","version":2}},"canonical_sha256":"d9d372ab53cdb37c090a1a80e00caed2c4123d041f6c0a62f0c4f883caefe00b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9d372ab53cdb37c090a1a80e00caed2c4123d041f6c0a62f0c4f883caefe00b","first_computed_at":"2026-05-26T01:03:32.028733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:32.028733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PU95VcPrzwe5z9F/NfyxbUAiGmqdzYDAQmMdyn4gfAR0O7FD6xfSeUEN8rmnQEq5m1sE43xiU6DLAiIzuk+wDg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:32.029610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.03460","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9393920eaf867e3c4a0a798ae0af20adad4bc496ebe4c5760cd008887e03f0d","sha256:94020ac77b9d7f799c11b785eaa3113c46cb1143bb50cd576dc7294f6f3dc13c"],"state_sha256":"3e297e5e4e0d0a069a626b3a08bf9474ffa7adbd3977078e566fd998a352f7cf"}