{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GNDTH2KOS25IVC3B3PBDOLGZEE","short_pith_number":"pith:GNDTH2KO","schema_version":"1.0","canonical_sha256":"334733e94e96ba8a8b61dbc2372cd921384b5758f05a72fcdadd7f8560b27b54","source":{"kind":"arxiv","id":"2112.13969","version":1},"attestation_state":"computed","paper":{"title":"LINDA: Unsupervised Learning to Interpolate in Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kyunghyun Cho, Seohyeong Jeong, Yekyung Kim","submitted_at":"2021-12-28T02:56:41Z","abstract_excerpt":"Despite the success of mixup in data augmentation, its applicability to natural language processing (NLP) tasks has been limited due to the discrete and variable-length nature of natural languages. Recent studies have thus relied on domain-specific heuristics and manually crafted resources, such as dictionaries, in order to apply mixup in NLP. In this paper, we instead propose an unsupervised learning approach to text interpolation for the purpose of data augmentation, to which we refer as \"Learning to INterpolate for Data Augmentation\" (LINDA), that does not require any heuristics nor manuall"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2112.13969","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-28T02:56:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48c6bc6f1b6c47a15b1cf77676f652585d9b6950d42f8b040271824dbb713407","abstract_canon_sha256":"d326737382e6d3f5ce19a23d883aa5d01fdacddadc480027e556060192e78881"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:16.967195Z","signature_b64":"1J8iL1+9haN8dl+bWda9vk9RCgvP3Ao8RCaaesIpeWKpqTQT6u16+pEWnhOZOPLdb+rVlmI9tFxmOJsrm8WaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"334733e94e96ba8a8b61dbc2372cd921384b5758f05a72fcdadd7f8560b27b54","last_reissued_at":"2026-07-05T03:44:16.966774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:16.966774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LINDA: Unsupervised Learning to Interpolate in Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kyunghyun Cho, Seohyeong Jeong, Yekyung Kim","submitted_at":"2021-12-28T02:56:41Z","abstract_excerpt":"Despite the success of mixup in data augmentation, its applicability to natural language processing (NLP) tasks has been limited due to the discrete and variable-length nature of natural languages. Recent studies have thus relied on domain-specific heuristics and manually crafted resources, such as dictionaries, in order to apply mixup in NLP. In this paper, we instead propose an unsupervised learning approach to text interpolation for the purpose of data augmentation, to which we refer as \"Learning to INterpolate for Data Augmentation\" (LINDA), that does not require any heuristics nor manuall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13969","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/2112.13969/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2112.13969","created_at":"2026-07-05T03:44:16.966842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.13969v1","created_at":"2026-07-05T03:44:16.966842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13969","created_at":"2026-07-05T03:44:16.966842+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNDTH2KOS25I","created_at":"2026-07-05T03:44:16.966842+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNDTH2KOS25IVC3B","created_at":"2026-07-05T03:44:16.966842+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNDTH2KO","created_at":"2026-07-05T03:44:16.966842+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2303.17760","citing_title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE","json":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE.json","graph_json":"https://pith.science/api/pith-number/GNDTH2KOS25IVC3B3PBDOLGZEE/graph.json","events_json":"https://pith.science/api/pith-number/GNDTH2KOS25IVC3B3PBDOLGZEE/events.json","paper":"https://pith.science/paper/GNDTH2KO"},"agent_actions":{"view_html":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE","download_json":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE.json","view_paper":"https://pith.science/paper/GNDTH2KO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.13969&json=true","fetch_graph":"https://pith.science/api/pith-number/GNDTH2KOS25IVC3B3PBDOLGZEE/graph.json","fetch_events":"https://pith.science/api/pith-number/GNDTH2KOS25IVC3B3PBDOLGZEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE/action/storage_attestation","attest_author":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE/action/author_attestation","sign_citation":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE/action/citation_signature","submit_replication":"https://pith.science/pith/GNDTH2KOS25IVC3B3PBDOLGZEE/action/replication_record"}},"created_at":"2026-07-05T03:44:16.966842+00:00","updated_at":"2026-07-05T03:44:16.966842+00:00"}