{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VPFP4QF4XW7RPODNKVO7TNGZAU","short_pith_number":"pith:VPFP4QF4","canonical_record":{"source":{"id":"2402.17453","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T12:26:07Z","cross_cats_sorted":[],"title_canon_sha256":"680bc9eb0f8924a29a5d4c8993cd6df2a3e5fd8460c25486a8109ee73c679197","abstract_canon_sha256":"bfae4087148714909d01e983c3b1f8ba2a3ebf407b01dde6cf6aa1605f4770ac"},"schema_version":"1.0"},"canonical_sha256":"abcafe40bcbdbf17b86d555df9b4d9053614f1fadda8e6c49333c662955a59df","source":{"kind":"arxiv","id":"2402.17453","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17453","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17453v5","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17453","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"VPFP4QF4XW7R","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"VPFP4QF4XW7RPODN","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"VPFP4QF4","created_at":"2026-07-05T08:24:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VPFP4QF4XW7RPODNKVO7TNGZAU","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17453","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T12:26:07Z","cross_cats_sorted":[],"title_canon_sha256":"680bc9eb0f8924a29a5d4c8993cd6df2a3e5fd8460c25486a8109ee73c679197","abstract_canon_sha256":"bfae4087148714909d01e983c3b1f8ba2a3ebf407b01dde6cf6aa1605f4770ac"},"schema_version":"1.0"},"canonical_sha256":"abcafe40bcbdbf17b86d555df9b4d9053614f1fadda8e6c49333c662955a59df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:02.870060Z","signature_b64":"8SmHWuXwSj//5ZTWn9w1XWDPDaZaLgGsGY3sp63N3YLMJVaOnE+jEhaiWbt4DrULW0GA9SSjG0HaK9xKxBn7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abcafe40bcbdbf17b86d555df9b4d9053614f1fadda8e6c49333c662955a59df","last_reissued_at":"2026-07-05T08:24:02.869645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:02.869645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17453","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:24:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"do3xGaXOuUmioLYL4alSDl360u+Lp3co5xNuPHB7JGD95H2beyzx6cl1G2FUghA3MFD7O83TwmihExLqOkXUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:25:01.614004Z"},"content_sha256":"1c0d52511da6c494932ac6e98905986f745313dc7f2fcf1886a2102bc251e196","schema_version":"1.0","event_id":"sha256:1c0d52511da6c494932ac6e98905986f745313dc7f2fcf1886a2102bc251e196"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VPFP4QF4XW7RPODNKVO7TNGZAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng Deng, Hechang Chen, Jun Wang, Siyuan Guo, Yi Chang, Ying Wen","submitted_at":"2024-02-27T12:26:07Z","abstract_excerpt":"In this work, we investigate the potential of large language models (LLMs) based agents to automate data science tasks, with the goal of comprehending task requirements, then building and training the best-fit machine learning models. Despite their widespread success, existing LLM agents are hindered by generating unreasonable experiment plans within this scenario. To this end, we present DS-Agent, a novel automatic framework that harnesses LLM agent and case-based reasoning (CBR). In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17453","kind":"arxiv","version":5},"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/2402.17453/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":"2026-07-05T08:24:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iY/YUHx/vFJrbHIPKkYuu8xGJ3JC+9c/LSnb2GZ5GTcJPzYyCxNjuXoGQvS3dGz/OerL+WSg5crCXnlHRB+MAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:25:01.614657Z"},"content_sha256":"489fcdc222c12ae56920ff83f657645b2ce290ffa498e100630cd8bbcc7db0dd","schema_version":"1.0","event_id":"sha256:489fcdc222c12ae56920ff83f657645b2ce290ffa498e100630cd8bbcc7db0dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPFP4QF4XW7RPODNKVO7TNGZAU/bundle.json","state_url":"https://pith.science/pith/VPFP4QF4XW7RPODNKVO7TNGZAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPFP4QF4XW7RPODNKVO7TNGZAU/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":"2026-08-04T20:25:01Z","links":{"resolver":"https://pith.science/pith/VPFP4QF4XW7RPODNKVO7TNGZAU","bundle":"https://pith.science/pith/VPFP4QF4XW7RPODNKVO7TNGZAU/bundle.json","state":"https://pith.science/pith/VPFP4QF4XW7RPODNKVO7TNGZAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPFP4QF4XW7RPODNKVO7TNGZAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VPFP4QF4XW7RPODNKVO7TNGZAU","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":"bfae4087148714909d01e983c3b1f8ba2a3ebf407b01dde6cf6aa1605f4770ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T12:26:07Z","title_canon_sha256":"680bc9eb0f8924a29a5d4c8993cd6df2a3e5fd8460c25486a8109ee73c679197"},"schema_version":"1.0","source":{"id":"2402.17453","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17453","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17453v5","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17453","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"VPFP4QF4XW7R","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"VPFP4QF4XW7RPODN","created_at":"2026-07-05T08:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"VPFP4QF4","created_at":"2026-07-05T08:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:489fcdc222c12ae56920ff83f657645b2ce290ffa498e100630cd8bbcc7db0dd","target":"graph","created_at":"2026-07-05T08:24:02Z","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/2402.17453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we investigate the potential of large language models (LLMs) based agents to automate data science tasks, with the goal of comprehending task requirements, then building and training the best-fit machine learning models. Despite their widespread success, existing LLM agents are hindered by generating unreasonable experiment plans within this scenario. To this end, we present DS-Agent, a novel automatic framework that harnesses LLM agent and case-based reasoning (CBR). In the development stage, DS-Agent follows the CBR framework to structure an automatic iteration pipeline, which ","authors_text":"Cheng Deng, Hechang Chen, Jun Wang, Siyuan Guo, Yi Chang, Ying Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T12:26:07Z","title":"DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17453","kind":"arxiv","version":5},"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":"sha256:1c0d52511da6c494932ac6e98905986f745313dc7f2fcf1886a2102bc251e196","target":"record","created_at":"2026-07-05T08:24:02Z","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":"bfae4087148714909d01e983c3b1f8ba2a3ebf407b01dde6cf6aa1605f4770ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T12:26:07Z","title_canon_sha256":"680bc9eb0f8924a29a5d4c8993cd6df2a3e5fd8460c25486a8109ee73c679197"},"schema_version":"1.0","source":{"id":"2402.17453","kind":"arxiv","version":5}},"canonical_sha256":"abcafe40bcbdbf17b86d555df9b4d9053614f1fadda8e6c49333c662955a59df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abcafe40bcbdbf17b86d555df9b4d9053614f1fadda8e6c49333c662955a59df","first_computed_at":"2026-07-05T08:24:02.869645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:02.869645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8SmHWuXwSj//5ZTWn9w1XWDPDaZaLgGsGY3sp63N3YLMJVaOnE+jEhaiWbt4DrULW0GA9SSjG0HaK9xKxBn7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:02.870060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17453","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c0d52511da6c494932ac6e98905986f745313dc7f2fcf1886a2102bc251e196","sha256:489fcdc222c12ae56920ff83f657645b2ce290ffa498e100630cd8bbcc7db0dd"],"state_sha256":"4098cd8e274e9ec3e22227eeaaecb5d644b6dc276e9ddc448e7817e4c04309cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1lXxc4aqHVlfSa9FKuRDXbuPjer+mdFwD7VwBc6up2pxyPghSB3GZWtCANbq9jMjBilZ0H2ZfcaWtzi9C5xDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:25:01.620655Z","bundle_sha256":"3db1c9a625f4117a5f9569f5d0f478acdf67d374c008a1f4675035a93019ad9b"}}