{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CVJKPVRCG5VRVY5ALSMGBYHWGS","short_pith_number":"pith:CVJKPVRC","canonical_record":{"source":{"id":"2607.18271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T21:20:24Z","cross_cats_sorted":[],"title_canon_sha256":"9890fba2c3e01fb4a59ea7d88585c7ad3047b51036056e17da7278b66479583c","abstract_canon_sha256":"8e63a01bc02fe4e2d31675fbf2bc4ac186a305bea9b7cfb5b8fe14e133865a89"},"schema_version":"1.0"},"canonical_sha256":"1552a7d622376b1ae3a05c9860e0f63481b9481c47b70bb8c7e33b31d5278efe","source":{"kind":"arxiv","id":"2607.18271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18271","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18271v1","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18271","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"CVJKPVRCG5VR","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"CVJKPVRCG5VRVY5A","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"CVJKPVRC","created_at":"2026-07-22T00:22:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CVJKPVRCG5VRVY5ALSMGBYHWGS","target":"record","payload":{"canonical_record":{"source":{"id":"2607.18271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T21:20:24Z","cross_cats_sorted":[],"title_canon_sha256":"9890fba2c3e01fb4a59ea7d88585c7ad3047b51036056e17da7278b66479583c","abstract_canon_sha256":"8e63a01bc02fe4e2d31675fbf2bc4ac186a305bea9b7cfb5b8fe14e133865a89"},"schema_version":"1.0"},"canonical_sha256":"1552a7d622376b1ae3a05c9860e0f63481b9481c47b70bb8c7e33b31d5278efe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:39.533259Z","signature_b64":"5GrZaysZh0z8bs1jXHD0w5YOUhNfiUGiFnTB2JDziP5TylMx4WgxtM3ir4fdUr/6otCo7dL/ZLymdz14AL7gBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1552a7d622376b1ae3a05c9860e0f63481b9481c47b70bb8c7e33b31d5278efe","last_reissued_at":"2026-07-22T00:22:39.532443Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:39.532443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.18271","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":"2026-07-22T00:22:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hpjkzNATE5r+AbOHMbdcuxnNcsjkEGbftH0TybPz+GnOraRwCFifszB8KsO0cAor41wxJTgACDgtNVv1CGWsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:21:35.701727Z"},"content_sha256":"1551d5fb53655a2aad20c22ec4404f959c8e01aff42f08d5842b9e82a991de06","schema_version":"1.0","event_id":"sha256:1551d5fb53655a2aad20c22ec4404f959c8e01aff42f08d5842b9e82a991de06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CVJKPVRCG5VRVY5ALSMGBYHWGS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using LLMs for Explainable, Data-Driven Insight Generation from Time Series","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gustavo Sato dos Santos, Michael Benedikt, Ria Mundhra","submitted_at":"2026-06-04T21:20:24Z","abstract_excerpt":"Time series forecasts are widely used in decision-critical domains, where they are rarely consumed without accompanying explanations. Producing such explanations is usually a manual and costly process, and attempts to automate it using large language models often suffer from hallucination when applied to temporal data. We propose a domain-agnostic framework for grounded natural language explanation generation for time series forecasts, illustrated in Figure 1. The framework consists of three components: (i) extraction of structured explanatory factors from historical analyst-written explanatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18271","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/2607.18271/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":"2026-07-22T00:22:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s6fjzc55oWP/qKZgZ9G/U0U6nKvS7MEu5cwArwbg2mD1huzhVVHNMYiliUS8EBnOnRuFr9kUxJKEqZEgb0n2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:21:35.702387Z"},"content_sha256":"bb8fa71cf316aa563e605a8ed56d9014dabff5d1de47303f7faca669fea996e2","schema_version":"1.0","event_id":"sha256:bb8fa71cf316aa563e605a8ed56d9014dabff5d1de47303f7faca669fea996e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CVJKPVRCG5VRVY5ALSMGBYHWGS/bundle.json","state_url":"https://pith.science/pith/CVJKPVRCG5VRVY5ALSMGBYHWGS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CVJKPVRCG5VRVY5ALSMGBYHWGS/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":"2026-08-05T11:21:35Z","links":{"resolver":"https://pith.science/pith/CVJKPVRCG5VRVY5ALSMGBYHWGS","bundle":"https://pith.science/pith/CVJKPVRCG5VRVY5ALSMGBYHWGS/bundle.json","state":"https://pith.science/pith/CVJKPVRCG5VRVY5ALSMGBYHWGS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CVJKPVRCG5VRVY5ALSMGBYHWGS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CVJKPVRCG5VRVY5ALSMGBYHWGS","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":"8e63a01bc02fe4e2d31675fbf2bc4ac186a305bea9b7cfb5b8fe14e133865a89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T21:20:24Z","title_canon_sha256":"9890fba2c3e01fb4a59ea7d88585c7ad3047b51036056e17da7278b66479583c"},"schema_version":"1.0","source":{"id":"2607.18271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18271","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18271v1","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18271","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_12","alias_value":"CVJKPVRCG5VR","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_16","alias_value":"CVJKPVRCG5VRVY5A","created_at":"2026-07-22T00:22:39Z"},{"alias_kind":"pith_short_8","alias_value":"CVJKPVRC","created_at":"2026-07-22T00:22:39Z"}],"graph_snapshots":[{"event_id":"sha256:bb8fa71cf316aa563e605a8ed56d9014dabff5d1de47303f7faca669fea996e2","target":"graph","created_at":"2026-07-22T00:22:39Z","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/2607.18271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Time series forecasts are widely used in decision-critical domains, where they are rarely consumed without accompanying explanations. Producing such explanations is usually a manual and costly process, and attempts to automate it using large language models often suffer from hallucination when applied to temporal data. We propose a domain-agnostic framework for grounded natural language explanation generation for time series forecasts, illustrated in Figure 1. The framework consists of three components: (i) extraction of structured explanatory factors from historical analyst-written explanatio","authors_text":"Gustavo Sato dos Santos, Michael Benedikt, Ria Mundhra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T21:20:24Z","title":"Using LLMs for Explainable, Data-Driven Insight Generation from Time Series"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18271","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":"sha256:1551d5fb53655a2aad20c22ec4404f959c8e01aff42f08d5842b9e82a991de06","target":"record","created_at":"2026-07-22T00:22:39Z","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":"8e63a01bc02fe4e2d31675fbf2bc4ac186a305bea9b7cfb5b8fe14e133865a89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-04T21:20:24Z","title_canon_sha256":"9890fba2c3e01fb4a59ea7d88585c7ad3047b51036056e17da7278b66479583c"},"schema_version":"1.0","source":{"id":"2607.18271","kind":"arxiv","version":1}},"canonical_sha256":"1552a7d622376b1ae3a05c9860e0f63481b9481c47b70bb8c7e33b31d5278efe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1552a7d622376b1ae3a05c9860e0f63481b9481c47b70bb8c7e33b31d5278efe","first_computed_at":"2026-07-22T00:22:39.532443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T00:22:39.532443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5GrZaysZh0z8bs1jXHD0w5YOUhNfiUGiFnTB2JDziP5TylMx4WgxtM3ir4fdUr/6otCo7dL/ZLymdz14AL7gBA==","signature_status":"signed_v1","signed_at":"2026-07-22T00:22:39.533259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1551d5fb53655a2aad20c22ec4404f959c8e01aff42f08d5842b9e82a991de06","sha256:bb8fa71cf316aa563e605a8ed56d9014dabff5d1de47303f7faca669fea996e2"],"state_sha256":"dbe7b79dfb97ffc373583c5adc488d31546387153b03e1be03cc513f50ef0102"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U0U8nJuAB6DnTVbXVG+NobMQSsd+Q6jOX13dXRjhBGEwPB9UvMAQP00u8HXaNngTnxeHr8zRQi9kI0nLhCxfBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:21:35.707860Z","bundle_sha256":"32aeccd5c72fd7760b45257a6cded44a7f351f91dcb145be838fba6edd250a5e"}}