{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:U6KBUO6ZMR3CH3KRB3X5QJA6CQ","short_pith_number":"pith:U6KBUO6Z","canonical_record":{"source":{"id":"2607.16617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-18T03:30:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8a61769c59684d6690f252178927a5c062e660feed464dca7a6393074b2bb6c","abstract_canon_sha256":"cd7c4d8413fd1ea6230093450804197d56d506a06dd7de16c90b5b1073ac8a1f"},"schema_version":"1.0"},"canonical_sha256":"a7941a3bd9647623ed510eefd8241e14121825d9b745a4a3b7c838fb3acaa1a7","source":{"kind":"arxiv","id":"2607.16617","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16617","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16617v1","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16617","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"U6KBUO6ZMR3C","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"pith_short_16","alias_value":"U6KBUO6ZMR3CH3KR","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"pith_short_8","alias_value":"U6KBUO6Z","created_at":"2026-07-21T00:20:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:U6KBUO6ZMR3CH3KRB3X5QJA6CQ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.16617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-18T03:30:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8a61769c59684d6690f252178927a5c062e660feed464dca7a6393074b2bb6c","abstract_canon_sha256":"cd7c4d8413fd1ea6230093450804197d56d506a06dd7de16c90b5b1073ac8a1f"},"schema_version":"1.0"},"canonical_sha256":"a7941a3bd9647623ed510eefd8241e14121825d9b745a4a3b7c838fb3acaa1a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:28.572471Z","signature_b64":"BpcKw28mo6V+k5BMSGkdJhsuzMe7yXNrH3jJtmem15rdmAPLsGzPqJcvMg0Y9dAJ5Wr+MEhsNBhpfxvFMb0hDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7941a3bd9647623ed510eefd8241e14121825d9b745a4a3b7c838fb3acaa1a7","last_reissued_at":"2026-07-21T00:20:28.571610Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:28.571610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.16617","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":"2026-07-21T00:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tsam5NqUqDuY70FewTzuKYva4r3VNF6bMPG/WJlVzA81WsDV2uxQz069xRmYBwyfQwdbU6/vdLus80jBuFdcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:58:12.846425Z"},"content_sha256":"d219cd17d6885055042ab2bddf15dfd9650f5a0f9fabdb670bc86b6ba3579f79","schema_version":"1.0","event_id":"sha256:d219cd17d6885055042ab2bddf15dfd9650f5a0f9fabdb670bc86b6ba3579f79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:U6KBUO6ZMR3CH3KRB3X5QJA6CQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chengyu Shen, Hao Liang, Runming He, Wentao Zhang, Xiaochen Ma, Zhen Hao Wong, Zimo Meng","submitted_at":"2026-07-18T03:30:19Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the \\textit{NL2Pipeline gap}. To bridge it, we introduce \\textsc{DataFlow-Harness}, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines \\textsc{DataFlow-Skills} for procedural guidance, a Model Context Protocol (MCP) layer t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16617","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/2607.16617/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":"2026-07-21T00:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VKmIk7Q4P1zUqemE/poVyFak3tx3zkQLi5cH65JbEh5qHv4p8kIhszNZdErnJlfbGOTTo6F4mYd2phWsIPBCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:58:12.846966Z"},"content_sha256":"e8e1e8f344740692618b7eaee8164c74f15316065a424cb4cac7a1ed3dcb166e","schema_version":"1.0","event_id":"sha256:e8e1e8f344740692618b7eaee8164c74f15316065a424cb4cac7a1ed3dcb166e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/bundle.json","state_url":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/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":"2026-08-03T17:58:12Z","links":{"resolver":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ","bundle":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/bundle.json","state":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U6KBUO6ZMR3CH3KRB3X5QJA6CQ","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":"cd7c4d8413fd1ea6230093450804197d56d506a06dd7de16c90b5b1073ac8a1f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-18T03:30:19Z","title_canon_sha256":"a8a61769c59684d6690f252178927a5c062e660feed464dca7a6393074b2bb6c"},"schema_version":"1.0","source":{"id":"2607.16617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16617","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16617v1","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16617","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"U6KBUO6ZMR3C","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"pith_short_16","alias_value":"U6KBUO6ZMR3CH3KR","created_at":"2026-07-21T00:20:28Z"},{"alias_kind":"pith_short_8","alias_value":"U6KBUO6Z","created_at":"2026-07-21T00:20:28Z"}],"graph_snapshots":[{"event_id":"sha256:e8e1e8f344740692618b7eaee8164c74f15316065a424cb4cac7a1ed3dcb166e","target":"graph","created_at":"2026-07-21T00:20:28Z","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/2607.16617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the \\textit{NL2Pipeline gap}. To bridge it, we introduce \\textsc{DataFlow-Harness}, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines \\textsc{DataFlow-Skills} for procedural guidance, a Model Context Protocol (MCP) layer t","authors_text":"Chengyu Shen, Hao Liang, Runming He, Wentao Zhang, Xiaochen Ma, Zhen Hao Wong, Zimo Meng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-18T03:30:19Z","title":"DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16617","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:d219cd17d6885055042ab2bddf15dfd9650f5a0f9fabdb670bc86b6ba3579f79","target":"record","created_at":"2026-07-21T00:20:28Z","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":"cd7c4d8413fd1ea6230093450804197d56d506a06dd7de16c90b5b1073ac8a1f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-18T03:30:19Z","title_canon_sha256":"a8a61769c59684d6690f252178927a5c062e660feed464dca7a6393074b2bb6c"},"schema_version":"1.0","source":{"id":"2607.16617","kind":"arxiv","version":1}},"canonical_sha256":"a7941a3bd9647623ed510eefd8241e14121825d9b745a4a3b7c838fb3acaa1a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7941a3bd9647623ed510eefd8241e14121825d9b745a4a3b7c838fb3acaa1a7","first_computed_at":"2026-07-21T00:20:28.571610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:28.571610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BpcKw28mo6V+k5BMSGkdJhsuzMe7yXNrH3jJtmem15rdmAPLsGzPqJcvMg0Y9dAJ5Wr+MEhsNBhpfxvFMb0hDw==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:28.572471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d219cd17d6885055042ab2bddf15dfd9650f5a0f9fabdb670bc86b6ba3579f79","sha256:e8e1e8f344740692618b7eaee8164c74f15316065a424cb4cac7a1ed3dcb166e"],"state_sha256":"bf567f7b2e6fa84ce2b4c9dbf4b13165d12bd48672c24de8c87015c55d518b7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uDqs4w6KMl2NJ5xvf2yhIhyWvqGBpwe0fL+J+hnR/INRq7ebD2WlPETeg9zLSNwpr2q1YxaoJNeg0ga7gC1+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:58:12.850864Z","bundle_sha256":"2b10fd9e64c2866b5498a47fad7e9d01dcdacf7425786c2b6786cb832312c8af"}}