{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RG2I3ENCWO42JJJNC2HSM4DZUH","short_pith_number":"pith:RG2I3ENC","canonical_record":{"source":{"id":"2004.12239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-25T21:37:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3b4f9d97247ee1c0e11548c5e0f8567ae96d6450a88cbad25a757b0ebfb9d91","abstract_canon_sha256":"bf3a0760c115399b092a3698b72364c100a80ae07c827a16cbb95a8354977d8c"},"schema_version":"1.0"},"canonical_sha256":"89b48d91a2b3b9a4a52d168f267079a1ce863058325f988203f9dc764b6c4029","source":{"kind":"arxiv","id":"2004.12239","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12239","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12239v1","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12239","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"pith_short_12","alias_value":"RG2I3ENCWO42","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"pith_short_16","alias_value":"RG2I3ENCWO42JJJN","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"pith_short_8","alias_value":"RG2I3ENC","created_at":"2026-07-05T00:58:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RG2I3ENCWO42JJJNC2HSM4DZUH","target":"record","payload":{"canonical_record":{"source":{"id":"2004.12239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-25T21:37:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3b4f9d97247ee1c0e11548c5e0f8567ae96d6450a88cbad25a757b0ebfb9d91","abstract_canon_sha256":"bf3a0760c115399b092a3698b72364c100a80ae07c827a16cbb95a8354977d8c"},"schema_version":"1.0"},"canonical_sha256":"89b48d91a2b3b9a4a52d168f267079a1ce863058325f988203f9dc764b6c4029","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:13.775536Z","signature_b64":"OCC3OWmUo6tELe9GIXWycTBcriuWfDENIyJ44nj0drkHpWtd34f2HIEy3ro7xVUGIRqLyrRJBIcBDR3w3Q8WDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89b48d91a2b3b9a4a52d168f267079a1ce863058325f988203f9dc764b6c4029","last_reissued_at":"2026-07-05T00:58:13.775165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:13.775165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.12239","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":"2026-07-05T00:58:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HxcwcqJ5KatB13d4x/N7QtG4Ih3fIst3dYDzr1xxMI1zZlPWknU5hCQjxmTIxAMVcusmOxXTTJgDmD9BSJ4ZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:58:26.527650Z"},"content_sha256":"098232b7ebf5ab3c9688581c516a28382491f9dd7cd9cb5df4ffe3e009c33b08","schema_version":"1.0","event_id":"sha256:098232b7ebf5ab3c9688581c516a28382491f9dd7cd9cb5df4ffe3e009c33b08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RG2I3ENCWO42JJJNC2HSM4DZUH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Diyi Yang, Jiaao Chen, Zichao Yang","submitted_at":"2020-04-25T21:37:36Z","abstract_excerpt":"This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in hidden space. Moreover, we leverage recent advances in data augmentation to guess low-entropy labels for unlabeled data, hence making them as easy to use as labeled data.By mixing labeled, unlabeled and augmented data, MixText significantly outperformed current pre-trained and fined-tuned models and other state-of-the-art semi-supervised learning methods on s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12239","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/2004.12239/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":"2026-07-05T00:58:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yc6BUlW2o0VsmA77kKRQCICaqpF8VTvGPyXboJs86G7s7Wdzzi864/iagPkbuWF9iUfX/JqGCtYUB98zCuDsCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:58:26.528295Z"},"content_sha256":"e70edc1eef566b15592b5dbf49c492bf0195ba2facf60bd34c433c5f63403114","schema_version":"1.0","event_id":"sha256:e70edc1eef566b15592b5dbf49c492bf0195ba2facf60bd34c433c5f63403114"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RG2I3ENCWO42JJJNC2HSM4DZUH/bundle.json","state_url":"https://pith.science/pith/RG2I3ENCWO42JJJNC2HSM4DZUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RG2I3ENCWO42JJJNC2HSM4DZUH/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":"2026-08-08T20:58:26Z","links":{"resolver":"https://pith.science/pith/RG2I3ENCWO42JJJNC2HSM4DZUH","bundle":"https://pith.science/pith/RG2I3ENCWO42JJJNC2HSM4DZUH/bundle.json","state":"https://pith.science/pith/RG2I3ENCWO42JJJNC2HSM4DZUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RG2I3ENCWO42JJJNC2HSM4DZUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RG2I3ENCWO42JJJNC2HSM4DZUH","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":"bf3a0760c115399b092a3698b72364c100a80ae07c827a16cbb95a8354977d8c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-25T21:37:36Z","title_canon_sha256":"a3b4f9d97247ee1c0e11548c5e0f8567ae96d6450a88cbad25a757b0ebfb9d91"},"schema_version":"1.0","source":{"id":"2004.12239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12239","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12239v1","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12239","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"pith_short_12","alias_value":"RG2I3ENCWO42","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"pith_short_16","alias_value":"RG2I3ENCWO42JJJN","created_at":"2026-07-05T00:58:13Z"},{"alias_kind":"pith_short_8","alias_value":"RG2I3ENC","created_at":"2026-07-05T00:58:13Z"}],"graph_snapshots":[{"event_id":"sha256:e70edc1eef566b15592b5dbf49c492bf0195ba2facf60bd34c433c5f63403114","target":"graph","created_at":"2026-07-05T00:58:13Z","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/2004.12239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents MixText, a semi-supervised learning method for text classification, which uses our newly designed data augmentation method called TMix. TMix creates a large amount of augmented training samples by interpolating text in hidden space. Moreover, we leverage recent advances in data augmentation to guess low-entropy labels for unlabeled data, hence making them as easy to use as labeled data.By mixing labeled, unlabeled and augmented data, MixText significantly outperformed current pre-trained and fined-tuned models and other state-of-the-art semi-supervised learning methods on s","authors_text":"Diyi Yang, Jiaao Chen, Zichao Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-25T21:37:36Z","title":"MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12239","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":"sha256:098232b7ebf5ab3c9688581c516a28382491f9dd7cd9cb5df4ffe3e009c33b08","target":"record","created_at":"2026-07-05T00:58:13Z","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":"bf3a0760c115399b092a3698b72364c100a80ae07c827a16cbb95a8354977d8c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-25T21:37:36Z","title_canon_sha256":"a3b4f9d97247ee1c0e11548c5e0f8567ae96d6450a88cbad25a757b0ebfb9d91"},"schema_version":"1.0","source":{"id":"2004.12239","kind":"arxiv","version":1}},"canonical_sha256":"89b48d91a2b3b9a4a52d168f267079a1ce863058325f988203f9dc764b6c4029","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89b48d91a2b3b9a4a52d168f267079a1ce863058325f988203f9dc764b6c4029","first_computed_at":"2026-07-05T00:58:13.775165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:58:13.775165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OCC3OWmUo6tELe9GIXWycTBcriuWfDENIyJ44nj0drkHpWtd34f2HIEy3ro7xVUGIRqLyrRJBIcBDR3w3Q8WDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:58:13.775536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.12239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:098232b7ebf5ab3c9688581c516a28382491f9dd7cd9cb5df4ffe3e009c33b08","sha256:e70edc1eef566b15592b5dbf49c492bf0195ba2facf60bd34c433c5f63403114"],"state_sha256":"3fdbfbcd157ce31d1da7cdd070026b39f5f3bfeca0eb9e60a9c64aade7096a6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XzVlNENjpnyFnqKHI7MR0U6vq7xdDeW2t8vIs4HgKPqAWbU6L7S0WQVaKjTRxxBKGQzcsCrtfumiOzMh74GKDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:58:26.534101Z","bundle_sha256":"764b7a352ecd4ccd0dde43b61d3ec29439715e8cc60579db3dcc7fb8fb66387b"}}