{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:67RENIBF4ZTCLQ2GU25CMU4YLQ","short_pith_number":"pith:67RENIBF","canonical_record":{"source":{"id":"2106.13861","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-06-25T19:44:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd8fa6b1801848f2993b2226b1493d8dbf2bc7fb73d8213583600271b655dbae","abstract_canon_sha256":"e6fc81f3c21583237e668dfbbbb471cb58db03638a202ab911114e25d136f0d8"},"schema_version":"1.0"},"canonical_sha256":"f7e246a025e66625c346a6ba2653985c2fdf352b277b88e5aae6c8e5321d892c","source":{"kind":"arxiv","id":"2106.13861","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13861","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13861v2","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13861","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"67RENIBF4ZTC","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"67RENIBF4ZTCLQ2G","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"67RENIBF","created_at":"2026-07-05T03:03:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:67RENIBF4ZTCLQ2GU25CMU4YLQ","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13861","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-06-25T19:44:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd8fa6b1801848f2993b2226b1493d8dbf2bc7fb73d8213583600271b655dbae","abstract_canon_sha256":"e6fc81f3c21583237e668dfbbbb471cb58db03638a202ab911114e25d136f0d8"},"schema_version":"1.0"},"canonical_sha256":"f7e246a025e66625c346a6ba2653985c2fdf352b277b88e5aae6c8e5321d892c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:08.825599Z","signature_b64":"OF57ZPOVvZke3bw8UDEJSHoeV5Ds6RM0oQTeaR6gF8DYoVWwLlpW+PZUCzjTfbX0a2AWh69bwyVNvmHNpW/kDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7e246a025e66625c346a6ba2653985c2fdf352b277b88e5aae6c8e5321d892c","last_reissued_at":"2026-07-05T03:03:08.825202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:08.825202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13861","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":"2026-07-05T03:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kLTgYciQPlg8G3FxRuqX+MZ+1LX+DmK9y7E8Ea1N7PACfE+UJcZ1wpCUJFt8rabDWgKi8sNesATya+XRfwptDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:10:21.683588Z"},"content_sha256":"b971298f701f8d82dbbb8fc7ff555492b56dc80127acd31f7e1565c041b573c2","schema_version":"1.0","event_id":"sha256:b971298f701f8d82dbbb8fc7ff555492b56dc80127acd31f7e1565c041b573c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:67RENIBF4ZTCLQ2GU25CMU4YLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Junwen Yang, Surajit Chaudhuri, Yeye He","submitted_at":"2021-06-25T19:44:01Z","abstract_excerpt":"Recent work has made significant progress in helping users to automate single data preparation steps, such as string-transformations and table-manipulation operators (e.g., Join, GroupBy, Pivot, etc.). We in this work propose to automate multiple such steps end-to-end, by synthesizing complex data pipelines with both string transformations and table-manipulation operators. We propose a novel \"by-target\" paradigm that allows users to easily specify the desired pipeline, which is a significant departure from the traditional by-example paradigm. Using by-target, users would provide input tables ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13861","kind":"arxiv","version":2},"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/2106.13861/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":"2026-07-05T03:03:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o1NY/J+eOFriHEbgXpSEWCEKgIfKHBVL1OcdbLDBQgCACLtMWGs9LOll43uBtxzf06yMfGIs+TgdgHXaxDP6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:10:21.684467Z"},"content_sha256":"64c7754c9ea5a69fe8a6e28c0d2a1beeac444e51d423b10ff981f7ed4024d213","schema_version":"1.0","event_id":"sha256:64c7754c9ea5a69fe8a6e28c0d2a1beeac444e51d423b10ff981f7ed4024d213"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67RENIBF4ZTCLQ2GU25CMU4YLQ/bundle.json","state_url":"https://pith.science/pith/67RENIBF4ZTCLQ2GU25CMU4YLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67RENIBF4ZTCLQ2GU25CMU4YLQ/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":"2026-08-08T01:10:21Z","links":{"resolver":"https://pith.science/pith/67RENIBF4ZTCLQ2GU25CMU4YLQ","bundle":"https://pith.science/pith/67RENIBF4ZTCLQ2GU25CMU4YLQ/bundle.json","state":"https://pith.science/pith/67RENIBF4ZTCLQ2GU25CMU4YLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67RENIBF4ZTCLQ2GU25CMU4YLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:67RENIBF4ZTCLQ2GU25CMU4YLQ","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":"e6fc81f3c21583237e668dfbbbb471cb58db03638a202ab911114e25d136f0d8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-06-25T19:44:01Z","title_canon_sha256":"dd8fa6b1801848f2993b2226b1493d8dbf2bc7fb73d8213583600271b655dbae"},"schema_version":"1.0","source":{"id":"2106.13861","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13861","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13861v2","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13861","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"pith_short_12","alias_value":"67RENIBF4ZTC","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"pith_short_16","alias_value":"67RENIBF4ZTCLQ2G","created_at":"2026-07-05T03:03:08Z"},{"alias_kind":"pith_short_8","alias_value":"67RENIBF","created_at":"2026-07-05T03:03:08Z"}],"graph_snapshots":[{"event_id":"sha256:64c7754c9ea5a69fe8a6e28c0d2a1beeac444e51d423b10ff981f7ed4024d213","target":"graph","created_at":"2026-07-05T03:03:08Z","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/2106.13861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has made significant progress in helping users to automate single data preparation steps, such as string-transformations and table-manipulation operators (e.g., Join, GroupBy, Pivot, etc.). We in this work propose to automate multiple such steps end-to-end, by synthesizing complex data pipelines with both string transformations and table-manipulation operators. We propose a novel \"by-target\" paradigm that allows users to easily specify the desired pipeline, which is a significant departure from the traditional by-example paradigm. Using by-target, users would provide input tables (","authors_text":"Junwen Yang, Surajit Chaudhuri, Yeye He","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-06-25T19:44:01Z","title":"Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13861","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:b971298f701f8d82dbbb8fc7ff555492b56dc80127acd31f7e1565c041b573c2","target":"record","created_at":"2026-07-05T03:03:08Z","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":"e6fc81f3c21583237e668dfbbbb471cb58db03638a202ab911114e25d136f0d8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2021-06-25T19:44:01Z","title_canon_sha256":"dd8fa6b1801848f2993b2226b1493d8dbf2bc7fb73d8213583600271b655dbae"},"schema_version":"1.0","source":{"id":"2106.13861","kind":"arxiv","version":2}},"canonical_sha256":"f7e246a025e66625c346a6ba2653985c2fdf352b277b88e5aae6c8e5321d892c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7e246a025e66625c346a6ba2653985c2fdf352b277b88e5aae6c8e5321d892c","first_computed_at":"2026-07-05T03:03:08.825202Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:08.825202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OF57ZPOVvZke3bw8UDEJSHoeV5Ds6RM0oQTeaR6gF8DYoVWwLlpW+PZUCzjTfbX0a2AWh69bwyVNvmHNpW/kDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:08.825599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13861","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b971298f701f8d82dbbb8fc7ff555492b56dc80127acd31f7e1565c041b573c2","sha256:64c7754c9ea5a69fe8a6e28c0d2a1beeac444e51d423b10ff981f7ed4024d213"],"state_sha256":"9f7756d0cb0da8f9fa4988296d6d71254218f650e3f622daf2111434e464d9d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNsyqNTbQdFxepEZHQBxT7n39/OfH8XCYSx8UDV9Nw/KsKPFlOzXhTfXf3NYIBVU5ApC8V+IB4fO4MJtvlh3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:10:21.689928Z","bundle_sha256":"9789d613266b407f8461225ead09a9b2e684b594fc27c2b5867f910a32cd84bc"}}