{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BSC4JTEJBPBJAUWSFJL2NECRIP","short_pith_number":"pith:BSC4JTEJ","canonical_record":{"source":{"id":"2504.14764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-20T23:35:41Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"3bfd83cdc0ea6dc10b15c46d1c8a8fa4cb0abc00b6f5a464c23017722c71d042","abstract_canon_sha256":"bbc6aa9c7a4513c1e148fd516da97dc9159eeff9e0f89cc5506c85b038c5da7f"},"schema_version":"1.0"},"canonical_sha256":"0c85c4cc890bc29052d22a57a6905143c1005f5a85ea02a78480382c4e0ddc8d","source":{"kind":"arxiv","id":"2504.14764","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14764","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14764v1","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14764","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"BSC4JTEJBPBJ","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"pith_short_16","alias_value":"BSC4JTEJBPBJAUWS","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"pith_short_8","alias_value":"BSC4JTEJ","created_at":"2026-07-05T10:51:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BSC4JTEJBPBJAUWSFJL2NECRIP","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-20T23:35:41Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"3bfd83cdc0ea6dc10b15c46d1c8a8fa4cb0abc00b6f5a464c23017722c71d042","abstract_canon_sha256":"bbc6aa9c7a4513c1e148fd516da97dc9159eeff9e0f89cc5506c85b038c5da7f"},"schema_version":"1.0"},"canonical_sha256":"0c85c4cc890bc29052d22a57a6905143c1005f5a85ea02a78480382c4e0ddc8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:50.241956Z","signature_b64":"Lb8upKAtaaxTDTheViYKpvt8rhtalIxYtkZgvZay2/HQz+EehXvb8jGR8elXP7gUlYiqFhFBuIaIoWT00q7jCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c85c4cc890bc29052d22a57a6905143c1005f5a85ea02a78480382c4e0ddc8d","last_reissued_at":"2026-07-05T10:51:50.241489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:50.241489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14764","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":"2026-07-05T10:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bje7Ip32GS+Jk6YdZnKOBM6yBq8iGfsVty0tywldpRHkqJ7PvJk5T6ExqjlozVaLMdJ1/8aGmh2ZFX3C2y3yBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:10:08.803605Z"},"content_sha256":"fefdb79858daaef5558d1eb79905b090f3bbe70211d6eb3e2b8a76cf320b9cb3","schema_version":"1.0","event_id":"sha256:fefdb79858daaef5558d1eb79905b090f3bbe70211d6eb3e2b8a76cf320b9cb3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BSC4JTEJBPBJAUWSFJL2NECRIP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Steering Semantic Data Processing With DocWrangler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.HC","authors_text":"Aditya G. Parameswaran, Bhavya Chopra, Bj\\\"orn Hartmann, Eugene Wu, Joseph M. Hellerstein, Mawil Hasan, Shreya Shankar, Stephen Lee","submitted_at":"2025-04-20T23:35:41Z","abstract_excerpt":"Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\\em semantic data processing}, where familiar data processing operators (e.g., map, reduce, filter) are powered by LLMs instead of code. However, building effective semantic data processing pipelines presents a departure from traditional data pipelines: users need to understand their data to write effective pipelines, yet they need to construct pipelines to extract the data necessary for that understanding -- all while navigating LLM idiosyncrasies and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14764","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/2504.14764/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":"2026-07-05T10:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"or9da214NtQFY3d4wrqlQwMpCHf6Wo0U+XoGLwic9dL8crZ4pjiyyXcyOCiUUi+i8KcoR+hugjrI6YJGiOYnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:10:08.804366Z"},"content_sha256":"927e4a109e18b0b8c8a27b1999a79749571bdacb9c35b3532d45edda2e758e37","schema_version":"1.0","event_id":"sha256:927e4a109e18b0b8c8a27b1999a79749571bdacb9c35b3532d45edda2e758e37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BSC4JTEJBPBJAUWSFJL2NECRIP/bundle.json","state_url":"https://pith.science/pith/BSC4JTEJBPBJAUWSFJL2NECRIP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BSC4JTEJBPBJAUWSFJL2NECRIP/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":"2026-08-17T06:10:08Z","links":{"resolver":"https://pith.science/pith/BSC4JTEJBPBJAUWSFJL2NECRIP","bundle":"https://pith.science/pith/BSC4JTEJBPBJAUWSFJL2NECRIP/bundle.json","state":"https://pith.science/pith/BSC4JTEJBPBJAUWSFJL2NECRIP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BSC4JTEJBPBJAUWSFJL2NECRIP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BSC4JTEJBPBJAUWSFJL2NECRIP","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":"bbc6aa9c7a4513c1e148fd516da97dc9159eeff9e0f89cc5506c85b038c5da7f","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-20T23:35:41Z","title_canon_sha256":"3bfd83cdc0ea6dc10b15c46d1c8a8fa4cb0abc00b6f5a464c23017722c71d042"},"schema_version":"1.0","source":{"id":"2504.14764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14764","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14764v1","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14764","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"BSC4JTEJBPBJ","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"pith_short_16","alias_value":"BSC4JTEJBPBJAUWS","created_at":"2026-07-05T10:51:50Z"},{"alias_kind":"pith_short_8","alias_value":"BSC4JTEJ","created_at":"2026-07-05T10:51:50Z"}],"graph_snapshots":[{"event_id":"sha256:927e4a109e18b0b8c8a27b1999a79749571bdacb9c35b3532d45edda2e758e37","target":"graph","created_at":"2026-07-05T10:51:50Z","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/2504.14764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unstructured text has long been difficult to automatically analyze at scale. Large language models (LLMs) now offer a way forward by enabling {\\em semantic data processing}, where familiar data processing operators (e.g., map, reduce, filter) are powered by LLMs instead of code. However, building effective semantic data processing pipelines presents a departure from traditional data pipelines: users need to understand their data to write effective pipelines, yet they need to construct pipelines to extract the data necessary for that understanding -- all while navigating LLM idiosyncrasies and ","authors_text":"Aditya G. Parameswaran, Bhavya Chopra, Bj\\\"orn Hartmann, Eugene Wu, Joseph M. Hellerstein, Mawil Hasan, Shreya Shankar, Stephen Lee","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-20T23:35:41Z","title":"Steering Semantic Data Processing With DocWrangler"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14764","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:fefdb79858daaef5558d1eb79905b090f3bbe70211d6eb3e2b8a76cf320b9cb3","target":"record","created_at":"2026-07-05T10:51:50Z","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":"bbc6aa9c7a4513c1e148fd516da97dc9159eeff9e0f89cc5506c85b038c5da7f","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-20T23:35:41Z","title_canon_sha256":"3bfd83cdc0ea6dc10b15c46d1c8a8fa4cb0abc00b6f5a464c23017722c71d042"},"schema_version":"1.0","source":{"id":"2504.14764","kind":"arxiv","version":1}},"canonical_sha256":"0c85c4cc890bc29052d22a57a6905143c1005f5a85ea02a78480382c4e0ddc8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c85c4cc890bc29052d22a57a6905143c1005f5a85ea02a78480382c4e0ddc8d","first_computed_at":"2026-07-05T10:51:50.241489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:50.241489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lb8upKAtaaxTDTheViYKpvt8rhtalIxYtkZgvZay2/HQz+EehXvb8jGR8elXP7gUlYiqFhFBuIaIoWT00q7jCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:50.241956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fefdb79858daaef5558d1eb79905b090f3bbe70211d6eb3e2b8a76cf320b9cb3","sha256:927e4a109e18b0b8c8a27b1999a79749571bdacb9c35b3532d45edda2e758e37"],"state_sha256":"36bd59f45914dcb8d1a12e62b93f2ca41eef91eed531ed72d2e7c8c20836e318"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n7yX0xMxoz7Ti5YDymimYAkWF4wJS4EmSzpHhNjGZpjHt4YQMIr1cAWEab7ESZYbICCEkN6j5+Vo7Z7K3Ha1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:10:08.812183Z","bundle_sha256":"2cb7d60818d18353ff02c2ad63bfe0676af682969a34199e58eae5bb251e924b"}}