{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JI2H37VFWNIMGHHWMHL5MH65FL","short_pith_number":"pith:JI2H37VF","schema_version":"1.0","canonical_sha256":"4a347dfea5b350c31cf661d7d61fdd2adda6c461ea0dc8420873cd5934877518","source":{"kind":"arxiv","id":"2307.01163","version":3},"attestation_state":"computed","paper":{"title":"Improving Language Plasticity via Pretraining with Active Forgetting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Kelly Marchisio, Mikel Artetxe, Pontus Stenetorp, Roberta Raileanu, Sebastian Riedel, Yihong Chen","submitted_at":"2023-07-03T17:12:44Z","abstract_excerpt":"Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities universally accessible. While prior work has shown it possible to address this issue by learning a new embedding layer for the new language, doing so is both data and compute inefficient. We propose to use an active forgetting mechanism during pretraining, as a simple way of creating PLMs that can quickly adapt to new languages. Concretely, by resetting the embed"},"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":"2307.01163","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-03T17:12:44Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"62b0c86a469a43aec730f2b5129438fd72b75aedb8890cea26c400109a80172e","abstract_canon_sha256":"c4240601c689b7785706211bd5cef18b62e36e1af9b0cc58a0369ea7210106e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:57.463687Z","signature_b64":"5tYLgGHlgaNrTcrX7fLOn3UD7H72LDO5OBcCoI+XtsrmlpigvdAJWTjDmV6boFMxy9bNr959AIwpXe1QXCBlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a347dfea5b350c31cf661d7d61fdd2adda6c461ea0dc8420873cd5934877518","last_reissued_at":"2026-07-05T07:32:57.463237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:57.463237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Language Plasticity via Pretraining with Active Forgetting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Kelly Marchisio, Mikel Artetxe, Pontus Stenetorp, Roberta Raileanu, Sebastian Riedel, Yihong Chen","submitted_at":"2023-07-03T17:12:44Z","abstract_excerpt":"Pretrained language models (PLMs) are today the primary model for natural language processing. Despite their impressive downstream performance, it can be difficult to apply PLMs to new languages, a barrier to making their capabilities universally accessible. While prior work has shown it possible to address this issue by learning a new embedding layer for the new language, doing so is both data and compute inefficient. We propose to use an active forgetting mechanism during pretraining, as a simple way of creating PLMs that can quickly adapt to new languages. Concretely, by resetting the embed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01163","kind":"arxiv","version":3},"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/2307.01163/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":"2307.01163","created_at":"2026-07-05T07:32:57.463297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01163v3","created_at":"2026-07-05T07:32:57.463297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01163","created_at":"2026-07-05T07:32:57.463297+00:00"},{"alias_kind":"pith_short_12","alias_value":"JI2H37VFWNIM","created_at":"2026-07-05T07:32:57.463297+00:00"},{"alias_kind":"pith_short_16","alias_value":"JI2H37VFWNIMGHHW","created_at":"2026-07-05T07:32:57.463297+00:00"},{"alias_kind":"pith_short_8","alias_value":"JI2H37VF","created_at":"2026-07-05T07:32:57.463297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL","json":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL.json","graph_json":"https://pith.science/api/pith-number/JI2H37VFWNIMGHHWMHL5MH65FL/graph.json","events_json":"https://pith.science/api/pith-number/JI2H37VFWNIMGHHWMHL5MH65FL/events.json","paper":"https://pith.science/paper/JI2H37VF"},"agent_actions":{"view_html":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL","download_json":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL.json","view_paper":"https://pith.science/paper/JI2H37VF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01163&json=true","fetch_graph":"https://pith.science/api/pith-number/JI2H37VFWNIMGHHWMHL5MH65FL/graph.json","fetch_events":"https://pith.science/api/pith-number/JI2H37VFWNIMGHHWMHL5MH65FL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL/action/storage_attestation","attest_author":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL/action/author_attestation","sign_citation":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL/action/citation_signature","submit_replication":"https://pith.science/pith/JI2H37VFWNIMGHHWMHL5MH65FL/action/replication_record"}},"created_at":"2026-07-05T07:32:57.463297+00:00","updated_at":"2026-07-05T07:32:57.463297+00:00"}