{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RJENA2OSXLHZQBCKJC5I4EPDPE","short_pith_number":"pith:RJENA2OS","canonical_record":{"source":{"id":"2402.10379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T00:10:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b823efa5fc813db3359f3f93e35dd5bcd31a25cc65d1f2d86a40e47775eeb8af","abstract_canon_sha256":"dd8db97b44ac177b3d24ab1f3a764bd6ea9885e9501c35a2c274c3fea1500f41"},"schema_version":"1.0"},"canonical_sha256":"8a48d069d2bacf98044a48ba8e11e37938601fb63f6adfe6cfba27145a803005","source":{"kind":"arxiv","id":"2402.10379","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10379","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10379v2","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10379","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"RJENA2OSXLHZ","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"RJENA2OSXLHZQBCK","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"RJENA2OS","created_at":"2026-07-05T08:24:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RJENA2OSXLHZQBCKJC5I4EPDPE","target":"record","payload":{"canonical_record":{"source":{"id":"2402.10379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T00:10:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b823efa5fc813db3359f3f93e35dd5bcd31a25cc65d1f2d86a40e47775eeb8af","abstract_canon_sha256":"dd8db97b44ac177b3d24ab1f3a764bd6ea9885e9501c35a2c274c3fea1500f41"},"schema_version":"1.0"},"canonical_sha256":"8a48d069d2bacf98044a48ba8e11e37938601fb63f6adfe6cfba27145a803005","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:01.795599Z","signature_b64":"+p4cSEyNiXrhuW89bYJklP6HRJlBnLEu+IlyEQpHy9IvBhvYw03Wx2sEDnOzWnLyAT6mlUzYYzA0qt8LpWsACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a48d069d2bacf98044a48ba8e11e37938601fb63f6adfe6cfba27145a803005","last_reissued_at":"2026-07-05T08:24:01.795074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:01.795074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.10379","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":"2026-07-05T08:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d4hYE3tOkHAEv1gZSEeJ8kHajrWbWnQRabBf7d17EoHh9FGAO3kzJcLj7IWuPdjv2VFIw9trkxftCNiLUD+xBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:47:46.289488Z"},"content_sha256":"3c43811033d537c5dcf259a6850cf464d813a1f2a9b63b0dbd2c94e3b6c0a779","schema_version":"1.0","event_id":"sha256:3c43811033d537c5dcf259a6850cf464d813a1f2a9b63b0dbd2c94e3b6c0a779"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RJENA2OSXLHZQBCKJC5I4EPDPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ajay Patel, Chris Callison-Burch, Colin Raffel","submitted_at":"2024-02-16T00:10:26Z","abstract_excerpt":"Large language models (LLMs) have become a dominant and important tool for NLP researchers in a wide range of tasks. Today, many researchers use LLMs in synthetic data generation, task evaluation, fine-tuning, distillation, and other model-in-the-loop research workflows. However, challenges arise when using these models that stem from their scale, their closed source nature, and the lack of standardized tooling for these new and emerging workflows. The rapid rise to prominence of these models and these unique challenges has had immediate adverse impacts on open science and on the reproducibili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10379","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/2402.10379/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":"2026-07-05T08:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sh9Pyhj1t7tHgRWAjQKH2wkSia+RqqdDbrZU6bD9IFFNZ7pWQ9r6gc5unlze714NQvM2WaAGvrzp/jgv+ZDxBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:47:46.289970Z"},"content_sha256":"6a0e20c8ddd28613ba8748c3e10d7065443328fe3a4377edb0719e4f645c34c7","schema_version":"1.0","event_id":"sha256:6a0e20c8ddd28613ba8748c3e10d7065443328fe3a4377edb0719e4f645c34c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJENA2OSXLHZQBCKJC5I4EPDPE/bundle.json","state_url":"https://pith.science/pith/RJENA2OSXLHZQBCKJC5I4EPDPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJENA2OSXLHZQBCKJC5I4EPDPE/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":"2026-08-14T08:47:46Z","links":{"resolver":"https://pith.science/pith/RJENA2OSXLHZQBCKJC5I4EPDPE","bundle":"https://pith.science/pith/RJENA2OSXLHZQBCKJC5I4EPDPE/bundle.json","state":"https://pith.science/pith/RJENA2OSXLHZQBCKJC5I4EPDPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJENA2OSXLHZQBCKJC5I4EPDPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RJENA2OSXLHZQBCKJC5I4EPDPE","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":"dd8db97b44ac177b3d24ab1f3a764bd6ea9885e9501c35a2c274c3fea1500f41","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T00:10:26Z","title_canon_sha256":"b823efa5fc813db3359f3f93e35dd5bcd31a25cc65d1f2d86a40e47775eeb8af"},"schema_version":"1.0","source":{"id":"2402.10379","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10379","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10379v2","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10379","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"RJENA2OSXLHZ","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"RJENA2OSXLHZQBCK","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"RJENA2OS","created_at":"2026-07-05T08:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:6a0e20c8ddd28613ba8748c3e10d7065443328fe3a4377edb0719e4f645c34c7","target":"graph","created_at":"2026-07-05T08:24:01Z","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/2402.10379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have become a dominant and important tool for NLP researchers in a wide range of tasks. Today, many researchers use LLMs in synthetic data generation, task evaluation, fine-tuning, distillation, and other model-in-the-loop research workflows. However, challenges arise when using these models that stem from their scale, their closed source nature, and the lack of standardized tooling for these new and emerging workflows. The rapid rise to prominence of these models and these unique challenges has had immediate adverse impacts on open science and on the reproducibili","authors_text":"Ajay Patel, Chris Callison-Burch, Colin Raffel","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T00:10:26Z","title":"DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10379","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":"sha256:3c43811033d537c5dcf259a6850cf464d813a1f2a9b63b0dbd2c94e3b6c0a779","target":"record","created_at":"2026-07-05T08:24:01Z","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":"dd8db97b44ac177b3d24ab1f3a764bd6ea9885e9501c35a2c274c3fea1500f41","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T00:10:26Z","title_canon_sha256":"b823efa5fc813db3359f3f93e35dd5bcd31a25cc65d1f2d86a40e47775eeb8af"},"schema_version":"1.0","source":{"id":"2402.10379","kind":"arxiv","version":2}},"canonical_sha256":"8a48d069d2bacf98044a48ba8e11e37938601fb63f6adfe6cfba27145a803005","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a48d069d2bacf98044a48ba8e11e37938601fb63f6adfe6cfba27145a803005","first_computed_at":"2026-07-05T08:24:01.795074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:01.795074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+p4cSEyNiXrhuW89bYJklP6HRJlBnLEu+IlyEQpHy9IvBhvYw03Wx2sEDnOzWnLyAT6mlUzYYzA0qt8LpWsACg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:01.795599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10379","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c43811033d537c5dcf259a6850cf464d813a1f2a9b63b0dbd2c94e3b6c0a779","sha256:6a0e20c8ddd28613ba8748c3e10d7065443328fe3a4377edb0719e4f645c34c7"],"state_sha256":"9b637fa827e21cb6f2352f25bc9e00bb37938d0107588746a756890804e651ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lIc4HIne2txIAx6cvkBWq2rKjoE82q2KSB3FJUQaHx+YmFIqcOpJ9TYEDNtY6o0kIKGwwZqv4Cs+C3FIBFGqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:47:46.295859Z","bundle_sha256":"8812c7f807763b575674cc85f44350889d49ce3fbb70783c2609376ef48cfcca"}}