{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QE3DRJJREZNX5ACCWHFAP7YDV3","short_pith_number":"pith:QE3DRJJR","canonical_record":{"source":{"id":"2502.01697","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T00:12:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6b865bbfbac7c7599787df64b9a3c70b73413b918e5b912d86af56c3d36e9fa3","abstract_canon_sha256":"9ee07351f53d249024e08e16d579f9c31c06fbafbca6ddceb8496146dbbab7f1"},"schema_version":"1.0"},"canonical_sha256":"813638a531265b7e8042b1ca07ff03aecaf57a101dcc5f565973c9ad65a578b0","source":{"kind":"arxiv","id":"2502.01697","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01697","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01697v3","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01697","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"QE3DRJJREZNX","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"QE3DRJJREZNX5ACC","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"QE3DRJJR","created_at":"2026-07-05T11:06:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QE3DRJJREZNX5ACCWHFAP7YDV3","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01697","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T00:12:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6b865bbfbac7c7599787df64b9a3c70b73413b918e5b912d86af56c3d36e9fa3","abstract_canon_sha256":"9ee07351f53d249024e08e16d579f9c31c06fbafbca6ddceb8496146dbbab7f1"},"schema_version":"1.0"},"canonical_sha256":"813638a531265b7e8042b1ca07ff03aecaf57a101dcc5f565973c9ad65a578b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:54.885328Z","signature_b64":"xScghanGpqznvkmi8LSQeTXtIz3E7bcqIc6g6tmq6x8FVqtQST4Vd5bOgsPCa+I/1fOQ3NCEtaCJDUsd9KUnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813638a531265b7e8042b1ca07ff03aecaf57a101dcc5f565973c9ad65a578b0","last_reissued_at":"2026-07-05T11:06:54.884837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:54.884837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01697","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"osSesyutprGhEwUYcpLmeNkvXeoWZ7sh0kfvNQTE7UafelaDkXve20Pn5axJBMXga3U8214iwAfFoUvaA9p5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:25:34.578470Z"},"content_sha256":"9820cb49bc9c92c44cb3b1dac37e4300096fa7e69588c0ee6955bb185dd45f6d","schema_version":"1.0","event_id":"sha256:9820cb49bc9c92c44cb3b1dac37e4300096fa7e69588c0ee6955bb185dd45f6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QE3DRJJREZNX5ACCWHFAP7YDV3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Zhu, Boris Hanin, Ion Stoica, Jared Quincy Davis, Joseph E. Gonzalez, Lingjiao Chen, Matei Zaharia, Parth Asawa","submitted_at":"2025-02-03T00:12:40Z","abstract_excerpt":"As the demand for high-quality data in model training grows, researchers and developers are increasingly generating synthetic data to tune and train LLMs. However, current data generation methods rely on seed sets containing tens of thousands of examples to prompt instruction-tuned models. This reliance can be especially problematic when the curation of high-quality examples is expensive or difficult. In this paper we explore the novel few-shot synthetic data generation setting -- generating a high-quality dataset from a few examples. We show that when working with only a few seed examples, in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01697","kind":"arxiv","version":3},"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/2502.01697/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":"2026-07-05T11:06:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WT74Gbm/oQoZsSxnVHLlS2vY9eNG6DYa9Saw/n2qUVTtSqZXrZYSbw01zAK81lzdD/1biLVCfXExyWsuGxbDAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:25:34.578996Z"},"content_sha256":"1e9a85a47395b3401210cf56dd1ad7d08b12a632823cfb19bc420773039e6580","schema_version":"1.0","event_id":"sha256:1e9a85a47395b3401210cf56dd1ad7d08b12a632823cfb19bc420773039e6580"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QE3DRJJREZNX5ACCWHFAP7YDV3/bundle.json","state_url":"https://pith.science/pith/QE3DRJJREZNX5ACCWHFAP7YDV3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QE3DRJJREZNX5ACCWHFAP7YDV3/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":"2026-08-09T03:25:34Z","links":{"resolver":"https://pith.science/pith/QE3DRJJREZNX5ACCWHFAP7YDV3","bundle":"https://pith.science/pith/QE3DRJJREZNX5ACCWHFAP7YDV3/bundle.json","state":"https://pith.science/pith/QE3DRJJREZNX5ACCWHFAP7YDV3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QE3DRJJREZNX5ACCWHFAP7YDV3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QE3DRJJREZNX5ACCWHFAP7YDV3","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":"9ee07351f53d249024e08e16d579f9c31c06fbafbca6ddceb8496146dbbab7f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T00:12:40Z","title_canon_sha256":"6b865bbfbac7c7599787df64b9a3c70b73413b918e5b912d86af56c3d36e9fa3"},"schema_version":"1.0","source":{"id":"2502.01697","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01697","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01697v3","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01697","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_12","alias_value":"QE3DRJJREZNX","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_16","alias_value":"QE3DRJJREZNX5ACC","created_at":"2026-07-05T11:06:54Z"},{"alias_kind":"pith_short_8","alias_value":"QE3DRJJR","created_at":"2026-07-05T11:06:54Z"}],"graph_snapshots":[{"event_id":"sha256:1e9a85a47395b3401210cf56dd1ad7d08b12a632823cfb19bc420773039e6580","target":"graph","created_at":"2026-07-05T11:06:54Z","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/2502.01697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the demand for high-quality data in model training grows, researchers and developers are increasingly generating synthetic data to tune and train LLMs. However, current data generation methods rely on seed sets containing tens of thousands of examples to prompt instruction-tuned models. This reliance can be especially problematic when the curation of high-quality examples is expensive or difficult. In this paper we explore the novel few-shot synthetic data generation setting -- generating a high-quality dataset from a few examples. We show that when working with only a few seed examples, in","authors_text":"Alan Zhu, Boris Hanin, Ion Stoica, Jared Quincy Davis, Joseph E. Gonzalez, Lingjiao Chen, Matei Zaharia, Parth Asawa","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T00:12:40Z","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01697","kind":"arxiv","version":3},"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":"sha256:9820cb49bc9c92c44cb3b1dac37e4300096fa7e69588c0ee6955bb185dd45f6d","target":"record","created_at":"2026-07-05T11:06:54Z","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":"9ee07351f53d249024e08e16d579f9c31c06fbafbca6ddceb8496146dbbab7f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-03T00:12:40Z","title_canon_sha256":"6b865bbfbac7c7599787df64b9a3c70b73413b918e5b912d86af56c3d36e9fa3"},"schema_version":"1.0","source":{"id":"2502.01697","kind":"arxiv","version":3}},"canonical_sha256":"813638a531265b7e8042b1ca07ff03aecaf57a101dcc5f565973c9ad65a578b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"813638a531265b7e8042b1ca07ff03aecaf57a101dcc5f565973c9ad65a578b0","first_computed_at":"2026-07-05T11:06:54.884837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:54.884837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xScghanGpqznvkmi8LSQeTXtIz3E7bcqIc6g6tmq6x8FVqtQST4Vd5bOgsPCa+I/1fOQ3NCEtaCJDUsd9KUnDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:54.885328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01697","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9820cb49bc9c92c44cb3b1dac37e4300096fa7e69588c0ee6955bb185dd45f6d","sha256:1e9a85a47395b3401210cf56dd1ad7d08b12a632823cfb19bc420773039e6580"],"state_sha256":"a458a93597d72d0bd65c1a0bfe6a642711289edfccd6ed03bbcaef46bda0a8fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"onw/GaiVUTWCx9dRqqE0pmFiNz2nRsMztizbyGmnwxLLJT3tHisHMHC3N+kn4/khHRzMJL0WU4+I+Cu4U20fAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:25:34.583438Z","bundle_sha256":"7c0a72d2588102ec614fc9179a4a482e5a73bffbfa9ce4f3042ddd98cb66a3dd"}}