{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AXDZOGMBDJI2SKYMOZCHR6FSEB","short_pith_number":"pith:AXDZOGMB","canonical_record":{"source":{"id":"2605.07323","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T06:29:58Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SC"],"title_canon_sha256":"7580c74ed1498efb265b400a3807847f45252c8e00d49ce57206d5d316b241ca","abstract_canon_sha256":"d9bae209f8592d32bcaff65c9b6369eabdd71a817624ceaac419e3b943de7b4b"},"schema_version":"1.0"},"canonical_sha256":"05c79719811a51a92b0c764478f8b22067cb8bab35a8ceed20b7c82d8aca710c","source":{"kind":"arxiv","id":"2605.07323","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07323","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07323v2","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07323","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"AXDZOGMBDJI2","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"AXDZOGMBDJI2SKYM","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"AXDZOGMB","created_at":"2026-07-16T01:22:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AXDZOGMBDJI2SKYMOZCHR6FSEB","target":"record","payload":{"canonical_record":{"source":{"id":"2605.07323","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T06:29:58Z","cross_cats_sorted":["cs.LG","cs.NE","cs.SC"],"title_canon_sha256":"7580c74ed1498efb265b400a3807847f45252c8e00d49ce57206d5d316b241ca","abstract_canon_sha256":"d9bae209f8592d32bcaff65c9b6369eabdd71a817624ceaac419e3b943de7b4b"},"schema_version":"1.0"},"canonical_sha256":"05c79719811a51a92b0c764478f8b22067cb8bab35a8ceed20b7c82d8aca710c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:41.122644Z","signature_b64":"wzWvaiHWvska75N5s8AnHeqjBWefdm/0to0FWDhdSiUa+OHxA3ykX1JOVArmsR519f4d5B7raJtJWmRudwTIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05c79719811a51a92b0c764478f8b22067cb8bab35a8ceed20b7c82d8aca710c","last_reissued_at":"2026-07-16T01:22:41.121598Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:41.121598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.07323","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T01:22:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cKyWTmx+AIy9ySAMu83pj5I1LyXXfC0O8sM4RcppCf7oGss0OIqc977P9Dw2aiOCmc1RTDOn3qBnvK1EJVsfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:01:54.896389Z"},"content_sha256":"0e88d3c04de87fe4ccffdea06423dea954c3fcd89194e3deb38691ead4e5ab1f","schema_version":"1.0","event_id":"sha256:0e88d3c04de87fe4ccffdea06423dea954c3fcd89194e3deb38691ead4e5ab1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AXDZOGMBDJI2SKYMOZCHR6FSEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"DoLQ recovers true ordinary differential equations from data more successfully by using an LLM to check both numerical fit and physical plausibility.","cross_cats":["cs.LG","cs.NE","cs.SC"],"primary_cat":"cs.AI","authors_text":"Bong Gyun Shin, Jae Yong Lee, Sum Kyun Song","submitted_at":"2026-05-08T06:29:58Z","abstract_excerpt":"Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regression approaches rely primarily on quantitative metrics; however, real-world differential equation modeling also requires incorporating domain knowledge to ensure physical plausibility. To address this gap, we propose DoLQ, a method for discovering ordinary differential equations with LLM-based qualitative and quantitative evaluation. DoLQ employs a multi-agent architecture: a Sampler Agent proposes dynamic system candidates, a Parameter Optimiz"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on multi-dimensional ordinary differential equation benchmarks demonstrate that DoLQ achieves superior performance compared to existing methods, not only attaining higher success rates but also more accurately recovering the correct symbolic terms of ground truth equations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The LLM-based Scientist Agent can reliably perform qualitative evaluation of physical plausibility and domain knowledge without introducing hallucinations, training-data biases, or inconsistent judgments across runs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DoLQ employs a sampler agent, parameter optimizer, and LLM-based scientist agent to iteratively propose, refine, and evaluate ODE candidates, yielding higher success rates and better symbolic term recovery than prior symbolic regression methods on multi-dimensional benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"DoLQ recovers true ordinary differential equations from data more successfully by using an LLM to check both numerical fit and physical plausibility.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c188ee3f7b5c05c4101a2fa730069aedbb01e8dffbacd776d9935009d4d8ced0"},"source":{"id":"2605.07323","kind":"arxiv","version":2},"verdict":{"id":"2aeba9af-c9d6-4e62-92dd-68f78d830e40","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T00:59:45.676016Z","strongest_claim":"Experiments on multi-dimensional ordinary differential equation benchmarks demonstrate that DoLQ achieves superior performance compared to existing methods, not only attaining higher success rates but also more accurately recovering the correct symbolic terms of ground truth equations.","one_line_summary":"DoLQ employs a sampler agent, parameter optimizer, and LLM-based scientist agent to iteratively propose, refine, and evaluate ODE candidates, yielding higher success rates and better symbolic term recovery than prior symbolic regression methods on multi-dimensional benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The LLM-based Scientist Agent can reliably perform qualitative evaluation of physical plausibility and domain knowledge without introducing hallucinations, training-data biases, or inconsistent judgments across runs.","pith_extraction_headline":"DoLQ recovers true ordinary differential equations from data more successfully by using an LLM to check both numerical fit and physical plausibility."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07323/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T11:02:03.283253Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-20T06:33:39.282041Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:01:18.858095Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:53:41.300652Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"003281981657321ce3f95ceb7ff104203817ea3f384de63d0979aa02ba33a176"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"260625824d0f08c3dcf168c13942e23dd08a82b2dcecb21e23f736aae8c6b23d"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2aeba9af-c9d6-4e62-92dd-68f78d830e40"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T01:22:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jjdonfcT/czDxcYj4VNYnbaAYMVBR5RwCXInbhCz0k1cz6W1h3VHh+hZjhRFWzuZkrl+Dhu9UK1PSG0qnO8JBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:01:54.897245Z"},"content_sha256":"2304d6308c2b147430259f710cc7cb6bb96098ca240997a5b4771a83ad24593f","schema_version":"1.0","event_id":"sha256:2304d6308c2b147430259f710cc7cb6bb96098ca240997a5b4771a83ad24593f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AXDZOGMBDJI2SKYMOZCHR6FSEB/bundle.json","state_url":"https://pith.science/pith/AXDZOGMBDJI2SKYMOZCHR6FSEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AXDZOGMBDJI2SKYMOZCHR6FSEB/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":"2026-08-12T22:01:54Z","links":{"resolver":"https://pith.science/pith/AXDZOGMBDJI2SKYMOZCHR6FSEB","bundle":"https://pith.science/pith/AXDZOGMBDJI2SKYMOZCHR6FSEB/bundle.json","state":"https://pith.science/pith/AXDZOGMBDJI2SKYMOZCHR6FSEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AXDZOGMBDJI2SKYMOZCHR6FSEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AXDZOGMBDJI2SKYMOZCHR6FSEB","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":"d9bae209f8592d32bcaff65c9b6369eabdd71a817624ceaac419e3b943de7b4b","cross_cats_sorted":["cs.LG","cs.NE","cs.SC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T06:29:58Z","title_canon_sha256":"7580c74ed1498efb265b400a3807847f45252c8e00d49ce57206d5d316b241ca"},"schema_version":"1.0","source":{"id":"2605.07323","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07323","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07323v2","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07323","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"AXDZOGMBDJI2","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"AXDZOGMBDJI2SKYM","created_at":"2026-07-16T01:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"AXDZOGMB","created_at":"2026-07-16T01:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:2304d6308c2b147430259f710cc7cb6bb96098ca240997a5b4771a83ad24593f","target":"graph","created_at":"2026-07-16T01:22:41Z","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 multi-dimensional ordinary differential equation benchmarks demonstrate that DoLQ achieves superior performance compared to existing methods, not only attaining higher success rates but also more accurately recovering the correct symbolic terms of ground truth equations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The LLM-based Scientist Agent can reliably perform qualitative evaluation of physical plausibility and domain knowledge without introducing hallucinations, training-data biases, or inconsistent judgments across runs."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DoLQ employs a sampler agent, parameter optimizer, and LLM-based scientist agent to iteratively propose, refine, and evaluate ODE candidates, yielding higher success rates and better symbolic term recovery than prior symbolic regression methods on multi-dimensional benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DoLQ recovers true ordinary differential equations from data more successfully by using an LLM to check both numerical fit and physical plausibility."}],"snapshot_sha256":"c188ee3f7b5c05c4101a2fa730069aedbb01e8dffbacd776d9935009d4d8ced0"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"260625824d0f08c3dcf168c13942e23dd08a82b2dcecb21e23f736aae8c6b23d"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T11:02:03.283253Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T06:33:39.282041Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T17:01:18.858095Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T11:53:41.300652Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.07323/integrity.json","findings":[],"snapshot_sha256":"003281981657321ce3f95ceb7ff104203817ea3f384de63d0979aa02ba33a176","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discovering governing differential equations from observational data is a fundamental challenge in scientific machine learning. Existing symbolic regression approaches rely primarily on quantitative metrics; however, real-world differential equation modeling also requires incorporating domain knowledge to ensure physical plausibility. To address this gap, we propose DoLQ, a method for discovering ordinary differential equations with LLM-based qualitative and quantitative evaluation. DoLQ employs a multi-agent architecture: a Sampler Agent proposes dynamic system candidates, a Parameter Optimiz","authors_text":"Bong Gyun Shin, Jae Yong Lee, Sum Kyun Song","cross_cats":["cs.LG","cs.NE","cs.SC"],"headline":"DoLQ recovers true ordinary differential equations from data more successfully by using an LLM to check both numerical fit and physical plausibility.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T06:29:58Z","title":"Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.07323","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T00:59:45.676016Z","id":"2aeba9af-c9d6-4e62-92dd-68f78d830e40","model_set":{"reader":"grok-4.3"},"one_line_summary":"DoLQ employs a sampler agent, parameter optimizer, and LLM-based scientist agent to iteratively propose, refine, and evaluate ODE candidates, yielding higher success rates and better symbolic term recovery than prior symbolic regression methods on multi-dimensional benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"DoLQ recovers true ordinary differential equations from data more successfully by using an LLM to check both numerical fit and physical plausibility.","strongest_claim":"Experiments on multi-dimensional ordinary differential equation benchmarks demonstrate that DoLQ achieves superior performance compared to existing methods, not only attaining higher success rates but also more accurately recovering the correct symbolic terms of ground truth equations.","weakest_assumption":"The LLM-based Scientist Agent can reliably perform qualitative evaluation of physical plausibility and domain knowledge without introducing hallucinations, training-data biases, or inconsistent judgments across runs."}},"verdict_id":"2aeba9af-c9d6-4e62-92dd-68f78d830e40"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0e88d3c04de87fe4ccffdea06423dea954c3fcd89194e3deb38691ead4e5ab1f","target":"record","created_at":"2026-07-16T01:22:41Z","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":"d9bae209f8592d32bcaff65c9b6369eabdd71a817624ceaac419e3b943de7b4b","cross_cats_sorted":["cs.LG","cs.NE","cs.SC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-08T06:29:58Z","title_canon_sha256":"7580c74ed1498efb265b400a3807847f45252c8e00d49ce57206d5d316b241ca"},"schema_version":"1.0","source":{"id":"2605.07323","kind":"arxiv","version":2}},"canonical_sha256":"05c79719811a51a92b0c764478f8b22067cb8bab35a8ceed20b7c82d8aca710c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05c79719811a51a92b0c764478f8b22067cb8bab35a8ceed20b7c82d8aca710c","first_computed_at":"2026-07-16T01:22:41.121598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:41.121598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wzWvaiHWvska75N5s8AnHeqjBWefdm/0to0FWDhdSiUa+OHxA3ykX1JOVArmsR519f4d5B7raJtJWmRudwTIAw==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:41.122644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.07323","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e88d3c04de87fe4ccffdea06423dea954c3fcd89194e3deb38691ead4e5ab1f","sha256:2304d6308c2b147430259f710cc7cb6bb96098ca240997a5b4771a83ad24593f"],"state_sha256":"3fe6573e6b36a1884e13e0d4a931423fde2fd0439f91ea55c86c1571d554f200"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GlFXi7atK2iQ4NePAhDyfrGYj6h84mmKXeEktoOYZ/VSYAAVC+ScXh2EzxEmGDOuAA/6mnO5RXz4R4XKIJ6AAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:01:54.902788Z","bundle_sha256":"807a68f81531dec52f7e01991f3cd71c3a149c8163375f7dd1d4ddfbd1a617a1"}}