{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SK6EC224EO4N74XZHKSOAVPZQH","short_pith_number":"pith:SK6EC224","canonical_record":{"source":{"id":"2604.16922","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T09:10:21Z","cross_cats_sorted":[],"title_canon_sha256":"28425f189c0dac27a0f1cbfee7fb5b2aba1af890fcbab145fdfd7495df9e9222","abstract_canon_sha256":"c077c838ee490856f5b786246d766906b015ef6e03682ba9247393069c0a7ddb"},"schema_version":"1.0"},"canonical_sha256":"92bc416b5c23b8dff2f93aa4e055f981c6b1a061bd7b7804ca405ea51ac2bfb7","source":{"kind":"arxiv","id":"2604.16922","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.16922","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.16922v3","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.16922","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"SK6EC224EO4N","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"SK6EC224EO4N74XZ","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"SK6EC224","created_at":"2026-06-01T01:02:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SK6EC224EO4N74XZHKSOAVPZQH","target":"record","payload":{"canonical_record":{"source":{"id":"2604.16922","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T09:10:21Z","cross_cats_sorted":[],"title_canon_sha256":"28425f189c0dac27a0f1cbfee7fb5b2aba1af890fcbab145fdfd7495df9e9222","abstract_canon_sha256":"c077c838ee490856f5b786246d766906b015ef6e03682ba9247393069c0a7ddb"},"schema_version":"1.0"},"canonical_sha256":"92bc416b5c23b8dff2f93aa4e055f981c6b1a061bd7b7804ca405ea51ac2bfb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:39.784771Z","signature_b64":"oT8sIX30yUdtX9J9nsUIbCv+5Y14ro7tcicQSsHDrAys4qaxZcToG6I0hYrk8d+16ABv74zns3F98mi3qt9sAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92bc416b5c23b8dff2f93aa4e055f981c6b1a061bd7b7804ca405ea51ac2bfb7","last_reissued_at":"2026-06-01T01:02:39.784138Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:39.784138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.16922","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NgPi2m3etmdTiD3Mmfzo5hrdEjId/GRb7LBTFkkGfKTCeYqODvgp0CF0TMxMpXZZh69iq+oZcIFgXpsL3tTWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T02:32:24.525114Z"},"content_sha256":"62c3f7afdcb8fb566131a26c6c0fe7456d4bdde81e4d5031ced93f5abeb0bd82","schema_version":"1.0","event_id":"sha256:62c3f7afdcb8fb566131a26c6c0fe7456d4bdde81e4d5031ced93f5abeb0bd82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SK6EC224EO4N74XZHKSOAVPZQH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ClimAgent turns LLMs into agents that run full climate science analyses by linking tools with structured reasoning.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hao Liu, Hao Wang, Jindong Han, Wei Fan","submitted_at":"2026-04-18T09:10:21Z","abstract_excerpt":"Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q&A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a unified tool-use environment combined with rigorous reasoning protocols can successfully handle the intricate physical constraints and data-driven nature of professional climate science without oversimplifying real-world challenges.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ClimAgent is an LLM-agent system for autonomous climate research that outperforms standard LLMs by 40.21% on the new ClimaBench benchmark in solution rigorousness and practicality.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ClimAgent turns LLMs into agents that run full climate science analyses by linking tools with structured reasoning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2889fd5649bfb7a3878aae715713aa339d39149439ae94160c2e0de20da0f188"},"source":{"id":"2604.16922","kind":"arxiv","version":3},"verdict":{"id":"1705405c-4696-4372-a3fa-fd9ccaecce30","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T07:27:18.916640Z","strongest_claim":"Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality.","one_line_summary":"ClimAgent is an LLM-agent system for autonomous climate research that outperforms standard LLMs by 40.21% on the new ClimaBench benchmark in solution rigorousness and practicality.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a unified tool-use environment combined with rigorous reasoning protocols can successfully handle the intricate physical constraints and data-driven nature of professional climate science without oversimplifying real-world challenges.","pith_extraction_headline":"ClimAgent turns LLMs into agents that run full climate science analyses by linking tools with structured reasoning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.16922/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":"1705405c-4696-4372-a3fa-fd9ccaecce30"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vq1AX15sykwS3jb7iiSpKb2FSg5mrsSprdU/VJFwjqTyfUi7ajNjWHQ0V+yooymHi5h1Ph8Io7WNiNANWZP5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T02:32:24.525670Z"},"content_sha256":"8a2e77492987eec69e8d5a6fda9cab863cd1eef56006f5226fe2b2bde1741730","schema_version":"1.0","event_id":"sha256:8a2e77492987eec69e8d5a6fda9cab863cd1eef56006f5226fe2b2bde1741730"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SK6EC224EO4N74XZHKSOAVPZQH/bundle.json","state_url":"https://pith.science/pith/SK6EC224EO4N74XZHKSOAVPZQH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SK6EC224EO4N74XZHKSOAVPZQH/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":"2026-06-06T02:32:24Z","links":{"resolver":"https://pith.science/pith/SK6EC224EO4N74XZHKSOAVPZQH","bundle":"https://pith.science/pith/SK6EC224EO4N74XZHKSOAVPZQH/bundle.json","state":"https://pith.science/pith/SK6EC224EO4N74XZHKSOAVPZQH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SK6EC224EO4N74XZHKSOAVPZQH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SK6EC224EO4N74XZHKSOAVPZQH","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":"c077c838ee490856f5b786246d766906b015ef6e03682ba9247393069c0a7ddb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T09:10:21Z","title_canon_sha256":"28425f189c0dac27a0f1cbfee7fb5b2aba1af890fcbab145fdfd7495df9e9222"},"schema_version":"1.0","source":{"id":"2604.16922","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.16922","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.16922v3","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.16922","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"SK6EC224EO4N","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"SK6EC224EO4N74XZ","created_at":"2026-06-01T01:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"SK6EC224","created_at":"2026-06-01T01:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:8a2e77492987eec69e8d5a6fda9cab863cd1eef56006f5226fe2b2bde1741730","target":"graph","created_at":"2026-06-01T01:02:39Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a unified tool-use environment combined with rigorous reasoning protocols can successfully handle the intricate physical constraints and data-driven nature of professional climate science without oversimplifying real-world challenges."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ClimAgent is an LLM-agent system for autonomous climate research that outperforms standard LLMs by 40.21% on the new ClimaBench benchmark in solution rigorousness and practicality."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ClimAgent turns LLMs into agents that run full climate science analyses by linking tools with structured reasoning."}],"snapshot_sha256":"2889fd5649bfb7a3878aae715713aa339d39149439ae94160c2e0de20da0f188"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.16922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of analytical tools have created significant bottlenecks, constraining scientific discovery to fragmented and labor-intensive workflows. While the emergence Large Language Models (LLMs) offers a transformative paradigm to scale scientific expertise, existing explorations remain largely confined to simple Question-Answering (Q&A) tasks. These approaches often oversimplify real-world challenges, neglecting the intricate physical constraints and the data-d","authors_text":"Hao Liu, Hao Wang, Jindong Han, Wei Fan","cross_cats":[],"headline":"ClimAgent turns LLMs into agents that run full climate science analyses by linking tools with structured reasoning.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T09:10:21Z","title":"ClimAgent: LLM as Agents for Autonomous Open-ended Climate Science Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.16922","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T07:27:18.916640Z","id":"1705405c-4696-4372-a3fa-fd9ccaecce30","model_set":{"reader":"grok-4.3"},"one_line_summary":"ClimAgent is an LLM-agent system for autonomous climate research that outperforms standard LLMs by 40.21% on the new ClimaBench benchmark in solution rigorousness and practicality.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ClimAgent turns LLMs into agents that run full climate science analyses by linking tools with structured reasoning.","strongest_claim":"Experiments on ClimaBench demonstrate that ClimAgent significantly outperforms state-of-the-art baselines, achieving a 40.21% improvement over original LLM solutions in solution rigorousness and practicality.","weakest_assumption":"That a unified tool-use environment combined with rigorous reasoning protocols can successfully handle the intricate physical constraints and data-driven nature of professional climate science without oversimplifying real-world challenges."}},"verdict_id":"1705405c-4696-4372-a3fa-fd9ccaecce30"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:62c3f7afdcb8fb566131a26c6c0fe7456d4bdde81e4d5031ced93f5abeb0bd82","target":"record","created_at":"2026-06-01T01:02:39Z","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":"c077c838ee490856f5b786246d766906b015ef6e03682ba9247393069c0a7ddb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T09:10:21Z","title_canon_sha256":"28425f189c0dac27a0f1cbfee7fb5b2aba1af890fcbab145fdfd7495df9e9222"},"schema_version":"1.0","source":{"id":"2604.16922","kind":"arxiv","version":3}},"canonical_sha256":"92bc416b5c23b8dff2f93aa4e055f981c6b1a061bd7b7804ca405ea51ac2bfb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92bc416b5c23b8dff2f93aa4e055f981c6b1a061bd7b7804ca405ea51ac2bfb7","first_computed_at":"2026-06-01T01:02:39.784138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:39.784138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oT8sIX30yUdtX9J9nsUIbCv+5Y14ro7tcicQSsHDrAys4qaxZcToG6I0hYrk8d+16ABv74zns3F98mi3qt9sAQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:39.784771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.16922","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62c3f7afdcb8fb566131a26c6c0fe7456d4bdde81e4d5031ced93f5abeb0bd82","sha256:8a2e77492987eec69e8d5a6fda9cab863cd1eef56006f5226fe2b2bde1741730"],"state_sha256":"03dc0c361487172fdbafe5a40b268a1b54d6fde6e256c78daec3550de049b8b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZHqWLhGyeAznP23IgY0VIceh1ntoWwU2dh+gTHtTgPh9XFGMEVNdkmZXNzGtqQD8nL1dGNjbGyUBQ6NO/k48DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T02:32:24.529519Z","bundle_sha256":"1c29478ee308bfdf2c8b8f030c220eba2f3dcd43b211d0a0a9fa97fd5942fd2e"}}