{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RVAPSIYQV5ZTQH4E3NBD4HAUW5","short_pith_number":"pith:RVAPSIYQ","canonical_record":{"source":{"id":"2410.16168","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:33:16Z","cross_cats_sorted":[],"title_canon_sha256":"3c315e1644d29c83f321e4d98231d51bab3d80d8597877ffe565abcace6f4c7e","abstract_canon_sha256":"5ce7c5d8c4bb37a9625466cba0f3a717c9dd9819ac91876b637df6c7ac2d36c2"},"schema_version":"1.0"},"canonical_sha256":"8d40f92310af73381f84db423e1c14b752cc333bb20033eea2a3f97c0b1914f7","source":{"kind":"arxiv","id":"2410.16168","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16168","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16168v2","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16168","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"RVAPSIYQV5ZT","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"RVAPSIYQV5ZTQH4E","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"RVAPSIYQ","created_at":"2026-07-05T11:06:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RVAPSIYQV5ZTQH4E3NBD4HAUW5","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16168","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:33:16Z","cross_cats_sorted":[],"title_canon_sha256":"3c315e1644d29c83f321e4d98231d51bab3d80d8597877ffe565abcace6f4c7e","abstract_canon_sha256":"5ce7c5d8c4bb37a9625466cba0f3a717c9dd9819ac91876b637df6c7ac2d36c2"},"schema_version":"1.0"},"canonical_sha256":"8d40f92310af73381f84db423e1c14b752cc333bb20033eea2a3f97c0b1914f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:24.418522Z","signature_b64":"erRJp6ML+M05CVZvexT5+F0Hk1wrcq3NGqqLOpPWMMnrDUGGiA2x8CY7D6PZjczDFUR8iAklf6I39nY2i0cVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d40f92310af73381f84db423e1c14b752cc333bb20033eea2a3f97c0b1914f7","last_reissued_at":"2026-07-05T11:06:24.418026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:24.418026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16168","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":"2026-07-05T11:06:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L21ke8jGFp5fhGJp953BbNsDCV2PWM9r6eOJ2aSWhPkpfJrKNuDC5fuJfFqNS4K3KUmmIgpESzNGE7ZRusilAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:46:01.268620Z"},"content_sha256":"86d0ac6bc64ceebb2508651f295c4d415a7f41c7ed1e2c3f37ac9ee45337358d","schema_version":"1.0","event_id":"sha256:86d0ac6bc64ceebb2508651f295c4d415a7f41c7ed1e2c3f37ac9ee45337358d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RVAPSIYQV5ZTQH4E3NBD4HAUW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Pretraining via Active Forgetting for Improving Cross Lingual Transfer for Decoder Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashutosh Sathe, Divyanshu Aggarwal, Sunayana Sitaram","submitted_at":"2024-10-21T16:33:16Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate exceptional capabilities in a multitude of NLP tasks. However, the efficacy of such models to languages other than English is often limited. Prior works have shown that encoder-only models such as BERT or XLM-RoBERTa show impressive cross lingual transfer of their capabilities from English to other languages. In this work, we propose a pretraining strategy that uses active forgetting to achieve similar cross lingual transfer in decoder-only LLMs. We show that LLMs pretrained with active forgetting are highly effective when adapting to new and unseen lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16168","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/2410.16168/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":"2026-07-05T11:06:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h03gX0uJO1/ueVaNFAYPIuTeHSv83oOpcMbcrTrvKguQDrNQF7NPC7BrdCjF4t3XNwJXBWgbJxee2j0y8QPCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T08:46:01.269532Z"},"content_sha256":"4cecf03274d26801c08a42e44ccd04d723c5f9e318125cd07d2ac0cc77cf150b","schema_version":"1.0","event_id":"sha256:4cecf03274d26801c08a42e44ccd04d723c5f9e318125cd07d2ac0cc77cf150b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/bundle.json","state_url":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/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":"2026-08-18T08:46:01Z","links":{"resolver":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5","bundle":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/bundle.json","state":"https://pith.science/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVAPSIYQV5ZTQH4E3NBD4HAUW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RVAPSIYQV5ZTQH4E3NBD4HAUW5","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":"5ce7c5d8c4bb37a9625466cba0f3a717c9dd9819ac91876b637df6c7ac2d36c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:33:16Z","title_canon_sha256":"3c315e1644d29c83f321e4d98231d51bab3d80d8597877ffe565abcace6f4c7e"},"schema_version":"1.0","source":{"id":"2410.16168","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16168","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16168v2","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16168","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"RVAPSIYQV5ZT","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"RVAPSIYQV5ZTQH4E","created_at":"2026-07-05T11:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"RVAPSIYQ","created_at":"2026-07-05T11:06:24Z"}],"graph_snapshots":[{"event_id":"sha256:4cecf03274d26801c08a42e44ccd04d723c5f9e318125cd07d2ac0cc77cf150b","target":"graph","created_at":"2026-07-05T11:06:24Z","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/2410.16168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate exceptional capabilities in a multitude of NLP tasks. However, the efficacy of such models to languages other than English is often limited. Prior works have shown that encoder-only models such as BERT or XLM-RoBERTa show impressive cross lingual transfer of their capabilities from English to other languages. In this work, we propose a pretraining strategy that uses active forgetting to achieve similar cross lingual transfer in decoder-only LLMs. We show that LLMs pretrained with active forgetting are highly effective when adapting to new and unseen lan","authors_text":"Ashutosh Sathe, Divyanshu Aggarwal, Sunayana Sitaram","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:33:16Z","title":"Exploring Pretraining via Active Forgetting for Improving Cross Lingual Transfer for Decoder Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16168","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":"sha256:86d0ac6bc64ceebb2508651f295c4d415a7f41c7ed1e2c3f37ac9ee45337358d","target":"record","created_at":"2026-07-05T11:06:24Z","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":"5ce7c5d8c4bb37a9625466cba0f3a717c9dd9819ac91876b637df6c7ac2d36c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:33:16Z","title_canon_sha256":"3c315e1644d29c83f321e4d98231d51bab3d80d8597877ffe565abcace6f4c7e"},"schema_version":"1.0","source":{"id":"2410.16168","kind":"arxiv","version":2}},"canonical_sha256":"8d40f92310af73381f84db423e1c14b752cc333bb20033eea2a3f97c0b1914f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d40f92310af73381f84db423e1c14b752cc333bb20033eea2a3f97c0b1914f7","first_computed_at":"2026-07-05T11:06:24.418026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:24.418026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erRJp6ML+M05CVZvexT5+F0Hk1wrcq3NGqqLOpPWMMnrDUGGiA2x8CY7D6PZjczDFUR8iAklf6I39nY2i0cVDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:24.418522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16168","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86d0ac6bc64ceebb2508651f295c4d415a7f41c7ed1e2c3f37ac9ee45337358d","sha256:4cecf03274d26801c08a42e44ccd04d723c5f9e318125cd07d2ac0cc77cf150b"],"state_sha256":"500cb6a52a3c19b39c2b690a240fba7b1b34c0dea000258cc777426e8f3f358c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tutvnReCwrvyvcsZ8DPczprIiU/WhaAZPnvLJJyN7e/3+tM6BoY2ovaYjI+jZ9Aboeufgogr1mDXec01uZ+9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T08:46:01.284483Z","bundle_sha256":"dc49b1252841a3cad6f3d300f42fee16027b52504034b0bf99377b1d158bd243"}}