{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QGXPIFONRXJLJS2OTZN3MYVENS","short_pith_number":"pith:QGXPIFON","schema_version":"1.0","canonical_sha256":"81aef415cd8dd2b4cb4e9e5bb662a46c9ba6e6c0c5fe64a9a49c98cf220607fb","source":{"kind":"arxiv","id":"2608.10296","version":1},"attestation_state":"computed","paper":{"title":"Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amanda Bertsch, Dirk Groeneveld, Graham Neubig, Hannaneh Hajishirzi, Kyle Lo, Luca Soldaini, Matthew R. Gormley","submitted_at":"2026-08-10T23:03:32Z","abstract_excerpt":"One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that this is not the case in the long context setting. Specifically, we show that a set of four minor architectural decisions --- all made by at least one of the Olmo, Llama, and Qwen dense model families --- have a compoundingly negative effect on long context extensibility. Any one of these choices alone has a minor impact on long context performance, but combining three or more can drop the performance downstream by up to 47%. Furthermore, these di"},"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":"2608.10296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-10T23:03:32Z","cross_cats_sorted":[],"title_canon_sha256":"503a3a3703e53a45f029762a3e94340b63c94b1ec012bde058b5409d162e544c","abstract_canon_sha256":"c9d86ccb451d28055cc135c39c8cc5c719a66953c19b2805591afa8ac2e228a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T00:23:49.085724Z","signature_b64":"NxNhdGXo2Me9hqV4OBR9Fq2Z1j1pDoPnF5CAseE6HN+MRtfYUEzi9vtZNB8uKeDdc7DvHrXSU2W8I4rKdvsvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81aef415cd8dd2b4cb4e9e5bb662a46c9ba6e6c0c5fe64a9a49c98cf220607fb","last_reissued_at":"2026-08-12T00:23:49.084175Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T00:23:49.084175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amanda Bertsch, Dirk Groeneveld, Graham Neubig, Hannaneh Hajishirzi, Kyle Lo, Luca Soldaini, Matthew R. Gormley","submitted_at":"2026-08-10T23:03:32Z","abstract_excerpt":"One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that this is not the case in the long context setting. Specifically, we show that a set of four minor architectural decisions --- all made by at least one of the Olmo, Llama, and Qwen dense model families --- have a compoundingly negative effect on long context extensibility. Any one of these choices alone has a minor impact on long context performance, but combining three or more can drop the performance downstream by up to 47%. Furthermore, these di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10296","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/2608.10296/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":"2608.10296","created_at":"2026-08-12T00:23:49.086837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10296v1","created_at":"2026-08-12T00:23:49.086837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10296","created_at":"2026-08-12T00:23:49.086837+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGXPIFONRXJL","created_at":"2026-08-12T00:23:49.086837+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGXPIFONRXJLJS2O","created_at":"2026-08-12T00:23:49.086837+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGXPIFON","created_at":"2026-08-12T00:23:49.086837+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/QGXPIFONRXJLJS2OTZN3MYVENS","json":"https://pith.science/pith/QGXPIFONRXJLJS2OTZN3MYVENS.json","graph_json":"https://pith.science/api/pith-number/QGXPIFONRXJLJS2OTZN3MYVENS/graph.json","events_json":"https://pith.science/api/pith-number/QGXPIFONRXJLJS2OTZN3MYVENS/events.json","paper":"https://pith.science/paper/QGXPIFON"},"agent_actions":{"view_html":"https://pith.science/pith/QGXPIFONRXJLJS2OTZN3MYVENS","download_json":"https://pith.science/pith/QGXPIFONRXJLJS2OTZN3MYVENS.json","view_paper":"https://pith.science/paper/QGXPIFON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10296&json=true","fetch_graph":"https://pith.science/api/pith-number/QGXPIFONRXJLJS2OTZN3MYVENS/graph.json","fetch_events":"https://pith.science/api/pith-number/QGXPIFONRXJLJS2OTZN3MYVENS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGXPIFONRXJLJS2OTZN3MYVENS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGXPIFONRXJLJS2OTZN3MYVENS/action/storage_attestation","attest_author":"https://pith.science/pith/QGXPIFONRXJLJS2OTZN3MYVENS/action/author_attestation","sign_citation":"https://pith.science/pith/QGXPIFONRXJLJS2OTZN3MYVENS/action/citation_signature","submit_replication":"https://pith.science/pith/QGXPIFONRXJLJS2OTZN3MYVENS/action/replication_record"}},"created_at":"2026-08-12T00:23:49.086837+00:00","updated_at":"2026-08-12T00:23:49.086837+00:00"}