{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XUYGKI35J622I4TTBBMGRPES5L","short_pith_number":"pith:XUYGKI35","canonical_record":{"source":{"id":"2507.14590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T12:23:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61765c1137c1c277d5abf4b76007cb3e9c6812c79bb9a5576c37fd1074acc3eb","abstract_canon_sha256":"a4b5b49dbc3c6f6bd8922bff7c1afad59bce856a6868071d0803097687fa46b2"},"schema_version":"1.0"},"canonical_sha256":"bd3065237d4fb5a47273085868bc92eae20a217256a7d943c696142776e6ea96","source":{"kind":"arxiv","id":"2507.14590","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14590","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14590v1","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14590","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"XUYGKI35J622","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_16","alias_value":"XUYGKI35J622I4TT","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_8","alias_value":"XUYGKI35","created_at":"2026-07-05T11:40:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XUYGKI35J622I4TTBBMGRPES5L","target":"record","payload":{"canonical_record":{"source":{"id":"2507.14590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T12:23:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61765c1137c1c277d5abf4b76007cb3e9c6812c79bb9a5576c37fd1074acc3eb","abstract_canon_sha256":"a4b5b49dbc3c6f6bd8922bff7c1afad59bce856a6868071d0803097687fa46b2"},"schema_version":"1.0"},"canonical_sha256":"bd3065237d4fb5a47273085868bc92eae20a217256a7d943c696142776e6ea96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:10.084117Z","signature_b64":"3eorIPE1zsc2CutekeBP3WlicBo0kYhgIM3Rp984x5DCSw6ZsLmB5wOoIi9v3NzoZ7jLvogxKpA+y9rtPBTRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd3065237d4fb5a47273085868bc92eae20a217256a7d943c696142776e6ea96","last_reissued_at":"2026-07-05T11:40:10.083625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:10.083625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.14590","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":"2026-07-05T11:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1CcYsy6AcxvQGwZwX+u9H7Op3F/NGztGFNDr6gUsd9Z2gGwit+f0OZoICCWXOeYfWcCe3vPDvJ2GqMoXRXLdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:47:40.416489Z"},"content_sha256":"d2f6d2176d240b4c47dbda558da58ecf5280378bcd49737b1ad8b84b3169a541","schema_version":"1.0","event_id":"sha256:d2f6d2176d240b4c47dbda558da58ecf5280378bcd49737b1ad8b84b3169a541"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XUYGKI35J622I4TTBBMGRPES5L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Backtranslation and paraphrasing in the LLM era? Comparing data augmentation methods for emotion classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jan Koco\\'n, {\\L}ukasz Radli\\'nski, Mateusz Gu\\'sciora","submitted_at":"2025-07-19T12:23:20Z","abstract_excerpt":"Numerous domain-specific machine learning tasks struggle with data scarcity and class imbalance. This paper systematically explores data augmentation methods for NLP, particularly through large language models like GPT. The purpose of this paper is to examine and evaluate whether traditional methods such as paraphrasing and backtranslation can leverage a new generation of models to achieve comparable performance to purely generative methods. Methods aimed at solving the problem of data scarcity and utilizing ChatGPT were chosen, as well as an exemplary dataset. We conducted a series of experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14590","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/2507.14590/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":"2026-07-05T11:40:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"InP+MdAOb0xXIi1gNjpToFdfwlr4aSaEht8S6WzNNnh93upH3jRPaT7WfccYKfIpTDEE94th32MMtrz+vc0GBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:47:40.416995Z"},"content_sha256":"7d38257d0f9a737cc8e1e04e5cf7a9b46126ee4468767d782145860a8c68ad38","schema_version":"1.0","event_id":"sha256:7d38257d0f9a737cc8e1e04e5cf7a9b46126ee4468767d782145860a8c68ad38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUYGKI35J622I4TTBBMGRPES5L/bundle.json","state_url":"https://pith.science/pith/XUYGKI35J622I4TTBBMGRPES5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUYGKI35J622I4TTBBMGRPES5L/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":"2026-08-10T01:47:40Z","links":{"resolver":"https://pith.science/pith/XUYGKI35J622I4TTBBMGRPES5L","bundle":"https://pith.science/pith/XUYGKI35J622I4TTBBMGRPES5L/bundle.json","state":"https://pith.science/pith/XUYGKI35J622I4TTBBMGRPES5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUYGKI35J622I4TTBBMGRPES5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XUYGKI35J622I4TTBBMGRPES5L","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":"a4b5b49dbc3c6f6bd8922bff7c1afad59bce856a6868071d0803097687fa46b2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T12:23:20Z","title_canon_sha256":"61765c1137c1c277d5abf4b76007cb3e9c6812c79bb9a5576c37fd1074acc3eb"},"schema_version":"1.0","source":{"id":"2507.14590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14590","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14590v1","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14590","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_12","alias_value":"XUYGKI35J622","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_16","alias_value":"XUYGKI35J622I4TT","created_at":"2026-07-05T11:40:10Z"},{"alias_kind":"pith_short_8","alias_value":"XUYGKI35","created_at":"2026-07-05T11:40:10Z"}],"graph_snapshots":[{"event_id":"sha256:7d38257d0f9a737cc8e1e04e5cf7a9b46126ee4468767d782145860a8c68ad38","target":"graph","created_at":"2026-07-05T11:40:10Z","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/2507.14590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous domain-specific machine learning tasks struggle with data scarcity and class imbalance. This paper systematically explores data augmentation methods for NLP, particularly through large language models like GPT. The purpose of this paper is to examine and evaluate whether traditional methods such as paraphrasing and backtranslation can leverage a new generation of models to achieve comparable performance to purely generative methods. Methods aimed at solving the problem of data scarcity and utilizing ChatGPT were chosen, as well as an exemplary dataset. We conducted a series of experim","authors_text":"Jan Koco\\'n, {\\L}ukasz Radli\\'nski, Mateusz Gu\\'sciora","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T12:23:20Z","title":"Backtranslation and paraphrasing in the LLM era? Comparing data augmentation methods for emotion classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14590","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:d2f6d2176d240b4c47dbda558da58ecf5280378bcd49737b1ad8b84b3169a541","target":"record","created_at":"2026-07-05T11:40:10Z","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":"a4b5b49dbc3c6f6bd8922bff7c1afad59bce856a6868071d0803097687fa46b2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T12:23:20Z","title_canon_sha256":"61765c1137c1c277d5abf4b76007cb3e9c6812c79bb9a5576c37fd1074acc3eb"},"schema_version":"1.0","source":{"id":"2507.14590","kind":"arxiv","version":1}},"canonical_sha256":"bd3065237d4fb5a47273085868bc92eae20a217256a7d943c696142776e6ea96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd3065237d4fb5a47273085868bc92eae20a217256a7d943c696142776e6ea96","first_computed_at":"2026-07-05T11:40:10.083625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:10.083625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3eorIPE1zsc2CutekeBP3WlicBo0kYhgIM3Rp984x5DCSw6ZsLmB5wOoIi9v3NzoZ7jLvogxKpA+y9rtPBTRDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:10.084117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2f6d2176d240b4c47dbda558da58ecf5280378bcd49737b1ad8b84b3169a541","sha256:7d38257d0f9a737cc8e1e04e5cf7a9b46126ee4468767d782145860a8c68ad38"],"state_sha256":"fed5dd10b7f8a66104243d417f9981d7b17b05931bf9c070242ab7b2dc19d39a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kWTPcMofZWxscoM9xCzELfhDSzrVqkWpd8Koo9ryoLLe2HhZrFmgr3UfdTOnaIb9ap3kdfjfjO+7ZXM/r7o6CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:47:40.421578Z","bundle_sha256":"d5fe1e5ff4f02ffb6406b73fa5044ee88719de600e233a045f7d6fb0168ac0bf"}}