{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OPBQXYSGKTBWPY4HAHFKST6N25","short_pith_number":"pith:OPBQXYSG","canonical_record":{"source":{"id":"2507.13712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T07:52:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"50034468317e64931ea5a1f8257551390c71dc1e15a17bf54e2c3486e1a089b4","abstract_canon_sha256":"fa60e4a0011d7d8d6ad3ba27688753525a390cccd25729880216b0c5d0a68858"},"schema_version":"1.0"},"canonical_sha256":"73c30be24654c367e38701caa94fcdd746a7dce52d973858fa3b7344ffc1a544","source":{"kind":"arxiv","id":"2507.13712","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13712","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13712v1","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13712","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"OPBQXYSGKTBW","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"pith_short_16","alias_value":"OPBQXYSGKTBWPY4H","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"pith_short_8","alias_value":"OPBQXYSG","created_at":"2026-07-05T11:39:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OPBQXYSGKTBWPY4HAHFKST6N25","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T07:52:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"50034468317e64931ea5a1f8257551390c71dc1e15a17bf54e2c3486e1a089b4","abstract_canon_sha256":"fa60e4a0011d7d8d6ad3ba27688753525a390cccd25729880216b0c5d0a68858"},"schema_version":"1.0"},"canonical_sha256":"73c30be24654c367e38701caa94fcdd746a7dce52d973858fa3b7344ffc1a544","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:21.565349Z","signature_b64":"HKoN1kNWhPsoy+bmp5ab+PoZ0kpaet1+oWFtOb5Ce0d0jHdz+7E0SNE37q/v7q8P18RuLUiaKQOV2cdl6pi/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73c30be24654c367e38701caa94fcdd746a7dce52d973858fa3b7344ffc1a544","last_reissued_at":"2026-07-05T11:39:21.564865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:21.564865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13712","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":"2026-07-05T11:39:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DmofpJ+e2GUdetMzVr8Et4eoaBk4NsUq71a0ef6RfHwDVFhyNzBl5hHd0T/3mDldPX+lZjOJ12MqDulN6zvaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:04:17.576253Z"},"content_sha256":"017f6c4cc3a9f010ff4a4ed98ae17787c9fd757428f8cdd1acf056156a68ef56","schema_version":"1.0","event_id":"sha256:017f6c4cc3a9f010ff4a4ed98ae17787c9fd757428f8cdd1acf056156a68ef56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OPBQXYSGKTBWPY4HAHFKST6N25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaPipe: LLM-Guided Reinforcement Learning for Automated Data Preparation Pipeline Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Chang Liu, Jianbin Qin, Jinbin Huang, Jing Chang, Rui Mao","submitted_at":"2025-07-18T07:52:19Z","abstract_excerpt":"Automated data preparation is crucial for democratizing machine learning, yet existing reinforcement learning (RL) based approaches suffer from inefficient exploration in the vast space of possible preprocessing pipelines. We present LLaPipe, a novel framework that addresses this exploration bottleneck by integrating Large Language Models (LLMs) as intelligent policy advisors. Unlike traditional methods that rely solely on statistical features and blind trial-and-error, LLaPipe leverages the semantic understanding capabilities of LLMs to provide contextually relevant exploration guidance. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13712","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/2507.13712/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":"2026-07-05T11:39:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P8MMnhqTnVesaTPYuLoki7d0y83lh95Kl5ed5R8WPQtgac6t20vXyHCclCb8Y/XOu1KdxbFh5Lwc/kSbfVkVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:04:17.576791Z"},"content_sha256":"ab9e0f24e1774388fabe22051a7fcef511aa048b6ec00ed68e3de3b8e1e7d670","schema_version":"1.0","event_id":"sha256:ab9e0f24e1774388fabe22051a7fcef511aa048b6ec00ed68e3de3b8e1e7d670"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPBQXYSGKTBWPY4HAHFKST6N25/bundle.json","state_url":"https://pith.science/pith/OPBQXYSGKTBWPY4HAHFKST6N25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPBQXYSGKTBWPY4HAHFKST6N25/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":"2026-08-10T07:04:17Z","links":{"resolver":"https://pith.science/pith/OPBQXYSGKTBWPY4HAHFKST6N25","bundle":"https://pith.science/pith/OPBQXYSGKTBWPY4HAHFKST6N25/bundle.json","state":"https://pith.science/pith/OPBQXYSGKTBWPY4HAHFKST6N25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPBQXYSGKTBWPY4HAHFKST6N25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OPBQXYSGKTBWPY4HAHFKST6N25","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":"fa60e4a0011d7d8d6ad3ba27688753525a390cccd25729880216b0c5d0a68858","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T07:52:19Z","title_canon_sha256":"50034468317e64931ea5a1f8257551390c71dc1e15a17bf54e2c3486e1a089b4"},"schema_version":"1.0","source":{"id":"2507.13712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13712","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13712v1","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13712","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"OPBQXYSGKTBW","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"pith_short_16","alias_value":"OPBQXYSGKTBWPY4H","created_at":"2026-07-05T11:39:21Z"},{"alias_kind":"pith_short_8","alias_value":"OPBQXYSG","created_at":"2026-07-05T11:39:21Z"}],"graph_snapshots":[{"event_id":"sha256:ab9e0f24e1774388fabe22051a7fcef511aa048b6ec00ed68e3de3b8e1e7d670","target":"graph","created_at":"2026-07-05T11:39:21Z","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/2507.13712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated data preparation is crucial for democratizing machine learning, yet existing reinforcement learning (RL) based approaches suffer from inefficient exploration in the vast space of possible preprocessing pipelines. We present LLaPipe, a novel framework that addresses this exploration bottleneck by integrating Large Language Models (LLMs) as intelligent policy advisors. Unlike traditional methods that rely solely on statistical features and blind trial-and-error, LLaPipe leverages the semantic understanding capabilities of LLMs to provide contextually relevant exploration guidance. Our ","authors_text":"Chang Liu, Jianbin Qin, Jinbin Huang, Jing Chang, Rui Mao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T07:52:19Z","title":"LLaPipe: LLM-Guided Reinforcement Learning for Automated Data Preparation Pipeline Construction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13712","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":"sha256:017f6c4cc3a9f010ff4a4ed98ae17787c9fd757428f8cdd1acf056156a68ef56","target":"record","created_at":"2026-07-05T11:39:21Z","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":"fa60e4a0011d7d8d6ad3ba27688753525a390cccd25729880216b0c5d0a68858","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T07:52:19Z","title_canon_sha256":"50034468317e64931ea5a1f8257551390c71dc1e15a17bf54e2c3486e1a089b4"},"schema_version":"1.0","source":{"id":"2507.13712","kind":"arxiv","version":1}},"canonical_sha256":"73c30be24654c367e38701caa94fcdd746a7dce52d973858fa3b7344ffc1a544","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73c30be24654c367e38701caa94fcdd746a7dce52d973858fa3b7344ffc1a544","first_computed_at":"2026-07-05T11:39:21.564865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:21.564865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HKoN1kNWhPsoy+bmp5ab+PoZ0kpaet1+oWFtOb5Ce0d0jHdz+7E0SNE37q/v7q8P18RuLUiaKQOV2cdl6pi/CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:21.565349Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:017f6c4cc3a9f010ff4a4ed98ae17787c9fd757428f8cdd1acf056156a68ef56","sha256:ab9e0f24e1774388fabe22051a7fcef511aa048b6ec00ed68e3de3b8e1e7d670"],"state_sha256":"a59323d0294a78b3075cf948fe90d8529fe9b1cfa7bca8a04e12a80e3cc8e8ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vaZRBpucmpWgGZZ/FhF/I17OVCqRLAGW+CWo1uFgS0GkHKWnjlm4pL3X3CTZ+UcaC8f6z+HQ/CD8uY0sn5ZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:04:17.583395Z","bundle_sha256":"779af9edd24294ddf5f550e639eafcf47412c2d3926bfb90b57556247e46832d"}}