{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MGJGX7MSPUZWOWMQUH4ANKNO2E","short_pith_number":"pith:MGJGX7MS","canonical_record":{"source":{"id":"2104.08320","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T19:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"d3d19dc530ac8cd2e03a6f955c7f343322e1cfc4bf425bd3d647406cbff0e9be","abstract_canon_sha256":"2f8284fcbe98045bceac3d116b01b7d4320ac32bfaf11aa494be8ab33f8e9c0c"},"schema_version":"1.0"},"canonical_sha256":"61926bfd927d33675990a1f806a9aed10c86ecfb16897d3399edfd14b3410c73","source":{"kind":"arxiv","id":"2104.08320","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08320","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08320v2","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08320","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"pith_short_12","alias_value":"MGJGX7MSPUZW","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"pith_short_16","alias_value":"MGJGX7MSPUZWOWMQ","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"pith_short_8","alias_value":"MGJGX7MS","created_at":"2026-07-05T04:01:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MGJGX7MSPUZWOWMQUH4ANKNO2E","target":"record","payload":{"canonical_record":{"source":{"id":"2104.08320","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T19:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"d3d19dc530ac8cd2e03a6f955c7f343322e1cfc4bf425bd3d647406cbff0e9be","abstract_canon_sha256":"2f8284fcbe98045bceac3d116b01b7d4320ac32bfaf11aa494be8ab33f8e9c0c"},"schema_version":"1.0"},"canonical_sha256":"61926bfd927d33675990a1f806a9aed10c86ecfb16897d3399edfd14b3410c73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:30.448446Z","signature_b64":"lzt0R01qcoQ3BNZUBCM/ri+Zkhfn8bWLZCdAaa4BTskoefFaAGv9R1yxvHBDjdkaiZB9M4I+niIJkxsMt0WjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61926bfd927d33675990a1f806a9aed10c86ecfb16897d3399edfd14b3410c73","last_reissued_at":"2026-07-05T04:01:30.448065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:30.448065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.08320","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":"2026-07-05T04:01:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dPPMQrJDL/f22ncw8KaTJ0STWj1HgSYUEWD6xbUk/nvW8czhHJ2/sDPeP7lN3PRou101C9xirtpubAp4oXPZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:06:39.791826Z"},"content_sha256":"645458579ec49d608168d456819d80526aa713c71305ab8f81103b05b460d25b","schema_version":"1.0","event_id":"sha256:645458579ec49d608168d456819d80526aa713c71305ab8f81103b05b460d25b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MGJGX7MSPUZWOWMQUH4ANKNO2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Importance of Effectively Adapting Pretrained Language Models for Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katerina Margatina, Lo\\\"ic Barrault, Nikolaos Aletras","submitted_at":"2021-04-16T19:07:31Z","abstract_excerpt":"Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed using off-the-shelf pretrained language models (LMs). In this paper, we argue that these LMs are not adapted effectively to the downstream task during AL and we explore ways to address this issue. We suggest to first adapt the pretrained LM to the target task by continuing training with all the available unlabeled data and then use it for AL. We also propose a simple yet effective fine-tuning method to ensure that the adapted LM is properly trained in both low and high resource scenarios during AL. Our experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08320","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/2104.08320/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":"2026-07-05T04:01:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WqwzZy27yjYq5RYAQAlWGiGVO5+AXm1FugzAJQkdCyu+57RlhdOzCALYTc+w9iLux9xmrkB8FvhySjJ/FrbUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:06:39.794620Z"},"content_sha256":"440556937400e18222604a2b7f683361ccb3c62668ec033611011466cd2c0e33","schema_version":"1.0","event_id":"sha256:440556937400e18222604a2b7f683361ccb3c62668ec033611011466cd2c0e33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGJGX7MSPUZWOWMQUH4ANKNO2E/bundle.json","state_url":"https://pith.science/pith/MGJGX7MSPUZWOWMQUH4ANKNO2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGJGX7MSPUZWOWMQUH4ANKNO2E/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":"2026-08-18T09:06:39Z","links":{"resolver":"https://pith.science/pith/MGJGX7MSPUZWOWMQUH4ANKNO2E","bundle":"https://pith.science/pith/MGJGX7MSPUZWOWMQUH4ANKNO2E/bundle.json","state":"https://pith.science/pith/MGJGX7MSPUZWOWMQUH4ANKNO2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGJGX7MSPUZWOWMQUH4ANKNO2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MGJGX7MSPUZWOWMQUH4ANKNO2E","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":"2f8284fcbe98045bceac3d116b01b7d4320ac32bfaf11aa494be8ab33f8e9c0c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T19:07:31Z","title_canon_sha256":"d3d19dc530ac8cd2e03a6f955c7f343322e1cfc4bf425bd3d647406cbff0e9be"},"schema_version":"1.0","source":{"id":"2104.08320","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08320","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08320v2","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08320","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"pith_short_12","alias_value":"MGJGX7MSPUZW","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"pith_short_16","alias_value":"MGJGX7MSPUZWOWMQ","created_at":"2026-07-05T04:01:30Z"},{"alias_kind":"pith_short_8","alias_value":"MGJGX7MS","created_at":"2026-07-05T04:01:30Z"}],"graph_snapshots":[{"event_id":"sha256:440556937400e18222604a2b7f683361ccb3c62668ec033611011466cd2c0e33","target":"graph","created_at":"2026-07-05T04:01:30Z","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/2104.08320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed using off-the-shelf pretrained language models (LMs). In this paper, we argue that these LMs are not adapted effectively to the downstream task during AL and we explore ways to address this issue. We suggest to first adapt the pretrained LM to the target task by continuing training with all the available unlabeled data and then use it for AL. We also propose a simple yet effective fine-tuning method to ensure that the adapted LM is properly trained in both low and high resource scenarios during AL. Our experim","authors_text":"Katerina Margatina, Lo\\\"ic Barrault, Nikolaos Aletras","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T19:07:31Z","title":"On the Importance of Effectively Adapting Pretrained Language Models for Active Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08320","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":"sha256:645458579ec49d608168d456819d80526aa713c71305ab8f81103b05b460d25b","target":"record","created_at":"2026-07-05T04:01:30Z","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":"2f8284fcbe98045bceac3d116b01b7d4320ac32bfaf11aa494be8ab33f8e9c0c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-16T19:07:31Z","title_canon_sha256":"d3d19dc530ac8cd2e03a6f955c7f343322e1cfc4bf425bd3d647406cbff0e9be"},"schema_version":"1.0","source":{"id":"2104.08320","kind":"arxiv","version":2}},"canonical_sha256":"61926bfd927d33675990a1f806a9aed10c86ecfb16897d3399edfd14b3410c73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61926bfd927d33675990a1f806a9aed10c86ecfb16897d3399edfd14b3410c73","first_computed_at":"2026-07-05T04:01:30.448065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:30.448065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lzt0R01qcoQ3BNZUBCM/ri+Zkhfn8bWLZCdAaa4BTskoefFaAGv9R1yxvHBDjdkaiZB9M4I+niIJkxsMt0WjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:30.448446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08320","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:645458579ec49d608168d456819d80526aa713c71305ab8f81103b05b460d25b","sha256:440556937400e18222604a2b7f683361ccb3c62668ec033611011466cd2c0e33"],"state_sha256":"86268fbebf7effe8756fe47ff9df9bdcae9b3aacac6b451e481fc3e8b31d08c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17lZ+xiXPngp7SCRyod2MS6VZEHxm9vfwzC13Q8hiRW8XIlGAkjnpKKItnNEMiKAKkGKBuuuqBXpv1aK5mFyBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:06:39.802331Z","bundle_sha256":"24adb700e44776e8a1d6a69e96e46c460846dea9a6847ff9a6cf246f0373d869"}}