{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SGG62JGT663ZZHYXBO7AE5WHZR","short_pith_number":"pith:SGG62JGT","canonical_record":{"source":{"id":"2402.13482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T02:45:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c7977ac631d1353384a44507b10fc852c9a68d09e1d38ef1557c5739a23ea205","abstract_canon_sha256":"df0b7ee1a6ebda22923afe26c8cc22eba19aad069bb71707e0b73559745429a4"},"schema_version":"1.0"},"canonical_sha256":"918ded24d3f7b79c9f170bbe0276c7cc48c03f4967a7e6da83d413d11e9a8451","source":{"kind":"arxiv","id":"2402.13482","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13482","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13482v1","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13482","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"SGG62JGT663Z","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"SGG62JGT663ZZHYX","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"SGG62JGT","created_at":"2026-07-05T07:47:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SGG62JGT663ZZHYXBO7AE5WHZR","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T02:45:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c7977ac631d1353384a44507b10fc852c9a68d09e1d38ef1557c5739a23ea205","abstract_canon_sha256":"df0b7ee1a6ebda22923afe26c8cc22eba19aad069bb71707e0b73559745429a4"},"schema_version":"1.0"},"canonical_sha256":"918ded24d3f7b79c9f170bbe0276c7cc48c03f4967a7e6da83d413d11e9a8451","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:33.048929Z","signature_b64":"YlclD8kiBpcKhLUTXAKabq5mXL8aEvnqWjI4n1jrA5vduLZRRJoXmjp3Z9F+yhyEdA2LKyOvbCL0GUyFopsdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"918ded24d3f7b79c9f170bbe0276c7cc48c03f4967a7e6da83d413d11e9a8451","last_reissued_at":"2026-07-05T07:47:33.048398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:33.048398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13482","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3j3EfPcYZGX/sfx+ozB/lPeiq9C9R+L9PjX6sAIbl3ExfunrxX2LAQGkhhTXBRhVGuJ6B2aa63fN5jYEdHQyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:10:50.668621Z"},"content_sha256":"5a3608b3f9fc5df915222a01f63f614bede1c65eaecd4bd36ad57b2a87fd4181","schema_version":"1.0","event_id":"sha256:5a3608b3f9fc5df915222a01f63f614bede1c65eaecd4bd36ad57b2a87fd4181"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SGG62JGT663ZZHYXBO7AE5WHZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"James Thorne, Jinheon Baek, Minju Seo, Sung Ju Hwang","submitted_at":"2024-02-21T02:45:46Z","abstract_excerpt":"Despite large successes of recent language models on diverse tasks, they suffer from severe performance degeneration in low-resource settings with limited training data available. Many existing works tackle this problem by generating synthetic data from the training data and then training models on them, recently using Large Language Models (LLMs). However, in low-resource settings, the amount of seed data samples to use for data augmentation is very small, which makes generated samples suboptimal and less diverse. To tackle this challenge, we propose a novel method that augments training data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13482","kind":"arxiv","version":1},"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/2402.13482/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":"2026-07-05T07:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfyQm3xmq2RbhWU2jMRuBKw3cVVYLGeoOH0s7RNMdVy6DXONaUqC1iPQjsqmqdUjTNA1Ygq/oLOnGxjfYsf0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:10:50.669017Z"},"content_sha256":"673c17ff2d08af32a3bdf0f6862b891d9b8b96a7507215028f783f0f579210f1","schema_version":"1.0","event_id":"sha256:673c17ff2d08af32a3bdf0f6862b891d9b8b96a7507215028f783f0f579210f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGG62JGT663ZZHYXBO7AE5WHZR/bundle.json","state_url":"https://pith.science/pith/SGG62JGT663ZZHYXBO7AE5WHZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGG62JGT663ZZHYXBO7AE5WHZR/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":"2026-07-07T10:10:50Z","links":{"resolver":"https://pith.science/pith/SGG62JGT663ZZHYXBO7AE5WHZR","bundle":"https://pith.science/pith/SGG62JGT663ZZHYXBO7AE5WHZR/bundle.json","state":"https://pith.science/pith/SGG62JGT663ZZHYXBO7AE5WHZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGG62JGT663ZZHYXBO7AE5WHZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SGG62JGT663ZZHYXBO7AE5WHZR","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":"df0b7ee1a6ebda22923afe26c8cc22eba19aad069bb71707e0b73559745429a4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T02:45:46Z","title_canon_sha256":"c7977ac631d1353384a44507b10fc852c9a68d09e1d38ef1557c5739a23ea205"},"schema_version":"1.0","source":{"id":"2402.13482","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13482","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13482v1","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13482","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"SGG62JGT663Z","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"SGG62JGT663ZZHYX","created_at":"2026-07-05T07:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"SGG62JGT","created_at":"2026-07-05T07:47:33Z"}],"graph_snapshots":[{"event_id":"sha256:673c17ff2d08af32a3bdf0f6862b891d9b8b96a7507215028f783f0f579210f1","target":"graph","created_at":"2026-07-05T07:47:33Z","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/2402.13482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite large successes of recent language models on diverse tasks, they suffer from severe performance degeneration in low-resource settings with limited training data available. Many existing works tackle this problem by generating synthetic data from the training data and then training models on them, recently using Large Language Models (LLMs). However, in low-resource settings, the amount of seed data samples to use for data augmentation is very small, which makes generated samples suboptimal and less diverse. To tackle this challenge, we propose a novel method that augments training data","authors_text":"James Thorne, Jinheon Baek, Minju Seo, Sung Ju Hwang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T02:45:46Z","title":"Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13482","kind":"arxiv","version":1},"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":"sha256:5a3608b3f9fc5df915222a01f63f614bede1c65eaecd4bd36ad57b2a87fd4181","target":"record","created_at":"2026-07-05T07:47:33Z","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":"df0b7ee1a6ebda22923afe26c8cc22eba19aad069bb71707e0b73559745429a4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T02:45:46Z","title_canon_sha256":"c7977ac631d1353384a44507b10fc852c9a68d09e1d38ef1557c5739a23ea205"},"schema_version":"1.0","source":{"id":"2402.13482","kind":"arxiv","version":1}},"canonical_sha256":"918ded24d3f7b79c9f170bbe0276c7cc48c03f4967a7e6da83d413d11e9a8451","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"918ded24d3f7b79c9f170bbe0276c7cc48c03f4967a7e6da83d413d11e9a8451","first_computed_at":"2026-07-05T07:47:33.048398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:33.048398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YlclD8kiBpcKhLUTXAKabq5mXL8aEvnqWjI4n1jrA5vduLZRRJoXmjp3Z9F+yhyEdA2LKyOvbCL0GUyFopsdDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:33.048929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13482","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a3608b3f9fc5df915222a01f63f614bede1c65eaecd4bd36ad57b2a87fd4181","sha256:673c17ff2d08af32a3bdf0f6862b891d9b8b96a7507215028f783f0f579210f1"],"state_sha256":"8535421513c5120817fbf2e8874f8308fc958c8e81b68f0797c92e2f73cd7e5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xZiPGWmK7fWy6vatri695sdzTLmQeQ6elrb1MzbzN+tDMNgwNAHAq3ajol84g+sY/P02IMbg9AggKEIO+ahkCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:10:50.670972Z","bundle_sha256":"9f9b883ed3216048688457076fe0c2377f75f3143b2ab66930223d86f9a92f1a"}}