{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:W4I5PHVX4DTBSRWTYXUVFEO7PC","short_pith_number":"pith:W4I5PHVX","canonical_record":{"source":{"id":"2006.15315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-27T08:13:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b7ccd9275e21c15cf2acf41aac957d2967303b27bc9ea2b68e364791bcd50726","abstract_canon_sha256":"4fec7ab4ba6e3aadc8b8ed4b5bcefadbfdad5cfaf6cda115c3946887c9a66a96"},"schema_version":"1.0"},"canonical_sha256":"b711d79eb7e0e61946d3c5e95291df78ad2b98cb8c2edde5ae7a675b39535308","source":{"kind":"arxiv","id":"2006.15315","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15315","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15315v1","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15315","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"W4I5PHVX4DTB","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"W4I5PHVX4DTBSRWT","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"W4I5PHVX","created_at":"2026-07-05T01:14:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:W4I5PHVX4DTBSRWTYXUVFEO7PC","target":"record","payload":{"canonical_record":{"source":{"id":"2006.15315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-27T08:13:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b7ccd9275e21c15cf2acf41aac957d2967303b27bc9ea2b68e364791bcd50726","abstract_canon_sha256":"4fec7ab4ba6e3aadc8b8ed4b5bcefadbfdad5cfaf6cda115c3946887c9a66a96"},"schema_version":"1.0"},"canonical_sha256":"b711d79eb7e0e61946d3c5e95291df78ad2b98cb8c2edde5ae7a675b39535308","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:04.500457Z","signature_b64":"zjPNCOXLiOdwEyYeRIzfrCv83VUSl4eDtCjswFi0JVvYcoSC/jh68jueofodqAkLOKVwBg9itA3KI9lULiMgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b711d79eb7e0e61946d3c5e95291df78ad2b98cb8c2edde5ae7a675b39535308","last_reissued_at":"2026-07-05T01:14:04.500047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:04.500047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.15315","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":"2026-07-05T01:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jQIHTh6YEfOajglz4oYlAk4zqI04ym8HyXobPEgvzMz4a8nxEXDZ6xTzONpBOI0M/TBrBZPEZLvGYWpBgjVPBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:43:56.196598Z"},"content_sha256":"9a396dc14abaaf9ed5feb8d6a84333770fdcf022e4d55a8826c9052f8b00c919","schema_version":"1.0","event_id":"sha256:9a396dc14abaaf9ed5feb8d6a84333770fdcf022e4d55a8826c9052f8b00c919"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:W4I5PHVX4DTBSRWTYXUVFEO7PC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-aware Self-training for Text Classification with Few Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ahmed Hassan Awadallah, Subhabrata Mukherjee","submitted_at":"2020-06-27T08:13:58Z","abstract_excerpt":"Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of the earliest semi-supervised learning approaches to reduce the annotation bottleneck by making use of large-scale unlabeled data for the target task. Standard self-training mechanism randomly samples instances from the unlabeled pool to pseudo-label and augment labeled data. In this work, we propose an approach to improve self-training by incorporating uncer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15315","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/2006.15315/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":"2026-07-05T01:14:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IYObLjTTPGN8zfOu0LHxbif2zg7jpLTEY0hDGqaSJzsn522FUHa9SfoPyHEmIKIWCkv1p6IbeN8n8fJvu0NwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:43:56.197157Z"},"content_sha256":"53a1dc3b4a097c0960f69c787b5a4e30fb7eec332ea3ed188d696c2d72363fee","schema_version":"1.0","event_id":"sha256:53a1dc3b4a097c0960f69c787b5a4e30fb7eec332ea3ed188d696c2d72363fee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4I5PHVX4DTBSRWTYXUVFEO7PC/bundle.json","state_url":"https://pith.science/pith/W4I5PHVX4DTBSRWTYXUVFEO7PC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4I5PHVX4DTBSRWTYXUVFEO7PC/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":"2026-08-18T09:43:56Z","links":{"resolver":"https://pith.science/pith/W4I5PHVX4DTBSRWTYXUVFEO7PC","bundle":"https://pith.science/pith/W4I5PHVX4DTBSRWTYXUVFEO7PC/bundle.json","state":"https://pith.science/pith/W4I5PHVX4DTBSRWTYXUVFEO7PC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4I5PHVX4DTBSRWTYXUVFEO7PC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:W4I5PHVX4DTBSRWTYXUVFEO7PC","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":"4fec7ab4ba6e3aadc8b8ed4b5bcefadbfdad5cfaf6cda115c3946887c9a66a96","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-27T08:13:58Z","title_canon_sha256":"b7ccd9275e21c15cf2acf41aac957d2967303b27bc9ea2b68e364791bcd50726"},"schema_version":"1.0","source":{"id":"2006.15315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15315","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15315v1","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15315","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"W4I5PHVX4DTB","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"W4I5PHVX4DTBSRWT","created_at":"2026-07-05T01:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"W4I5PHVX","created_at":"2026-07-05T01:14:04Z"}],"graph_snapshots":[{"event_id":"sha256:53a1dc3b4a097c0960f69c787b5a4e30fb7eec332ea3ed188d696c2d72363fee","target":"graph","created_at":"2026-07-05T01:14:04Z","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/2006.15315/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of the earliest semi-supervised learning approaches to reduce the annotation bottleneck by making use of large-scale unlabeled data for the target task. Standard self-training mechanism randomly samples instances from the unlabeled pool to pseudo-label and augment labeled data. In this work, we propose an approach to improve self-training by incorporating uncer","authors_text":"Ahmed Hassan Awadallah, Subhabrata Mukherjee","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-27T08:13:58Z","title":"Uncertainty-aware Self-training for Text Classification with Few Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15315","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":"sha256:9a396dc14abaaf9ed5feb8d6a84333770fdcf022e4d55a8826c9052f8b00c919","target":"record","created_at":"2026-07-05T01:14:04Z","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":"4fec7ab4ba6e3aadc8b8ed4b5bcefadbfdad5cfaf6cda115c3946887c9a66a96","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-27T08:13:58Z","title_canon_sha256":"b7ccd9275e21c15cf2acf41aac957d2967303b27bc9ea2b68e364791bcd50726"},"schema_version":"1.0","source":{"id":"2006.15315","kind":"arxiv","version":1}},"canonical_sha256":"b711d79eb7e0e61946d3c5e95291df78ad2b98cb8c2edde5ae7a675b39535308","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b711d79eb7e0e61946d3c5e95291df78ad2b98cb8c2edde5ae7a675b39535308","first_computed_at":"2026-07-05T01:14:04.500047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:14:04.500047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zjPNCOXLiOdwEyYeRIzfrCv83VUSl4eDtCjswFi0JVvYcoSC/jh68jueofodqAkLOKVwBg9itA3KI9lULiMgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:14:04.500457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.15315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a396dc14abaaf9ed5feb8d6a84333770fdcf022e4d55a8826c9052f8b00c919","sha256:53a1dc3b4a097c0960f69c787b5a4e30fb7eec332ea3ed188d696c2d72363fee"],"state_sha256":"4e4a08380aaa029e26079745d9fae7ac5b8d877ad5286d772a07d7c7075e493b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Paf5EpKe/bQzJzxmVsXAMLWA1SeWT72ZQ7dDEJ0i5LqEcv2u3UDQCbLsAw4ZTJ2rbkprS4pSoUdpq56qsGrbAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:43:56.202271Z","bundle_sha256":"1198d2d9c4d8e3cc9e67bc61f8a307b8516feb7ff35ded0ec1d1b13312d27f53"}}