{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4YQC72EHWUJOQLUYEOPM36JW2V","short_pith_number":"pith:4YQC72EH","canonical_record":{"source":{"id":"2504.14508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T06:45:16Z","cross_cats_sorted":[],"title_canon_sha256":"912eda4841917bd9d2b44a6c209ec4476e889ee141952e7f2487d298cf0498e6","abstract_canon_sha256":"06ae7352478e54172663561e613b0f716981282b9a629b1e11252a3a8150742f"},"schema_version":"1.0"},"canonical_sha256":"e6202fe887b512e82e98239ecdf936d550f33c68abfc95be05d6015cedecc1d4","source":{"kind":"arxiv","id":"2504.14508","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14508","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14508v2","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14508","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"4YQC72EHWUJO","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"4YQC72EHWUJOQLUY","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"4YQC72EH","created_at":"2026-07-05T11:42:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4YQC72EHWUJOQLUYEOPM36JW2V","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14508","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T06:45:16Z","cross_cats_sorted":[],"title_canon_sha256":"912eda4841917bd9d2b44a6c209ec4476e889ee141952e7f2487d298cf0498e6","abstract_canon_sha256":"06ae7352478e54172663561e613b0f716981282b9a629b1e11252a3a8150742f"},"schema_version":"1.0"},"canonical_sha256":"e6202fe887b512e82e98239ecdf936d550f33c68abfc95be05d6015cedecc1d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:54.109478Z","signature_b64":"hIcsJZqRfGauR6HBKAj+bwdn3cZCH4xoxfZSbTlPavIbpzIs9GoQaKzLVDDPNuV4BS4Fgk6g8DQCa97mIvjuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6202fe887b512e82e98239ecdf936d550f33c68abfc95be05d6015cedecc1d4","last_reissued_at":"2026-07-05T11:42:54.109016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:54.109016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14508","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":"2026-07-05T11:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Z9k5OagqelL3bnuGRElowlaieWO13wGjBKY32He6tdixC4wgJQ9eNx2ZiqygkOEz+Un63pSgGt7lnLSka+JDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:50:00.137860Z"},"content_sha256":"60609b026a115f2e0609fc47edf8d1530c95be9e492052d490fcf925315fad68","schema_version":"1.0","event_id":"sha256:60609b026a115f2e0609fc47edf8d1530c95be9e492052d490fcf925315fad68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4YQC72EHWUJOQLUYEOPM36JW2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less is More: Adaptive Coverage for Synthetic Training Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Max Springer, MohammadHossein Bateni, MohammadTaghi Hajiaghayi, Neslihan Bulut, Sasan Tavakkol, Vincent Cohen-Addad","submitted_at":"2025-04-20T06:45:16Z","abstract_excerpt":"Synthetic training data generation with Large Language Models (LLMs) like Google's Gemma and OpenAI's GPT offer a promising solution to the challenge of obtaining large, labeled datasets for training classifiers. When rapid model deployment is critical, such as in classifying emerging social media trends or combating new forms of online abuse tied to current events, the ability to generate training data is invaluable. While prior research has examined the comparability of synthetic data to human-labeled data, this study introduces a novel sampling algorithm, based on the maximum coverage probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14508","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/2504.14508/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":"2026-07-05T11:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jex3D8P6h1q1gctm9law6GML/X3sgomN95X0xy1/sfmsIdPP+ImXyf9DhsFtnEKJFZHWlclOl/a/Z1vkmksYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:50:00.138552Z"},"content_sha256":"c04d564909b8f2c7c0b8539a5b772a927937ac9978436f8e6494628b4c116791","schema_version":"1.0","event_id":"sha256:c04d564909b8f2c7c0b8539a5b772a927937ac9978436f8e6494628b4c116791"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4YQC72EHWUJOQLUYEOPM36JW2V/bundle.json","state_url":"https://pith.science/pith/4YQC72EHWUJOQLUYEOPM36JW2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4YQC72EHWUJOQLUYEOPM36JW2V/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":"2026-08-18T01:50:00Z","links":{"resolver":"https://pith.science/pith/4YQC72EHWUJOQLUYEOPM36JW2V","bundle":"https://pith.science/pith/4YQC72EHWUJOQLUYEOPM36JW2V/bundle.json","state":"https://pith.science/pith/4YQC72EHWUJOQLUYEOPM36JW2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4YQC72EHWUJOQLUYEOPM36JW2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4YQC72EHWUJOQLUYEOPM36JW2V","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":"06ae7352478e54172663561e613b0f716981282b9a629b1e11252a3a8150742f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T06:45:16Z","title_canon_sha256":"912eda4841917bd9d2b44a6c209ec4476e889ee141952e7f2487d298cf0498e6"},"schema_version":"1.0","source":{"id":"2504.14508","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14508","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14508v2","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14508","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"4YQC72EHWUJO","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"4YQC72EHWUJOQLUY","created_at":"2026-07-05T11:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"4YQC72EH","created_at":"2026-07-05T11:42:54Z"}],"graph_snapshots":[{"event_id":"sha256:c04d564909b8f2c7c0b8539a5b772a927937ac9978436f8e6494628b4c116791","target":"graph","created_at":"2026-07-05T11:42:54Z","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/2504.14508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Synthetic training data generation with Large Language Models (LLMs) like Google's Gemma and OpenAI's GPT offer a promising solution to the challenge of obtaining large, labeled datasets for training classifiers. When rapid model deployment is critical, such as in classifying emerging social media trends or combating new forms of online abuse tied to current events, the ability to generate training data is invaluable. While prior research has examined the comparability of synthetic data to human-labeled data, this study introduces a novel sampling algorithm, based on the maximum coverage probl","authors_text":"Max Springer, MohammadHossein Bateni, MohammadTaghi Hajiaghayi, Neslihan Bulut, Sasan Tavakkol, Vincent Cohen-Addad","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T06:45:16Z","title":"Less is More: Adaptive Coverage for Synthetic Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14508","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":"sha256:60609b026a115f2e0609fc47edf8d1530c95be9e492052d490fcf925315fad68","target":"record","created_at":"2026-07-05T11:42:54Z","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":"06ae7352478e54172663561e613b0f716981282b9a629b1e11252a3a8150742f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-20T06:45:16Z","title_canon_sha256":"912eda4841917bd9d2b44a6c209ec4476e889ee141952e7f2487d298cf0498e6"},"schema_version":"1.0","source":{"id":"2504.14508","kind":"arxiv","version":2}},"canonical_sha256":"e6202fe887b512e82e98239ecdf936d550f33c68abfc95be05d6015cedecc1d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6202fe887b512e82e98239ecdf936d550f33c68abfc95be05d6015cedecc1d4","first_computed_at":"2026-07-05T11:42:54.109016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:54.109016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hIcsJZqRfGauR6HBKAj+bwdn3cZCH4xoxfZSbTlPavIbpzIs9GoQaKzLVDDPNuV4BS4Fgk6g8DQCa97mIvjuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:54.109478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14508","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60609b026a115f2e0609fc47edf8d1530c95be9e492052d490fcf925315fad68","sha256:c04d564909b8f2c7c0b8539a5b772a927937ac9978436f8e6494628b4c116791"],"state_sha256":"017d456c998698cf4267cccfd24a63946d5a730ce00788f96b773abb7e92c05a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OL8KenaPohTTwRAU2TuhTiR2edogJ6Lj/1G2Bn0eTAHx4aqyZb2aa8o2y9RXVAm0Ef8AEVCbrk56d9bECxcgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:50:00.144710Z","bundle_sha256":"179ca9626c7dbede6470ca0d84f8202224d338bedb2c7456c62e386e07168dc3"}}