{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SYLCWLVE3IA4GEPHURO3NQ374G","short_pith_number":"pith:SYLCWLVE","canonical_record":{"source":{"id":"2011.08626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-17T13:39:05Z","cross_cats_sorted":[],"title_canon_sha256":"fb1e7d30d1c7552f88d8a6027d3176e20fa94834d6f9d074044679710467a253","abstract_canon_sha256":"8f82f4a9b2f2939014118e130e619dc891d9f12b66aa2374b0cb6fc8fe874bfc"},"schema_version":"1.0"},"canonical_sha256":"96162b2ea4da01c311e7a45db6c37fe188a5d6d03de7ecd4853cbfd479f67fcc","source":{"kind":"arxiv","id":"2011.08626","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.08626","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"arxiv_version","alias_value":"2011.08626v2","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08626","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_12","alias_value":"SYLCWLVE3IA4","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_16","alias_value":"SYLCWLVE3IA4GEPH","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_8","alias_value":"SYLCWLVE","created_at":"2026-07-05T01:53:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SYLCWLVE3IA4GEPHURO3NQ374G","target":"record","payload":{"canonical_record":{"source":{"id":"2011.08626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-17T13:39:05Z","cross_cats_sorted":[],"title_canon_sha256":"fb1e7d30d1c7552f88d8a6027d3176e20fa94834d6f9d074044679710467a253","abstract_canon_sha256":"8f82f4a9b2f2939014118e130e619dc891d9f12b66aa2374b0cb6fc8fe874bfc"},"schema_version":"1.0"},"canonical_sha256":"96162b2ea4da01c311e7a45db6c37fe188a5d6d03de7ecd4853cbfd479f67fcc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:00.516650Z","signature_b64":"72z/nEJaFtOQt+dWyYyhW88ru7ojfaYrYJxLi4VFgCInUG14y9szoLFhIP7dUNm6lDZl7m0adiV6uAeD6vvIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96162b2ea4da01c311e7a45db6c37fe188a5d6d03de7ecd4853cbfd479f67fcc","last_reissued_at":"2026-07-05T01:53:00.516200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:00.516200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.08626","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:53:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GCcjJA8ZWUmGscZ7owI2FQc71rWYVBS+X91AEXJ6PfNWX8AM5p8YssrIXs6JPX1MoQgLuyI/TmFHz3bDbAdlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:37:43.780315Z"},"content_sha256":"6f3b5cc86e95f538c748c5f08934083eefeaca016871e3bb903ba73c5c95ed8c","schema_version":"1.0","event_id":"sha256:6f3b5cc86e95f538c748c5f08934083eefeaca016871e3bb903ba73c5c95ed8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SYLCWLVE3IA4GEPHURO3NQ374G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chun Fan, Fei Wu, Jiwei Li, Xiaofei Sun, Yuxian Meng, Zijun Sun","submitted_at":"2020-11-17T13:39:05Z","abstract_excerpt":"The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is poorly understood: is semi-supervised learning still beneficial with the presence of large-scale pretraining? should U be used for in-domain LM pretraining or pseudo-label generation? how should the pseudo-label based semi-supervised model be actually implemented? how different semi-supervised strategies affect performances regarding D of different sizes, U"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08626","kind":"arxiv","version":2},"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/2011.08626/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":"2026-07-05T01:53:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FtivsWn1TUY1BU5Ae9Xye4FLrQqsrg3RpF9r6Ajia56/Y5Z00i+719+Ejtg84rKF8871DQzOzHHP7Q9Jj0RGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:37:43.781210Z"},"content_sha256":"75aebcd2dc107b8448ac0edde8d223c3af52317d18bc1751e9ea6c0c5d5e8d50","schema_version":"1.0","event_id":"sha256:75aebcd2dc107b8448ac0edde8d223c3af52317d18bc1751e9ea6c0c5d5e8d50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SYLCWLVE3IA4GEPHURO3NQ374G/bundle.json","state_url":"https://pith.science/pith/SYLCWLVE3IA4GEPHURO3NQ374G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SYLCWLVE3IA4GEPHURO3NQ374G/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":"2026-08-03T15:37:43Z","links":{"resolver":"https://pith.science/pith/SYLCWLVE3IA4GEPHURO3NQ374G","bundle":"https://pith.science/pith/SYLCWLVE3IA4GEPHURO3NQ374G/bundle.json","state":"https://pith.science/pith/SYLCWLVE3IA4GEPHURO3NQ374G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SYLCWLVE3IA4GEPHURO3NQ374G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SYLCWLVE3IA4GEPHURO3NQ374G","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":"8f82f4a9b2f2939014118e130e619dc891d9f12b66aa2374b0cb6fc8fe874bfc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-17T13:39:05Z","title_canon_sha256":"fb1e7d30d1c7552f88d8a6027d3176e20fa94834d6f9d074044679710467a253"},"schema_version":"1.0","source":{"id":"2011.08626","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.08626","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"arxiv_version","alias_value":"2011.08626v2","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08626","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_12","alias_value":"SYLCWLVE3IA4","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_16","alias_value":"SYLCWLVE3IA4GEPH","created_at":"2026-07-05T01:53:00Z"},{"alias_kind":"pith_short_8","alias_value":"SYLCWLVE","created_at":"2026-07-05T01:53:00Z"}],"graph_snapshots":[{"event_id":"sha256:75aebcd2dc107b8448ac0edde8d223c3af52317d18bc1751e9ea6c0c5d5e8d50","target":"graph","created_at":"2026-07-05T01:53:00Z","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/2011.08626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is poorly understood: is semi-supervised learning still beneficial with the presence of large-scale pretraining? should U be used for in-domain LM pretraining or pseudo-label generation? how should the pseudo-label based semi-supervised model be actually implemented? how different semi-supervised strategies affect performances regarding D of different sizes, U","authors_text":"Chun Fan, Fei Wu, Jiwei Li, Xiaofei Sun, Yuxian Meng, Zijun Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-17T13:39:05Z","title":"Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08626","kind":"arxiv","version":2},"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":"sha256:6f3b5cc86e95f538c748c5f08934083eefeaca016871e3bb903ba73c5c95ed8c","target":"record","created_at":"2026-07-05T01:53:00Z","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":"8f82f4a9b2f2939014118e130e619dc891d9f12b66aa2374b0cb6fc8fe874bfc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-17T13:39:05Z","title_canon_sha256":"fb1e7d30d1c7552f88d8a6027d3176e20fa94834d6f9d074044679710467a253"},"schema_version":"1.0","source":{"id":"2011.08626","kind":"arxiv","version":2}},"canonical_sha256":"96162b2ea4da01c311e7a45db6c37fe188a5d6d03de7ecd4853cbfd479f67fcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96162b2ea4da01c311e7a45db6c37fe188a5d6d03de7ecd4853cbfd479f67fcc","first_computed_at":"2026-07-05T01:53:00.516200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:53:00.516200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"72z/nEJaFtOQt+dWyYyhW88ru7ojfaYrYJxLi4VFgCInUG14y9szoLFhIP7dUNm6lDZl7m0adiV6uAeD6vvIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:53:00.516650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.08626","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f3b5cc86e95f538c748c5f08934083eefeaca016871e3bb903ba73c5c95ed8c","sha256:75aebcd2dc107b8448ac0edde8d223c3af52317d18bc1751e9ea6c0c5d5e8d50"],"state_sha256":"9808cb405620d7f01d7ec005a35720cb50a763a127266f95ef3e4ebb4db46a07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0UIHS19bhAVJ/utgPOv0MMyX6aoUP4upiS516Jdb8haMch54Z/AFd3wsf6aPYFiygmZfbxh8IzpzY4agqNYsBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:37:43.786493Z","bundle_sha256":"a9c3bfa6253c5f4c06768c4f7c03fbd06f455bc7fb8cd1c9efa7c2023d63916b"}}