{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SQLEP2X6UZSPQP5KCNQYH5AJBO","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":"951e9726b66f04165c0969d4e3fa5dd51bdfca6a09613617177b25ffb321beeb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-20T11:10:24Z","title_canon_sha256":"e2d4ee2918541512d3818b219559986ee3748647edd77a8231f78257378379c7"},"schema_version":"1.0","source":{"id":"2506.16912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16912","created_at":"2026-07-05T11:24:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16912v1","created_at":"2026-07-05T11:24:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16912","created_at":"2026-07-05T11:24:44Z"},{"alias_kind":"pith_short_12","alias_value":"SQLEP2X6UZSP","created_at":"2026-07-05T11:24:44Z"},{"alias_kind":"pith_short_16","alias_value":"SQLEP2X6UZSPQP5K","created_at":"2026-07-05T11:24:44Z"},{"alias_kind":"pith_short_8","alias_value":"SQLEP2X6","created_at":"2026-07-05T11:24:44Z"}],"graph_snapshots":[{"event_id":"sha256:99ed2cab68d84a9d686655e65b076f4d8c4b4d9ca77f98cdb993626457a8093f","target":"graph","created_at":"2026-07-05T11:24:44Z","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/2506.16912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency is a crucial property of language models with practical implications for training efficiency. In real-world text, information follows a long-tailed distribution. Yet, we expect models to learn and recall frequent and infrequent facts. Sample-efficient models are better equipped to handle this challenge of learning and retaining rare information without requiring excessive exposure. This study analyzes multiple models of varying architectures and sizes, all trained on the same pre-training data. By annotating relational facts with their frequencies in the training corpus, we e","authors_text":"Alan Akbik, Daniel Christoph, Max Ploner, Patrick Haller","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-20T11:10:24Z","title":"From Data to Knowledge: Evaluating How Efficiently Language Models Learn Facts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16912","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:a57851225e97743f7381e36e2de5b80307256795aa5fef60f82a72b615c99a2a","target":"record","created_at":"2026-07-05T11:24:44Z","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":"951e9726b66f04165c0969d4e3fa5dd51bdfca6a09613617177b25ffb321beeb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-20T11:10:24Z","title_canon_sha256":"e2d4ee2918541512d3818b219559986ee3748647edd77a8231f78257378379c7"},"schema_version":"1.0","source":{"id":"2506.16912","kind":"arxiv","version":1}},"canonical_sha256":"941647eafea664f83faa136183f4090b9362c9f42331a731eabfc072e610dcdb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"941647eafea664f83faa136183f4090b9362c9f42331a731eabfc072e610dcdb","first_computed_at":"2026-07-05T11:24:44.850703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:44.850703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bf71bZ7LlarWKJD9dky2tnfJiV5kQvYhaLnU7Kh67H3y6SLRmsKfjF6r3qd/dYBj580ITtebtZGjBnv0PvjPDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:44.851161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a57851225e97743f7381e36e2de5b80307256795aa5fef60f82a72b615c99a2a","sha256:99ed2cab68d84a9d686655e65b076f4d8c4b4d9ca77f98cdb993626457a8093f"],"state_sha256":"28376c7c6dfe558de562c1bfd2629b69cc18290abb9de313a08bd9161169b807"}