{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JUNTFYSWNPXRJOOMMHXMLLQUGJ","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":"746cf54fb70928517168065bcec0f509f2238f2c1b43caedf68a1234a8133ee1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T07:43:22Z","title_canon_sha256":"746c2cdcff249ccdcd02d4362367d2a74e0388bf6e1fb2d280ef3b942901e10f"},"schema_version":"1.0","source":{"id":"2507.13710","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13710","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13710v2","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13710","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"pith_short_12","alias_value":"JUNTFYSWNPXR","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"pith_short_16","alias_value":"JUNTFYSWNPXRJOOM","created_at":"2026-07-05T11:43:33Z"},{"alias_kind":"pith_short_8","alias_value":"JUNTFYSW","created_at":"2026-07-05T11:43:33Z"}],"graph_snapshots":[{"event_id":"sha256:38795b4934cadf2704eb902bcae3d1b24dd76e4a65dd1415a3d36c3bc3ad118e","target":"graph","created_at":"2026-07-05T11:43:33Z","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/2507.13710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data preparation is a foundational yet notoriously challenging component of the machine learning lifecycle, characterized by a vast combinatorial search space. While reinforcement learning (RL) offers a promising direction, state-of-the-art methods suffer from a critical limitation: to manage the search space, they rely on rigid ``hard constraints'' that prematurely prune the search space and often preclude optimal solutions. To address this, we introduce SoftPipe, a novel RL framework that replaces these constraints with a flexible ``soft guidance'' paradigm. SoftPipe formulates action select","authors_text":"Chang Liu, Jianbin Qin, Jinbin Huang, Jing Chang, Rui Mao, Shuyuan Zheng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T07:43:22Z","title":"SoftPipe: A Soft-Guided Reinforcement Learning Framework for Automated Data Preparation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13710","kind":"arxiv","version":2},"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:f4bcca4c64b647308193f25c9170bd2f56620214ff4b56fceae46c88e0a72c29","target":"record","created_at":"2026-07-05T11:43:33Z","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":"746cf54fb70928517168065bcec0f509f2238f2c1b43caedf68a1234a8133ee1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T07:43:22Z","title_canon_sha256":"746c2cdcff249ccdcd02d4362367d2a74e0388bf6e1fb2d280ef3b942901e10f"},"schema_version":"1.0","source":{"id":"2507.13710","kind":"arxiv","version":2}},"canonical_sha256":"4d1b32e2566bef14b9cc61eec5ae1432637966fae9cbb0a6c2cadd5601035aee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d1b32e2566bef14b9cc61eec5ae1432637966fae9cbb0a6c2cadd5601035aee","first_computed_at":"2026-07-05T11:43:33.808694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:33.808694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"peC8M5d/yCs93gJQWbcHMnhLxtG262Jw1sxIQTU++8UPhACyp/sHR65v3rokNHWxCK039UAkjhAJdQkw+E+5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:33.809176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13710","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4bcca4c64b647308193f25c9170bd2f56620214ff4b56fceae46c88e0a72c29","sha256:38795b4934cadf2704eb902bcae3d1b24dd76e4a65dd1415a3d36c3bc3ad118e"],"state_sha256":"3df720fb7beed60df94904b5e30070cffc6bec3aeb67faf8472296869e232e92"}