{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WJ4UGCR2RYEVATKJMQCA52KDX3","short_pith_number":"pith:WJ4UGCR2","canonical_record":{"source":{"id":"2405.10040","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T12:22:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"59497e63f6f5d895f0b63b4f54576e63d6e1ee5b3a41fea8c33bb06e7745c7b5","abstract_canon_sha256":"fb068b04e6a92658eddac8b11f50d953038377769eb193e9d53016fd5ae07a74"},"schema_version":"1.0"},"canonical_sha256":"b279430a3a8e09504d4964040ee943bed1b4d2ba09f73fa7cb0a636e9cd3ac47","source":{"kind":"arxiv","id":"2405.10040","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10040","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10040v3","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10040","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"WJ4UGCR2RYEV","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_16","alias_value":"WJ4UGCR2RYEVATKJ","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_8","alias_value":"WJ4UGCR2","created_at":"2026-07-05T09:34:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WJ4UGCR2RYEVATKJMQCA52KDX3","target":"record","payload":{"canonical_record":{"source":{"id":"2405.10040","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T12:22:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"59497e63f6f5d895f0b63b4f54576e63d6e1ee5b3a41fea8c33bb06e7745c7b5","abstract_canon_sha256":"fb068b04e6a92658eddac8b11f50d953038377769eb193e9d53016fd5ae07a74"},"schema_version":"1.0"},"canonical_sha256":"b279430a3a8e09504d4964040ee943bed1b4d2ba09f73fa7cb0a636e9cd3ac47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:35.859625Z","signature_b64":"ABROAFGugDO+iOx2EiFYfxOdrBz3WaH9evvbh/CkewoRxJSWWHG87AaREHbj/fzyW/AMNJMBX2jTRJ3WhYvzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b279430a3a8e09504d4964040ee943bed1b4d2ba09f73fa7cb0a636e9cd3ac47","last_reissued_at":"2026-07-05T09:34:35.859149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:35.859149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.10040","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":"2026-07-05T09:34:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmIwfAc+0RXbETU8fKuWDW3fW0ZHxHkxwIgzUQvdvIMfJlr8vtRzvBmr1Yu+B5m4SUEBnCH+j8Y7vN6I+QdrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:01:28.531867Z"},"content_sha256":"54732fdbbffb20b0b1145475a4b3494b3ed2b19b77699372ba64eb2bea15adac","schema_version":"1.0","event_id":"sha256:54732fdbbffb20b0b1145475a4b3494b3ed2b19b77699372ba64eb2bea15adac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WJ4UGCR2RYEVATKJMQCA52KDX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhishek Divekar, Greg Durrett","submitted_at":"2024-05-16T12:22:41Z","abstract_excerpt":"It is often desirable to distill the capabilities of large language models (LLMs) into smaller student models due to compute and memory constraints. One way to do this for classification tasks is via dataset synthesis, which can be accomplished by generating examples of each label from the LLM. Prior approaches to synthesis use few-shot prompting, which relies on the LLM's parametric knowledge to generate usable examples. However, this leads to issues of repetition, bias towards popular entities, and stylistic differences from human text. In this work, we propose Synthesize by Retrieval and Re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10040","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/2405.10040/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":"2026-07-05T09:34:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nt7VqFnauEOt19wY6n9iQeFE5WIfQbV3Fbjd/Orn9bKUQR583J9o5ru3QjvKJE6neIcXSJfGuxadG9Q4VTUdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:01:28.532384Z"},"content_sha256":"d1e7b3e4532b12a222536312f02b2da285483844053d7bc9fc0b314a09d1a451","schema_version":"1.0","event_id":"sha256:d1e7b3e4532b12a222536312f02b2da285483844053d7bc9fc0b314a09d1a451"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WJ4UGCR2RYEVATKJMQCA52KDX3/bundle.json","state_url":"https://pith.science/pith/WJ4UGCR2RYEVATKJMQCA52KDX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WJ4UGCR2RYEVATKJMQCA52KDX3/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":"2026-08-14T12:01:28Z","links":{"resolver":"https://pith.science/pith/WJ4UGCR2RYEVATKJMQCA52KDX3","bundle":"https://pith.science/pith/WJ4UGCR2RYEVATKJMQCA52KDX3/bundle.json","state":"https://pith.science/pith/WJ4UGCR2RYEVATKJMQCA52KDX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WJ4UGCR2RYEVATKJMQCA52KDX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WJ4UGCR2RYEVATKJMQCA52KDX3","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":"fb068b04e6a92658eddac8b11f50d953038377769eb193e9d53016fd5ae07a74","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T12:22:41Z","title_canon_sha256":"59497e63f6f5d895f0b63b4f54576e63d6e1ee5b3a41fea8c33bb06e7745c7b5"},"schema_version":"1.0","source":{"id":"2405.10040","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10040","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10040v3","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10040","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"WJ4UGCR2RYEV","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_16","alias_value":"WJ4UGCR2RYEVATKJ","created_at":"2026-07-05T09:34:35Z"},{"alias_kind":"pith_short_8","alias_value":"WJ4UGCR2","created_at":"2026-07-05T09:34:35Z"}],"graph_snapshots":[{"event_id":"sha256:d1e7b3e4532b12a222536312f02b2da285483844053d7bc9fc0b314a09d1a451","target":"graph","created_at":"2026-07-05T09:34:35Z","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/2405.10040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is often desirable to distill the capabilities of large language models (LLMs) into smaller student models due to compute and memory constraints. One way to do this for classification tasks is via dataset synthesis, which can be accomplished by generating examples of each label from the LLM. Prior approaches to synthesis use few-shot prompting, which relies on the LLM's parametric knowledge to generate usable examples. However, this leads to issues of repetition, bias towards popular entities, and stylistic differences from human text. In this work, we propose Synthesize by Retrieval and Re","authors_text":"Abhishek Divekar, Greg Durrett","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T12:22:41Z","title":"SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10040","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":"sha256:54732fdbbffb20b0b1145475a4b3494b3ed2b19b77699372ba64eb2bea15adac","target":"record","created_at":"2026-07-05T09:34:35Z","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":"fb068b04e6a92658eddac8b11f50d953038377769eb193e9d53016fd5ae07a74","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-16T12:22:41Z","title_canon_sha256":"59497e63f6f5d895f0b63b4f54576e63d6e1ee5b3a41fea8c33bb06e7745c7b5"},"schema_version":"1.0","source":{"id":"2405.10040","kind":"arxiv","version":3}},"canonical_sha256":"b279430a3a8e09504d4964040ee943bed1b4d2ba09f73fa7cb0a636e9cd3ac47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b279430a3a8e09504d4964040ee943bed1b4d2ba09f73fa7cb0a636e9cd3ac47","first_computed_at":"2026-07-05T09:34:35.859149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:35.859149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ABROAFGugDO+iOx2EiFYfxOdrBz3WaH9evvbh/CkewoRxJSWWHG87AaREHbj/fzyW/AMNJMBX2jTRJ3WhYvzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:35.859625Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10040","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54732fdbbffb20b0b1145475a4b3494b3ed2b19b77699372ba64eb2bea15adac","sha256:d1e7b3e4532b12a222536312f02b2da285483844053d7bc9fc0b314a09d1a451"],"state_sha256":"03011efe345880000ef75e8a5b823483fd93edbf96b256db2e4d2412f2e15da4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0hV5jSOM+WZWW/CYQ/ZfCGNuABtNf6jrjr9ghxCOH62NJFWtqbvQHmks89Eezat3kNEeVhA9FTUP257EsgAsAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T12:01:28.536722Z","bundle_sha256":"870fae17678c9a4f2383143b2adc264f18ef2eb8c0d709638bdf5182b572f3f4"}}