{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MCIKMJQUMGY64GQXM5P6HM6WGR","short_pith_number":"pith:MCIKMJQU","canonical_record":{"source":{"id":"2506.03593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T05:48:20Z","cross_cats_sorted":[],"title_canon_sha256":"f4deace009c30c7a55d902c7a622e969ac564415d98e696830c1a3d5e5465676","abstract_canon_sha256":"f3e8604602a64e59ab095816886f9df161c53ae854a9a475dec85621b4bb163a"},"schema_version":"1.0"},"canonical_sha256":"6090a6261461b1ee1a17675fe3b3d6347f0a7669209e8b46c30439180b134f43","source":{"kind":"arxiv","id":"2506.03593","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03593","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03593v1","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03593","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"MCIKMJQUMGY6","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"MCIKMJQUMGY64GQX","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"MCIKMJQU","created_at":"2026-07-05T11:15:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MCIKMJQUMGY64GQXM5P6HM6WGR","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T05:48:20Z","cross_cats_sorted":[],"title_canon_sha256":"f4deace009c30c7a55d902c7a622e969ac564415d98e696830c1a3d5e5465676","abstract_canon_sha256":"f3e8604602a64e59ab095816886f9df161c53ae854a9a475dec85621b4bb163a"},"schema_version":"1.0"},"canonical_sha256":"6090a6261461b1ee1a17675fe3b3d6347f0a7669209e8b46c30439180b134f43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:48.493146Z","signature_b64":"dOLTsTzrD421T1rWeRqN+jdXqhwbChHRsalZRs85iulJoOoPhubfO8AOkg6au6nj5WS66gwI937jdqtYD2KeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6090a6261461b1ee1a17675fe3b3d6347f0a7669209e8b46c30439180b134f43","last_reissued_at":"2026-07-05T11:15:48.492675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:48.492675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03593","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":"2026-07-05T11:15:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m39UOJhEqhyaz6oMW+MyDk/RNOmz/K19xaw2e0j7mz9vJeTaa/QfIxiNBbFF2utJ66g85xVFEiXpEjPzvg8OAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:30:58.275701Z"},"content_sha256":"09cc2164476ec10c8758223c294aef3bf2616eb1ee884d1d46bf3c8bb61d639a","schema_version":"1.0","event_id":"sha256:09cc2164476ec10c8758223c294aef3bf2616eb1ee884d1d46bf3c8bb61d639a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MCIKMJQUMGY64GQXM5P6HM6WGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is linguistically-motivated data augmentation worth it?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Palmer, Michael Ginn, Ray Groshan","submitted_at":"2025-06-04T05:48:20Z","abstract_excerpt":"Data augmentation, a widely-employed technique for addressing data scarcity, involves generating synthetic data examples which are then used to augment available training data. Researchers have seen surprising success from simple methods, such as random perturbations from natural examples, where models seem to benefit even from data with nonsense words, or data that doesn't conform to the rules of the language. A second line of research produces synthetic data that does in fact follow all linguistic constraints; these methods require some linguistic expertise and are generally more challenging"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03593","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/2506.03593/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":"2026-07-05T11:15:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hcr3uAqbV+D4fh/Bj0ahKTYqg7wqI/wRCbUZ0BqOHPEtCYXVTjeCaCrd2uPwDZPil68qEmfnIpAFbZuMlUHuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:30:58.276844Z"},"content_sha256":"2f56f5fee38760efd6a47ad5cce2ac36c5e898be8faeb7f2c4cd22973ce27031","schema_version":"1.0","event_id":"sha256:2f56f5fee38760efd6a47ad5cce2ac36c5e898be8faeb7f2c4cd22973ce27031"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCIKMJQUMGY64GQXM5P6HM6WGR/bundle.json","state_url":"https://pith.science/pith/MCIKMJQUMGY64GQXM5P6HM6WGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCIKMJQUMGY64GQXM5P6HM6WGR/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":"2026-08-10T06:30:58Z","links":{"resolver":"https://pith.science/pith/MCIKMJQUMGY64GQXM5P6HM6WGR","bundle":"https://pith.science/pith/MCIKMJQUMGY64GQXM5P6HM6WGR/bundle.json","state":"https://pith.science/pith/MCIKMJQUMGY64GQXM5P6HM6WGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCIKMJQUMGY64GQXM5P6HM6WGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MCIKMJQUMGY64GQXM5P6HM6WGR","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":"f3e8604602a64e59ab095816886f9df161c53ae854a9a475dec85621b4bb163a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T05:48:20Z","title_canon_sha256":"f4deace009c30c7a55d902c7a622e969ac564415d98e696830c1a3d5e5465676"},"schema_version":"1.0","source":{"id":"2506.03593","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03593","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03593v1","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03593","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_12","alias_value":"MCIKMJQUMGY6","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_16","alias_value":"MCIKMJQUMGY64GQX","created_at":"2026-07-05T11:15:48Z"},{"alias_kind":"pith_short_8","alias_value":"MCIKMJQU","created_at":"2026-07-05T11:15:48Z"}],"graph_snapshots":[{"event_id":"sha256:2f56f5fee38760efd6a47ad5cce2ac36c5e898be8faeb7f2c4cd22973ce27031","target":"graph","created_at":"2026-07-05T11:15:48Z","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/2506.03593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation, a widely-employed technique for addressing data scarcity, involves generating synthetic data examples which are then used to augment available training data. Researchers have seen surprising success from simple methods, such as random perturbations from natural examples, where models seem to benefit even from data with nonsense words, or data that doesn't conform to the rules of the language. A second line of research produces synthetic data that does in fact follow all linguistic constraints; these methods require some linguistic expertise and are generally more challenging","authors_text":"Alexis Palmer, Michael Ginn, Ray Groshan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T05:48:20Z","title":"Is linguistically-motivated data augmentation worth it?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03593","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":"sha256:09cc2164476ec10c8758223c294aef3bf2616eb1ee884d1d46bf3c8bb61d639a","target":"record","created_at":"2026-07-05T11:15:48Z","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":"f3e8604602a64e59ab095816886f9df161c53ae854a9a475dec85621b4bb163a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T05:48:20Z","title_canon_sha256":"f4deace009c30c7a55d902c7a622e969ac564415d98e696830c1a3d5e5465676"},"schema_version":"1.0","source":{"id":"2506.03593","kind":"arxiv","version":1}},"canonical_sha256":"6090a6261461b1ee1a17675fe3b3d6347f0a7669209e8b46c30439180b134f43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6090a6261461b1ee1a17675fe3b3d6347f0a7669209e8b46c30439180b134f43","first_computed_at":"2026-07-05T11:15:48.492675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:48.492675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dOLTsTzrD421T1rWeRqN+jdXqhwbChHRsalZRs85iulJoOoPhubfO8AOkg6au6nj5WS66gwI937jdqtYD2KeCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:48.493146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03593","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09cc2164476ec10c8758223c294aef3bf2616eb1ee884d1d46bf3c8bb61d639a","sha256:2f56f5fee38760efd6a47ad5cce2ac36c5e898be8faeb7f2c4cd22973ce27031"],"state_sha256":"68ed0a39191ab9f92f86bed4edd3a748dbf4e475963145bf798cf6d3eabc8701"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sP8i8WvaFUYDFGwuNKDuYR1RCWB6aePOzb3YKdHvM82dLgkSl+OlC3S4bBltkzjWA1mUIBMxAqxf9tmupoOUDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:30:58.284127Z","bundle_sha256":"07c6980e9500d5eec8adb02e58ab4d15fb475dde787a49848b7b302044ec47e1"}}