{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IG5IQME5CQFON27H6AM6OHY7TN","short_pith_number":"pith:IG5IQME5","canonical_record":{"source":{"id":"2606.01498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T23:34:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a304938299da7a5d758e5bcdf8a56ac4eaa26839cf4115624cac40f11cc9717e","abstract_canon_sha256":"8771734138e5d0800f1c127cfbcf1191f60b050cbb984a5ec911d382f49c4fd3"},"schema_version":"1.0"},"canonical_sha256":"41ba88309d140ae6ebe7f019e71f1f9b478f6cf558907cb1dba1e54a08e1a4d4","source":{"kind":"arxiv","id":"2606.01498","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01498","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01498v1","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01498","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"IG5IQME5CQFO","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"IG5IQME5CQFON27H","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"IG5IQME5","created_at":"2026-06-02T02:04:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IG5IQME5CQFON27H6AM6OHY7TN","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T23:34:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a304938299da7a5d758e5bcdf8a56ac4eaa26839cf4115624cac40f11cc9717e","abstract_canon_sha256":"8771734138e5d0800f1c127cfbcf1191f60b050cbb984a5ec911d382f49c4fd3"},"schema_version":"1.0"},"canonical_sha256":"41ba88309d140ae6ebe7f019e71f1f9b478f6cf558907cb1dba1e54a08e1a4d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:34.850270Z","signature_b64":"mh3tl3vF2VpAkzyeNgWqywfJwxQUkAN4eHX5/0laeCvir3X8NI5MILsH0makhhyZAIB6J4rDp0osC4RfFtCdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41ba88309d140ae6ebe7f019e71f1f9b478f6cf558907cb1dba1e54a08e1a4d4","last_reissued_at":"2026-06-02T02:04:34.849861Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:34.849861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01498","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":"2026-06-02T02:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csTkhDeGCqxwgq5BCH5s4Qziyzrw7lkTKq3HZMHWSIdjYyg+VMwcmx/S6U3FeNSttk6FWuaZHVe9/wCjdK6PDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T15:51:16.468636Z"},"content_sha256":"ecb0eca20c1569dde294985fddd906ad233435a60f8f80c75f1abe9e8019766b","schema_version":"1.0","event_id":"sha256:ecb0eca20c1569dde294985fddd906ad233435a60f8f80c75f1abe9e8019766b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IG5IQME5CQFON27H6AM6OHY7TN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anna Vettoruzzo, Joaquin Vanschoren, Ming Jin, Qingren Yao, Qingsong Wen, Stefan Zohren, Yaxuan Kong, Yichen Li, Yilei Shao, Yuqi Nie","submitted_at":"2026-05-31T23:34:35Z","abstract_excerpt":"Time series data inform critical decisions across many real-world domains. While large language model (LLM) agents can analyze data through natural language and tools, it remains unclear whether they can conduct reliable time series analysis across multi-turn conversations. Existing benchmarks focus on single-step tasks such as forecasting and anomaly detection, overlooking practical workflows where user goals evolve, agents must build on prior analyses, and conclusions emerge from accumulated evidence. In this work, we introduce TimeSage-MT, a multi-turn benchmark for agentic time series reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01498","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/2606.01498/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":"2026-06-02T02:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yw5qLLGtup6Y0i62XT7ghd9Pu9AVrxC793p66SQf+dARqTWtNPylID44kMrr8tZhEmvAjrWVWJLtDS5HzxiXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T15:51:16.469343Z"},"content_sha256":"2d5568785e9082f8dfcd44e83bb8131fea9fe1e6256af20d9399d5e8f0b99c25","schema_version":"1.0","event_id":"sha256:2d5568785e9082f8dfcd44e83bb8131fea9fe1e6256af20d9399d5e8f0b99c25"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IG5IQME5CQFON27H6AM6OHY7TN/bundle.json","state_url":"https://pith.science/pith/IG5IQME5CQFON27H6AM6OHY7TN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IG5IQME5CQFON27H6AM6OHY7TN/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":"2026-06-03T15:51:16Z","links":{"resolver":"https://pith.science/pith/IG5IQME5CQFON27H6AM6OHY7TN","bundle":"https://pith.science/pith/IG5IQME5CQFON27H6AM6OHY7TN/bundle.json","state":"https://pith.science/pith/IG5IQME5CQFON27H6AM6OHY7TN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IG5IQME5CQFON27H6AM6OHY7TN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IG5IQME5CQFON27H6AM6OHY7TN","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":"8771734138e5d0800f1c127cfbcf1191f60b050cbb984a5ec911d382f49c4fd3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T23:34:35Z","title_canon_sha256":"a304938299da7a5d758e5bcdf8a56ac4eaa26839cf4115624cac40f11cc9717e"},"schema_version":"1.0","source":{"id":"2606.01498","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01498","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01498v1","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01498","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"IG5IQME5CQFO","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"IG5IQME5CQFON27H","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"IG5IQME5","created_at":"2026-06-02T02:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:2d5568785e9082f8dfcd44e83bb8131fea9fe1e6256af20d9399d5e8f0b99c25","target":"graph","created_at":"2026-06-02T02:04:34Z","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/2606.01498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Time series data inform critical decisions across many real-world domains. While large language model (LLM) agents can analyze data through natural language and tools, it remains unclear whether they can conduct reliable time series analysis across multi-turn conversations. Existing benchmarks focus on single-step tasks such as forecasting and anomaly detection, overlooking practical workflows where user goals evolve, agents must build on prior analyses, and conclusions emerge from accumulated evidence. In this work, we introduce TimeSage-MT, a multi-turn benchmark for agentic time series reas","authors_text":"Anna Vettoruzzo, Joaquin Vanschoren, Ming Jin, Qingren Yao, Qingsong Wen, Stefan Zohren, Yaxuan Kong, Yichen Li, Yilei Shao, Yuqi Nie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T23:34:35Z","title":"TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01498","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:ecb0eca20c1569dde294985fddd906ad233435a60f8f80c75f1abe9e8019766b","target":"record","created_at":"2026-06-02T02:04:34Z","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":"8771734138e5d0800f1c127cfbcf1191f60b050cbb984a5ec911d382f49c4fd3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T23:34:35Z","title_canon_sha256":"a304938299da7a5d758e5bcdf8a56ac4eaa26839cf4115624cac40f11cc9717e"},"schema_version":"1.0","source":{"id":"2606.01498","kind":"arxiv","version":1}},"canonical_sha256":"41ba88309d140ae6ebe7f019e71f1f9b478f6cf558907cb1dba1e54a08e1a4d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41ba88309d140ae6ebe7f019e71f1f9b478f6cf558907cb1dba1e54a08e1a4d4","first_computed_at":"2026-06-02T02:04:34.849861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:34.849861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mh3tl3vF2VpAkzyeNgWqywfJwxQUkAN4eHX5/0laeCvir3X8NI5MILsH0makhhyZAIB6J4rDp0osC4RfFtCdAA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:34.850270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01498","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecb0eca20c1569dde294985fddd906ad233435a60f8f80c75f1abe9e8019766b","sha256:2d5568785e9082f8dfcd44e83bb8131fea9fe1e6256af20d9399d5e8f0b99c25"],"state_sha256":"967b82babd4f71b9a52ff797ab7d4fe465779e05a1457d07def372031288a7e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8gvV4OsgTP2FykhaKknqcemwTrNioSXavgFB4dXSLYImfETG+kr2PTPhLyCGMvSSybKFevldEF4bBgOiKzaVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T15:51:16.472589Z","bundle_sha256":"b9b2722c8ebcefff1e27bdce424cef73d6ae4253a50cb4768e119217b9857308"}}