{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7C5UOKQM4CP6VBCCE6DIOQO6BI","short_pith_number":"pith:7C5UOKQM","canonical_record":{"source":{"id":"2409.15848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-24T08:19:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0b986917e89dc6dda1b997072ef4e1b6d4d2056b286b5d5b5c9539d3dc55f1fa","abstract_canon_sha256":"fa5cbbb394f93a6e6b056a81f08b2f344237eb6b28c793eb515e1971da37209e"},"schema_version":"1.0"},"canonical_sha256":"f8bb472a0ce09fea844227868741de0a2fc354aa20c857548d6ec0ea5a72e8fb","source":{"kind":"arxiv","id":"2409.15848","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15848","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15848v2","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15848","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"7C5UOKQM4CP6","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"pith_short_16","alias_value":"7C5UOKQM4CP6VBCC","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"pith_short_8","alias_value":"7C5UOKQM","created_at":"2026-07-05T10:39:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7C5UOKQM4CP6VBCCE6DIOQO6BI","target":"record","payload":{"canonical_record":{"source":{"id":"2409.15848","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-24T08:19:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0b986917e89dc6dda1b997072ef4e1b6d4d2056b286b5d5b5c9539d3dc55f1fa","abstract_canon_sha256":"fa5cbbb394f93a6e6b056a81f08b2f344237eb6b28c793eb515e1971da37209e"},"schema_version":"1.0"},"canonical_sha256":"f8bb472a0ce09fea844227868741de0a2fc354aa20c857548d6ec0ea5a72e8fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:46.356923Z","signature_b64":"n+7f/VIZFV/VSDV4KBojOoPgSDNFxXD6nmaUip8+tp4K5qoTixdfCvLU6AcbU9pdCUUkm1/v3zYw7h3AkBKHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8bb472a0ce09fea844227868741de0a2fc354aa20c857548d6ec0ea5a72e8fb","last_reissued_at":"2026-07-05T10:39:46.356339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:46.356339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.15848","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":"2026-07-05T10:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQWhG+D9yUIMe9CFUS+avfcdzVVPkQHLmGB1Dudcpwyk1GAjdKQ+jVewQ0QlZs3Sg1ayzDk4uOuevmTkGeHSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:56:31.170016Z"},"content_sha256":"226c7bfc30480158fd77c09e2679065f2dc702065da8104f3cea322476a94218","schema_version":"1.0","event_id":"sha256:226c7bfc30480158fd77c09e2679065f2dc702065da8104f3cea322476a94218"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7C5UOKQM4CP6VBCCE6DIOQO6BI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"iGAiVA: Integrated Generative AI and Visual Analytics in a Machine Learning Workflow for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Adrian Carrasco-Revilla, Min Chen, Yuanzhe Jin","submitted_at":"2024-09-24T08:19:45Z","abstract_excerpt":"In developing machine learning (ML) models for text classification, one common challenge is that the collected data is often not ideally distributed, especially when new classes are introduced in response to changes of data and tasks. In this paper, we present a solution for using visual analytics (VA) to guide the generation of synthetic data using large language models. As VA enables model developers to identify data-related deficiency, data synthesis can be targeted to address such deficiency. We discuss different types of data deficiency, describe different VA techniques for supporting the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15848","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/2409.15848/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":"2026-07-05T10:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLW2kmkoTDJ7uhHmlfIi9VXTDMmXalii+MlahD+mivr7n0UJEcHzyHEmDdszrN99s9kv5fXppUi3cj7RWgQ4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:56:31.170521Z"},"content_sha256":"b29c940bb99d14dd2a9ce2efe6fc617a853d8a89d2f4aa715812504432484266","schema_version":"1.0","event_id":"sha256:b29c940bb99d14dd2a9ce2efe6fc617a853d8a89d2f4aa715812504432484266"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7C5UOKQM4CP6VBCCE6DIOQO6BI/bundle.json","state_url":"https://pith.science/pith/7C5UOKQM4CP6VBCCE6DIOQO6BI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7C5UOKQM4CP6VBCCE6DIOQO6BI/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":"2026-08-08T23:56:31Z","links":{"resolver":"https://pith.science/pith/7C5UOKQM4CP6VBCCE6DIOQO6BI","bundle":"https://pith.science/pith/7C5UOKQM4CP6VBCCE6DIOQO6BI/bundle.json","state":"https://pith.science/pith/7C5UOKQM4CP6VBCCE6DIOQO6BI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7C5UOKQM4CP6VBCCE6DIOQO6BI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7C5UOKQM4CP6VBCCE6DIOQO6BI","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":"fa5cbbb394f93a6e6b056a81f08b2f344237eb6b28c793eb515e1971da37209e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-24T08:19:45Z","title_canon_sha256":"0b986917e89dc6dda1b997072ef4e1b6d4d2056b286b5d5b5c9539d3dc55f1fa"},"schema_version":"1.0","source":{"id":"2409.15848","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15848","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15848v2","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15848","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"7C5UOKQM4CP6","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"pith_short_16","alias_value":"7C5UOKQM4CP6VBCC","created_at":"2026-07-05T10:39:46Z"},{"alias_kind":"pith_short_8","alias_value":"7C5UOKQM","created_at":"2026-07-05T10:39:46Z"}],"graph_snapshots":[{"event_id":"sha256:b29c940bb99d14dd2a9ce2efe6fc617a853d8a89d2f4aa715812504432484266","target":"graph","created_at":"2026-07-05T10:39:46Z","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/2409.15848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In developing machine learning (ML) models for text classification, one common challenge is that the collected data is often not ideally distributed, especially when new classes are introduced in response to changes of data and tasks. In this paper, we present a solution for using visual analytics (VA) to guide the generation of synthetic data using large language models. As VA enables model developers to identify data-related deficiency, data synthesis can be targeted to address such deficiency. We discuss different types of data deficiency, describe different VA techniques for supporting the","authors_text":"Adrian Carrasco-Revilla, Min Chen, Yuanzhe Jin","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-24T08:19:45Z","title":"iGAiVA: Integrated Generative AI and Visual Analytics in a Machine Learning Workflow for Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15848","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":"sha256:226c7bfc30480158fd77c09e2679065f2dc702065da8104f3cea322476a94218","target":"record","created_at":"2026-07-05T10:39:46Z","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":"fa5cbbb394f93a6e6b056a81f08b2f344237eb6b28c793eb515e1971da37209e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-24T08:19:45Z","title_canon_sha256":"0b986917e89dc6dda1b997072ef4e1b6d4d2056b286b5d5b5c9539d3dc55f1fa"},"schema_version":"1.0","source":{"id":"2409.15848","kind":"arxiv","version":2}},"canonical_sha256":"f8bb472a0ce09fea844227868741de0a2fc354aa20c857548d6ec0ea5a72e8fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8bb472a0ce09fea844227868741de0a2fc354aa20c857548d6ec0ea5a72e8fb","first_computed_at":"2026-07-05T10:39:46.356339Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:46.356339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n+7f/VIZFV/VSDV4KBojOoPgSDNFxXD6nmaUip8+tp4K5qoTixdfCvLU6AcbU9pdCUUkm1/v3zYw7h3AkBKHDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:46.356923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15848","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:226c7bfc30480158fd77c09e2679065f2dc702065da8104f3cea322476a94218","sha256:b29c940bb99d14dd2a9ce2efe6fc617a853d8a89d2f4aa715812504432484266"],"state_sha256":"a4db3be5c5bfcfbfb7658fec3a6f3df6a78f039e8a631260f916cda901867632"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tlp0y1Dcl/JoF/Q+vnX30gwCB1NBJVBZBxlA/Zv0PCg3XbmDdpWYw3yOsDI8HEm0Wk4ftQNzKpdUkj0osjGHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:56:31.177985Z","bundle_sha256":"d9b049a6ce49f80c3e3040a67153867d4450e243409e59f59db7dfc6986a5466"}}