{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LLCI6MD76I42ZLYKL77GXVHXT7","short_pith_number":"pith:LLCI6MD7","canonical_record":{"source":{"id":"2505.21575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-27T07:44:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e79d69234865b3f2172e32d107e93cbb43be0d31a21ad00efa0e13c9ce6d589b","abstract_canon_sha256":"18f687262444a8ff989a73ed79153b180db633e25c07e2b1f782a26682e2a8af"},"schema_version":"1.0"},"canonical_sha256":"5ac48f307ff239acaf0a5ffe6bd4f79fd08a68e03aa5323f368d82b2827f6e9b","source":{"kind":"arxiv","id":"2505.21575","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21575","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21575v1","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21575","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"LLCI6MD76I42","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_16","alias_value":"LLCI6MD76I42ZLYK","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_8","alias_value":"LLCI6MD7","created_at":"2026-07-05T11:11:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LLCI6MD76I42ZLYKL77GXVHXT7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.21575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-27T07:44:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e79d69234865b3f2172e32d107e93cbb43be0d31a21ad00efa0e13c9ce6d589b","abstract_canon_sha256":"18f687262444a8ff989a73ed79153b180db633e25c07e2b1f782a26682e2a8af"},"schema_version":"1.0"},"canonical_sha256":"5ac48f307ff239acaf0a5ffe6bd4f79fd08a68e03aa5323f368d82b2827f6e9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:00.306623Z","signature_b64":"j++5pSn2qSVLr3we9Zq+ydd4wstDfo3gviPRI8vIFYSOIQEAbZT429vnMrcHGo9FqxmcOpn8yt+Jg6mvK9AbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ac48f307ff239acaf0a5ffe6bd4f79fd08a68e03aa5323f368d82b2827f6e9b","last_reissued_at":"2026-07-05T11:11:00.306122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:00.306122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.21575","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":"2026-07-05T11:11:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+ZqOrjRyPGwwHoaohSRBxcTJ3U+2X1jyVmBbPGasFbZBqCxV6/b1aTIQxZHfz8MuA2yTneovQG0ZvZ2hBURCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T09:19:15.671529Z"},"content_sha256":"4f906ff93dbceec3a7a918b2cfde2060d2712431896c9e3daf48186120ad035d","schema_version":"1.0","event_id":"sha256:4f906ff93dbceec3a7a918b2cfde2060d2712431896c9e3daf48186120ad035d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LLCI6MD76I42ZLYKL77GXVHXT7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StreamLink: Large-Language-Model Driven Distributed Data Engineering System","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Dawei Feng, Di Mei, Huiri Tan, Lei Ren, Xianying Lou, Zhangxi Tan","submitted_at":"2025-05-27T07:44:16Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable proficiency in natural language understanding (NLU), opening doors for innovative applications. We introduce StreamLink - an LLM-driven distributed data system designed to improve the efficiency and accessibility of data engineering tasks. We build StreamLink on top of distributed frameworks such as Apache Spark and Hadoop to handle large data at scale. One of the important design philosophies of StreamLink is to respect user data privacy by utilizing local fine-tuned LLMs instead of a public AI service like ChatGPT. With help from domain-adap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21575","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/2505.21575/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":"2026-07-05T11:11:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YgvwtWl59mAT4FxkdE62kw9jRktEMrSUL/8hafrZB1CCvuTDD3KSr1wv5TgHkBXHWrivuU9qPXxq6NOvTliFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T09:19:15.671921Z"},"content_sha256":"59579e03d6f2cea44e3a2bf3b4a395b5afa691de1589126f9815bba35ba1cb82","schema_version":"1.0","event_id":"sha256:59579e03d6f2cea44e3a2bf3b4a395b5afa691de1589126f9815bba35ba1cb82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLCI6MD76I42ZLYKL77GXVHXT7/bundle.json","state_url":"https://pith.science/pith/LLCI6MD76I42ZLYKL77GXVHXT7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLCI6MD76I42ZLYKL77GXVHXT7/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":"2026-07-26T09:19:15Z","links":{"resolver":"https://pith.science/pith/LLCI6MD76I42ZLYKL77GXVHXT7","bundle":"https://pith.science/pith/LLCI6MD76I42ZLYKL77GXVHXT7/bundle.json","state":"https://pith.science/pith/LLCI6MD76I42ZLYKL77GXVHXT7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLCI6MD76I42ZLYKL77GXVHXT7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LLCI6MD76I42ZLYKL77GXVHXT7","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":"18f687262444a8ff989a73ed79153b180db633e25c07e2b1f782a26682e2a8af","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-27T07:44:16Z","title_canon_sha256":"e79d69234865b3f2172e32d107e93cbb43be0d31a21ad00efa0e13c9ce6d589b"},"schema_version":"1.0","source":{"id":"2505.21575","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21575","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21575v1","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21575","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"LLCI6MD76I42","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_16","alias_value":"LLCI6MD76I42ZLYK","created_at":"2026-07-05T11:11:00Z"},{"alias_kind":"pith_short_8","alias_value":"LLCI6MD7","created_at":"2026-07-05T11:11:00Z"}],"graph_snapshots":[{"event_id":"sha256:59579e03d6f2cea44e3a2bf3b4a395b5afa691de1589126f9815bba35ba1cb82","target":"graph","created_at":"2026-07-05T11:11:00Z","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/2505.21575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown remarkable proficiency in natural language understanding (NLU), opening doors for innovative applications. We introduce StreamLink - an LLM-driven distributed data system designed to improve the efficiency and accessibility of data engineering tasks. We build StreamLink on top of distributed frameworks such as Apache Spark and Hadoop to handle large data at scale. One of the important design philosophies of StreamLink is to respect user data privacy by utilizing local fine-tuned LLMs instead of a public AI service like ChatGPT. With help from domain-adap","authors_text":"Dawei Feng, Di Mei, Huiri Tan, Lei Ren, Xianying Lou, Zhangxi Tan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-27T07:44:16Z","title":"StreamLink: Large-Language-Model Driven Distributed Data Engineering System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21575","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":"sha256:4f906ff93dbceec3a7a918b2cfde2060d2712431896c9e3daf48186120ad035d","target":"record","created_at":"2026-07-05T11:11:00Z","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":"18f687262444a8ff989a73ed79153b180db633e25c07e2b1f782a26682e2a8af","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-27T07:44:16Z","title_canon_sha256":"e79d69234865b3f2172e32d107e93cbb43be0d31a21ad00efa0e13c9ce6d589b"},"schema_version":"1.0","source":{"id":"2505.21575","kind":"arxiv","version":1}},"canonical_sha256":"5ac48f307ff239acaf0a5ffe6bd4f79fd08a68e03aa5323f368d82b2827f6e9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ac48f307ff239acaf0a5ffe6bd4f79fd08a68e03aa5323f368d82b2827f6e9b","first_computed_at":"2026-07-05T11:11:00.306122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:00.306122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j++5pSn2qSVLr3we9Zq+ydd4wstDfo3gviPRI8vIFYSOIQEAbZT429vnMrcHGo9FqxmcOpn8yt+Jg6mvK9AbCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:00.306623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21575","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f906ff93dbceec3a7a918b2cfde2060d2712431896c9e3daf48186120ad035d","sha256:59579e03d6f2cea44e3a2bf3b4a395b5afa691de1589126f9815bba35ba1cb82"],"state_sha256":"c734f11716d4791a02f6391165241cd495bf25f6261a52bcc31e2bcb99ac1750"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"md0PUvbBN5ZixeH50GSRgRuCQGE5OPha3yFaPLSu5/0bUoDwl/Tw0e9CfEmQYXHXjj1x2P9Oo6hYDENXYC3lBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T09:19:15.674406Z","bundle_sha256":"f2a101a16bef83186b454747cdf0aa86c9a3dd57af206ea929f43e9b6cf1740f"}}