{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Z2UOLCYY45WZG5NV4KAOQW2GM7","short_pith_number":"pith:Z2UOLCYY","canonical_record":{"source":{"id":"2607.21861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T23:14:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a5157e19a1127c2ba9a513a9763b6085624b2fd82db36cb334bf24dee95245d","abstract_canon_sha256":"c28c1d18d41c53fd11ea3a2f8784fa3d9d9b8bac971738829fbfe089c076d292"},"schema_version":"1.0"},"canonical_sha256":"cea8e58b18e76d9375b5e280e85b4667fe873c53c60b76a6906d722487e6e758","source":{"kind":"arxiv","id":"2607.21861","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21861","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21861v1","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21861","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"pith_short_12","alias_value":"Z2UOLCYY45WZ","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"pith_short_16","alias_value":"Z2UOLCYY45WZG5NV","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"pith_short_8","alias_value":"Z2UOLCYY","created_at":"2026-07-27T00:20:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Z2UOLCYY45WZG5NV4KAOQW2GM7","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21861","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T23:14:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a5157e19a1127c2ba9a513a9763b6085624b2fd82db36cb334bf24dee95245d","abstract_canon_sha256":"c28c1d18d41c53fd11ea3a2f8784fa3d9d9b8bac971738829fbfe089c076d292"},"schema_version":"1.0"},"canonical_sha256":"cea8e58b18e76d9375b5e280e85b4667fe873c53c60b76a6906d722487e6e758","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:24.822400Z","signature_b64":"ObjYffJIJgK27ij2nDXOLdKaaVKVPtW9KPa/E4MhHBwcoqu263lO3xQHNpzuX9DpSb9XciZPewmLyTGsODv1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cea8e58b18e76d9375b5e280e85b4667fe873c53c60b76a6906d722487e6e758","last_reissued_at":"2026-07-27T00:20:24.821570Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:24.821570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21861","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":"2026-07-27T00:20:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3e8ZH2ndSFey5Mf7gLSwWJHUoGNB/PEOUcPBfU42k8WH8fpH4uyTHzRdSrxBCMLl0G2xcMq1Fw3sXWxArmB2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:13:19.687407Z"},"content_sha256":"d27d42a02dfd8dd1b59b15842ba890c4385f40ad7d1ebbb570fdb6aa82c10903","schema_version":"1.0","event_id":"sha256:d27d42a02dfd8dd1b59b15842ba890c4385f40ad7d1ebbb570fdb6aa82c10903"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Z2UOLCYY45WZG5NV4KAOQW2GM7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Joan Figuerola Hurtado","submitted_at":"2026-07-23T23:14:59Z","abstract_excerpt":"We study baking documents directly into the weights of a 4-bit Gemma-4-e4b model via LoRA, so a system can answer questions about a corpus closed-book: no retrieval and no context-window budget. Across roughly 100 training runs from single documents to a 99-document corpus, we find that once adapter capacity is adequate, training-data quality is the dominant lever on closed-book accuracy, outweighing LoRA rank, learning rate, and two alternative architectures combined; capacity itself is a hard gate below which no data intervention helps. A single curation pass (shortening gold answers to cano"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21861","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/2607.21861/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":"2026-07-27T00:20:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FYdriVtyDAul9dnzyn0Gm2YN+nc8FzLk6F+fF0zpStUpQRIgz3saxrIC52bnNJSVK49HHu34LpIhbWzJ/y6CDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:13:19.688074Z"},"content_sha256":"dc7f0d37e89d1c8f509f13e410debadb0d051e90c160db44efaabd9993dd7b9f","schema_version":"1.0","event_id":"sha256:dc7f0d37e89d1c8f509f13e410debadb0d051e90c160db44efaabd9993dd7b9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z2UOLCYY45WZG5NV4KAOQW2GM7/bundle.json","state_url":"https://pith.science/pith/Z2UOLCYY45WZG5NV4KAOQW2GM7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z2UOLCYY45WZG5NV4KAOQW2GM7/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":"2026-08-03T09:13:19Z","links":{"resolver":"https://pith.science/pith/Z2UOLCYY45WZG5NV4KAOQW2GM7","bundle":"https://pith.science/pith/Z2UOLCYY45WZG5NV4KAOQW2GM7/bundle.json","state":"https://pith.science/pith/Z2UOLCYY45WZG5NV4KAOQW2GM7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z2UOLCYY45WZG5NV4KAOQW2GM7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z2UOLCYY45WZG5NV4KAOQW2GM7","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":"c28c1d18d41c53fd11ea3a2f8784fa3d9d9b8bac971738829fbfe089c076d292","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T23:14:59Z","title_canon_sha256":"5a5157e19a1127c2ba9a513a9763b6085624b2fd82db36cb334bf24dee95245d"},"schema_version":"1.0","source":{"id":"2607.21861","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21861","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21861v1","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21861","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"pith_short_12","alias_value":"Z2UOLCYY45WZ","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"pith_short_16","alias_value":"Z2UOLCYY45WZG5NV","created_at":"2026-07-27T00:20:24Z"},{"alias_kind":"pith_short_8","alias_value":"Z2UOLCYY","created_at":"2026-07-27T00:20:24Z"}],"graph_snapshots":[{"event_id":"sha256:dc7f0d37e89d1c8f509f13e410debadb0d051e90c160db44efaabd9993dd7b9f","target":"graph","created_at":"2026-07-27T00:20:24Z","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/2607.21861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study baking documents directly into the weights of a 4-bit Gemma-4-e4b model via LoRA, so a system can answer questions about a corpus closed-book: no retrieval and no context-window budget. Across roughly 100 training runs from single documents to a 99-document corpus, we find that once adapter capacity is adequate, training-data quality is the dominant lever on closed-book accuracy, outweighing LoRA rank, learning rate, and two alternative architectures combined; capacity itself is a hard gate below which no data intervention helps. A single curation pass (shortening gold answers to cano","authors_text":"Joan Figuerola Hurtado","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T23:14:59Z","title":"Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21861","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:d27d42a02dfd8dd1b59b15842ba890c4385f40ad7d1ebbb570fdb6aa82c10903","target":"record","created_at":"2026-07-27T00:20:24Z","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":"c28c1d18d41c53fd11ea3a2f8784fa3d9d9b8bac971738829fbfe089c076d292","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T23:14:59Z","title_canon_sha256":"5a5157e19a1127c2ba9a513a9763b6085624b2fd82db36cb334bf24dee95245d"},"schema_version":"1.0","source":{"id":"2607.21861","kind":"arxiv","version":1}},"canonical_sha256":"cea8e58b18e76d9375b5e280e85b4667fe873c53c60b76a6906d722487e6e758","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cea8e58b18e76d9375b5e280e85b4667fe873c53c60b76a6906d722487e6e758","first_computed_at":"2026-07-27T00:20:24.821570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T00:20:24.821570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ObjYffJIJgK27ij2nDXOLdKaaVKVPtW9KPa/E4MhHBwcoqu263lO3xQHNpzuX9DpSb9XciZPewmLyTGsODv1Bw==","signature_status":"signed_v1","signed_at":"2026-07-27T00:20:24.822400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21861","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d27d42a02dfd8dd1b59b15842ba890c4385f40ad7d1ebbb570fdb6aa82c10903","sha256:dc7f0d37e89d1c8f509f13e410debadb0d051e90c160db44efaabd9993dd7b9f"],"state_sha256":"e05f1392bae3ac04d2f474c5cb0892d60fbd59921dc8a9a2c16a1c786ed1db2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WPfrRPx2HmlVnqYf6A4vTrBYwmxnJu6alfsqEWQXqsi9gnDEy5fwdzh98HEvWci8MakRIsSyzwtJ2NFcNXJjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T09:13:19.699764Z","bundle_sha256":"fe96426ca3f03b6d875915e10906f80babccdc0af8e4f553a70196d589f2ad17"}}