{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GGVUHJ6VVEAS72MN6LQ34R4SOU","short_pith_number":"pith:GGVUHJ6V","canonical_record":{"source":{"id":"2607.07504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-08T15:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"d53916d16244da68aa69a3868223a2b74b5636f98028ee28876784f7db0653de","abstract_canon_sha256":"cb675665f90cfa827ebf8e7e7e79b4d1cfee8a5758ae8b715d54929f0fab2461"},"schema_version":"1.0"},"canonical_sha256":"31ab43a7d5a9012fe98df2e1be47927535179ad3e29158f504a6957e494b6040","source":{"kind":"arxiv","id":"2607.07504","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07504","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07504v1","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07504","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"GGVUHJ6VVEAS","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"GGVUHJ6VVEAS72MN","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"GGVUHJ6V","created_at":"2026-07-09T01:20:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GGVUHJ6VVEAS72MN6LQ34R4SOU","target":"record","payload":{"canonical_record":{"source":{"id":"2607.07504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-08T15:00:16Z","cross_cats_sorted":[],"title_canon_sha256":"d53916d16244da68aa69a3868223a2b74b5636f98028ee28876784f7db0653de","abstract_canon_sha256":"cb675665f90cfa827ebf8e7e7e79b4d1cfee8a5758ae8b715d54929f0fab2461"},"schema_version":"1.0"},"canonical_sha256":"31ab43a7d5a9012fe98df2e1be47927535179ad3e29158f504a6957e494b6040","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:27.472544Z","signature_b64":"1DbadlVfKQ49ryAycc5nE1yma+JfNFth9v6vWWQFXGmyZR4HYArhwr8JC+iGcbJUowJYWW/upfIDtbJlpXbgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ab43a7d5a9012fe98df2e1be47927535179ad3e29158f504a6957e494b6040","last_reissued_at":"2026-07-09T01:20:27.472099Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:27.472099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.07504","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":"2026-07-09T01:20:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jm/8j1gvgsHlun2Lrwgce7wmCu8jSMzh6bw0qqjrCwR1nN9dja/taOk/SYJEGlTfhpqFZcncyOkq3HCcS1vZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:44:44.653158Z"},"content_sha256":"18db20b3a7a43f016d8e9369bfba82910cd59876478a479dcc7d4135df6f4c56","schema_version":"1.0","event_id":"sha256:18db20b3a7a43f016d8e9369bfba82910cd59876478a479dcc7d4135df6f4c56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GGVUHJ6VVEAS72MN6LQ34R4SOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Wei-Jung Huang","submitted_at":"2026-07-08T15:00:16Z","abstract_excerpt":"Product data scientists often ask LLM-based agents to help with recurring execution tasks such as cleaning data, writing SQL, choosing statistical tests, and formatting results. Reusable skill files are meant to avoid prompting from scratch by packaging guidance for a task family. Expert-written skills can encode high-quality guidance, but writing and maintaining them across many data-science task families creates a manual bottleneck. We ask whether LLM-generated skills offer a useful low-curation alternative: do they improve performance over the task prompt alone? We test this question across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07504","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/2607.07504/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":"2026-07-09T01:20:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+VwM7giQDYv6Ae4Tcz/0v3QqAMT6yxLVg0jtqPYBd8Kq9tLD0BMBW3K70ph4bfx5+ZUFGIrpBk4K9Qt1KmsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:44:44.653583Z"},"content_sha256":"a6d926dbfb5447e81c1684f25636679b93e03a6f960299bb7345a119436cf97e","schema_version":"1.0","event_id":"sha256:a6d926dbfb5447e81c1684f25636679b93e03a6f960299bb7345a119436cf97e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GGVUHJ6VVEAS72MN6LQ34R4SOU/bundle.json","state_url":"https://pith.science/pith/GGVUHJ6VVEAS72MN6LQ34R4SOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GGVUHJ6VVEAS72MN6LQ34R4SOU/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":"2026-08-03T18:44:44Z","links":{"resolver":"https://pith.science/pith/GGVUHJ6VVEAS72MN6LQ34R4SOU","bundle":"https://pith.science/pith/GGVUHJ6VVEAS72MN6LQ34R4SOU/bundle.json","state":"https://pith.science/pith/GGVUHJ6VVEAS72MN6LQ34R4SOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GGVUHJ6VVEAS72MN6LQ34R4SOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GGVUHJ6VVEAS72MN6LQ34R4SOU","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":"cb675665f90cfa827ebf8e7e7e79b4d1cfee8a5758ae8b715d54929f0fab2461","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-08T15:00:16Z","title_canon_sha256":"d53916d16244da68aa69a3868223a2b74b5636f98028ee28876784f7db0653de"},"schema_version":"1.0","source":{"id":"2607.07504","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07504","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07504v1","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07504","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"pith_short_12","alias_value":"GGVUHJ6VVEAS","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"pith_short_16","alias_value":"GGVUHJ6VVEAS72MN","created_at":"2026-07-09T01:20:27Z"},{"alias_kind":"pith_short_8","alias_value":"GGVUHJ6V","created_at":"2026-07-09T01:20:27Z"}],"graph_snapshots":[{"event_id":"sha256:a6d926dbfb5447e81c1684f25636679b93e03a6f960299bb7345a119436cf97e","target":"graph","created_at":"2026-07-09T01:20:27Z","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/2607.07504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Product data scientists often ask LLM-based agents to help with recurring execution tasks such as cleaning data, writing SQL, choosing statistical tests, and formatting results. Reusable skill files are meant to avoid prompting from scratch by packaging guidance for a task family. Expert-written skills can encode high-quality guidance, but writing and maintaining them across many data-science task families creates a manual bottleneck. We ask whether LLM-generated skills offer a useful low-curation alternative: do they improve performance over the task prompt alone? We test this question across","authors_text":"Wei-Jung Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-08T15:00:16Z","title":"Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07504","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":"sha256:18db20b3a7a43f016d8e9369bfba82910cd59876478a479dcc7d4135df6f4c56","target":"record","created_at":"2026-07-09T01:20:27Z","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":"cb675665f90cfa827ebf8e7e7e79b4d1cfee8a5758ae8b715d54929f0fab2461","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-08T15:00:16Z","title_canon_sha256":"d53916d16244da68aa69a3868223a2b74b5636f98028ee28876784f7db0653de"},"schema_version":"1.0","source":{"id":"2607.07504","kind":"arxiv","version":1}},"canonical_sha256":"31ab43a7d5a9012fe98df2e1be47927535179ad3e29158f504a6957e494b6040","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31ab43a7d5a9012fe98df2e1be47927535179ad3e29158f504a6957e494b6040","first_computed_at":"2026-07-09T01:20:27.472099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:27.472099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1DbadlVfKQ49ryAycc5nE1yma+JfNFth9v6vWWQFXGmyZR4HYArhwr8JC+iGcbJUowJYWW/upfIDtbJlpXbgAA==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:27.472544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07504","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18db20b3a7a43f016d8e9369bfba82910cd59876478a479dcc7d4135df6f4c56","sha256:a6d926dbfb5447e81c1684f25636679b93e03a6f960299bb7345a119436cf97e"],"state_sha256":"e26e22324ed42d765dfc228e014694b3dc23b5db39390b81f21e76d5673db8cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6ehI0z/4il95UZvOZOVqrjZBENhBTnXZyQOA4qS8Vn3UlQSDR5pxIDCowrm7IRMTWPd5o3/pjG9KkgE7nXUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:44:44.656346Z","bundle_sha256":"be3368cad5eee0dbc342ce6ce724b12bd0b04b1ceb5aee42d96835b8b9cf6c31"}}