{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CCBKDXAODYBWVL54KBKWAWWFPT","short_pith_number":"pith:CCBKDXAO","canonical_record":{"source":{"id":"2502.10140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T13:10:39Z","cross_cats_sorted":[],"title_canon_sha256":"9131d9a7525e48d1edffc7583e647db58b9653d6aa179e284d633bad81993140","abstract_canon_sha256":"49386e796efc0da7eed93c77be747b30332bf0f27e9981dcb8253d5827508e77"},"schema_version":"1.0"},"canonical_sha256":"1082a1dc0e1e036aafbc5055605ac57cc396fb0bdc7e45b882de5b2850e71099","source":{"kind":"arxiv","id":"2502.10140","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10140","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10140v1","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10140","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"CCBKDXAODYBW","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"CCBKDXAODYBWVL54","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"CCBKDXAO","created_at":"2026-07-05T10:14:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CCBKDXAODYBWVL54KBKWAWWFPT","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T13:10:39Z","cross_cats_sorted":[],"title_canon_sha256":"9131d9a7525e48d1edffc7583e647db58b9653d6aa179e284d633bad81993140","abstract_canon_sha256":"49386e796efc0da7eed93c77be747b30332bf0f27e9981dcb8253d5827508e77"},"schema_version":"1.0"},"canonical_sha256":"1082a1dc0e1e036aafbc5055605ac57cc396fb0bdc7e45b882de5b2850e71099","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:28.811849Z","signature_b64":"H4kf4UKIWcZHXRp9e5vhfsRgtBBUzRATdz4wtUlxwMqU88LSgUk9/yMhAyMksj5LM+su6vGPQHjoyf5RLbUiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1082a1dc0e1e036aafbc5055605ac57cc396fb0bdc7e45b882de5b2850e71099","last_reissued_at":"2026-07-05T10:14:28.811274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:28.811274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10140","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":"2026-07-05T10:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32tHvxvWT9Wn8lao5iK/f5CEQpOran2jXnNP1ffbou/BzamiYPGcXYim+5bb+hVzPzhaDDwgbLBZQxUiQlyuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:10:11.847204Z"},"content_sha256":"631dbc204a7990d115a765fce01ba3088da0c0f399353a112dddd98fd8696505","schema_version":"1.0","event_id":"sha256:631dbc204a7990d115a765fce01ba3088da0c0f399353a112dddd98fd8696505"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CCBKDXAODYBWVL54KBKWAWWFPT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniil Gurgurov, Ivan Vykopal, Josef van Genabith, Simon Ostermann","submitted_at":"2025-02-14T13:10:39Z","abstract_excerpt":"Low-resource languages (LRLs) face significant challenges in natural language processing (NLP) due to limited data. While current state-of-the-art large language models (LLMs) still struggle with LRLs, smaller multilingual models (mLMs) such as mBERT and XLM-R offer greater promise due to a better fit of their capacity to low training data sizes. This study systematically investigates parameter-efficient adapter-based methods for adapting mLMs to LRLs, evaluating three architectures: Sequential Bottleneck, Invertible Bottleneck, and Low-Rank Adaptation. Using unstructured text from GlotCC and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10140","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/2502.10140/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":"2026-07-05T10:14:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W9o3I1te4ITGn+HJ1tQkct9++RDz0lFMlmI1VUJaG7IysfGc64zS4MoA8+gD6FUTHqdK2bU11VDO1a6ejvBHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:10:11.847685Z"},"content_sha256":"46d96475f3e168d72105a868dfc4bdba882b7c578f0acdf6d8f4ad33ad255a02","schema_version":"1.0","event_id":"sha256:46d96475f3e168d72105a868dfc4bdba882b7c578f0acdf6d8f4ad33ad255a02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCBKDXAODYBWVL54KBKWAWWFPT/bundle.json","state_url":"https://pith.science/pith/CCBKDXAODYBWVL54KBKWAWWFPT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCBKDXAODYBWVL54KBKWAWWFPT/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":"2026-08-04T16:10:11Z","links":{"resolver":"https://pith.science/pith/CCBKDXAODYBWVL54KBKWAWWFPT","bundle":"https://pith.science/pith/CCBKDXAODYBWVL54KBKWAWWFPT/bundle.json","state":"https://pith.science/pith/CCBKDXAODYBWVL54KBKWAWWFPT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCBKDXAODYBWVL54KBKWAWWFPT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CCBKDXAODYBWVL54KBKWAWWFPT","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":"49386e796efc0da7eed93c77be747b30332bf0f27e9981dcb8253d5827508e77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T13:10:39Z","title_canon_sha256":"9131d9a7525e48d1edffc7583e647db58b9653d6aa179e284d633bad81993140"},"schema_version":"1.0","source":{"id":"2502.10140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10140","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10140v1","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10140","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"CCBKDXAODYBW","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"CCBKDXAODYBWVL54","created_at":"2026-07-05T10:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"CCBKDXAO","created_at":"2026-07-05T10:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:46d96475f3e168d72105a868dfc4bdba882b7c578f0acdf6d8f4ad33ad255a02","target":"graph","created_at":"2026-07-05T10:14:28Z","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/2502.10140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low-resource languages (LRLs) face significant challenges in natural language processing (NLP) due to limited data. While current state-of-the-art large language models (LLMs) still struggle with LRLs, smaller multilingual models (mLMs) such as mBERT and XLM-R offer greater promise due to a better fit of their capacity to low training data sizes. This study systematically investigates parameter-efficient adapter-based methods for adapting mLMs to LRLs, evaluating three architectures: Sequential Bottleneck, Invertible Bottleneck, and Low-Rank Adaptation. Using unstructured text from GlotCC and ","authors_text":"Daniil Gurgurov, Ivan Vykopal, Josef van Genabith, Simon Ostermann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T13:10:39Z","title":"Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10140","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":"sha256:631dbc204a7990d115a765fce01ba3088da0c0f399353a112dddd98fd8696505","target":"record","created_at":"2026-07-05T10:14:28Z","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":"49386e796efc0da7eed93c77be747b30332bf0f27e9981dcb8253d5827508e77","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T13:10:39Z","title_canon_sha256":"9131d9a7525e48d1edffc7583e647db58b9653d6aa179e284d633bad81993140"},"schema_version":"1.0","source":{"id":"2502.10140","kind":"arxiv","version":1}},"canonical_sha256":"1082a1dc0e1e036aafbc5055605ac57cc396fb0bdc7e45b882de5b2850e71099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1082a1dc0e1e036aafbc5055605ac57cc396fb0bdc7e45b882de5b2850e71099","first_computed_at":"2026-07-05T10:14:28.811274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:28.811274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H4kf4UKIWcZHXRp9e5vhfsRgtBBUzRATdz4wtUlxwMqU88LSgUk9/yMhAyMksj5LM+su6vGPQHjoyf5RLbUiBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:28.811849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:631dbc204a7990d115a765fce01ba3088da0c0f399353a112dddd98fd8696505","sha256:46d96475f3e168d72105a868dfc4bdba882b7c578f0acdf6d8f4ad33ad255a02"],"state_sha256":"c1590941657870a908737ac218c496f93a17475141f1e349ec9b01dbda28ec1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1SpEbLJGUJRznA/kMZ+FMF5iDIBDexxaenns0C9AgwOX7f37I8NiFGchOnhVbGrsSwMycdDR9gx/2NhbATGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:10:11.851255Z","bundle_sha256":"0992285ca3454c8d858c25795b0dda7458ee8bf2e31858e62aa8902ffe17a3fa"}}