{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PMRPBMEJV5PX7BC7LT2YXVPVCK","short_pith_number":"pith:PMRPBMEJ","schema_version":"1.0","canonical_sha256":"7b22f0b089af5f7f845f5cf58bd5f512bf6a0f43571d7579e0b1b672edaf79a0","source":{"kind":"arxiv","id":"2502.00617","version":1},"attestation_state":"computed","paper":{"title":"Efficient Language Modeling for Low-Resource Settings with Hybrid RNN-Transformer Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabriel Lindenmaier, Sean Papay, Sebastian Pad\\'o","submitted_at":"2025-02-02T01:05:09Z","abstract_excerpt":"Transformer-based language models have recently been at the forefront of active research in text generation. However, these models' advances come at the price of prohibitive training costs, with parameter counts in the billions and compute requirements measured in petaflop/s-decades. In this paper, we investigate transformer-based architectures for improving model performance in a low-data regime by selectively replacing attention layers with feed-forward and quasi-recurrent neural network layers. We test these architectures on the standard Enwik8 and Wikitext-103 corpora. Our results show tha"},"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":"2502.00617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T01:05:09Z","cross_cats_sorted":[],"title_canon_sha256":"d5b80ffab2471ff3b8c826c59e5dead0a948fe9f9f9d65486c2b99c2ffcefbd1","abstract_canon_sha256":"34dd718bac62a9db627462ebbea4444d925e6aa68085fb675e3928da71902684"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:36.209291Z","signature_b64":"+BiVGSLfyAepFFtM2F1xNImuBdS+yzFmVhwinAjwqfyEeKEvPEGfXSpLRvwgWz0mH735S39/msl7mHRQmflZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b22f0b089af5f7f845f5cf58bd5f512bf6a0f43571d7579e0b1b672edaf79a0","last_reissued_at":"2026-07-05T10:08:36.208836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:36.208836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Language Modeling for Low-Resource Settings with Hybrid RNN-Transformer Architectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gabriel Lindenmaier, Sean Papay, Sebastian Pad\\'o","submitted_at":"2025-02-02T01:05:09Z","abstract_excerpt":"Transformer-based language models have recently been at the forefront of active research in text generation. However, these models' advances come at the price of prohibitive training costs, with parameter counts in the billions and compute requirements measured in petaflop/s-decades. In this paper, we investigate transformer-based architectures for improving model performance in a low-data regime by selectively replacing attention layers with feed-forward and quasi-recurrent neural network layers. We test these architectures on the standard Enwik8 and Wikitext-103 corpora. Our results show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00617","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/2502.00617/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":"2502.00617","created_at":"2026-07-05T10:08:36.208894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00617v1","created_at":"2026-07-05T10:08:36.208894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00617","created_at":"2026-07-05T10:08:36.208894+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMRPBMEJV5PX","created_at":"2026-07-05T10:08:36.208894+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMRPBMEJV5PX7BC7","created_at":"2026-07-05T10:08:36.208894+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMRPBMEJ","created_at":"2026-07-05T10:08:36.208894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02608","citing_title":"Dependency Parsing Across the Resource Spectrum: Evaluating Architectures on High and Low-Resource Languages","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK","json":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK.json","graph_json":"https://pith.science/api/pith-number/PMRPBMEJV5PX7BC7LT2YXVPVCK/graph.json","events_json":"https://pith.science/api/pith-number/PMRPBMEJV5PX7BC7LT2YXVPVCK/events.json","paper":"https://pith.science/paper/PMRPBMEJ"},"agent_actions":{"view_html":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK","download_json":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK.json","view_paper":"https://pith.science/paper/PMRPBMEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00617&json=true","fetch_graph":"https://pith.science/api/pith-number/PMRPBMEJV5PX7BC7LT2YXVPVCK/graph.json","fetch_events":"https://pith.science/api/pith-number/PMRPBMEJV5PX7BC7LT2YXVPVCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK/action/storage_attestation","attest_author":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK/action/author_attestation","sign_citation":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK/action/citation_signature","submit_replication":"https://pith.science/pith/PMRPBMEJV5PX7BC7LT2YXVPVCK/action/replication_record"}},"created_at":"2026-07-05T10:08:36.208894+00:00","updated_at":"2026-07-05T10:08:36.208894+00:00"}