{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PRDJUS7HPCJOHJQ4WJL3OCDOLR","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":"7004eb3744ea820a27556dc262db7a8a27804a5b859221719745bc1811a14fa0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-08T17:58:15Z","title_canon_sha256":"efe84471e9087fa3d2f4e36a74508124e4c3aa51873ea86337bf98b0fb703471"},"schema_version":"1.0","source":{"id":"2308.04430","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04430","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04430v2","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04430","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_12","alias_value":"PRDJUS7HPCJO","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_16","alias_value":"PRDJUS7HPCJOHJQ4","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_8","alias_value":"PRDJUS7H","created_at":"2026-07-05T08:50:24Z"}],"graph_snapshots":[{"event_id":"sha256:4fccb8ad6f5b59f789d7fbc2aa65f15c425814a8b876a68aa1b9b14ee7b2fad9","target":"graph","created_at":"2026-07-05T08:50:24Z","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/2308.04430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The legality of training language models (LMs) on copyrighted or otherwise restricted data is under intense debate. However, as we show, model performance significantly degrades if trained only on low-risk text (e.g., out-of-copyright books or government documents), due to its limited size and domain coverage. We present SILO, a new language model that manages this risk-performance tradeoff during inference. SILO is built by (1) training a parametric LM on Open License Corpus (OLC), a new corpus we curate with 228B tokens of public domain and permissively licensed text and (2) augmenting it wi","authors_text":"Eric Wallace, Hannaneh Hajishirzi, Luke Zettlemoyer, Noah A. Smith, Sewon Min, Suchin Gururangan, Weijia Shi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-08T17:58:15Z","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04430","kind":"arxiv","version":2},"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":"sha256:0d246ff9a66cba6c0e0827a9b28acf0686785cfb3614868aac31efbd50b6f1a4","target":"record","created_at":"2026-07-05T08:50:24Z","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":"7004eb3744ea820a27556dc262db7a8a27804a5b859221719745bc1811a14fa0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-08T17:58:15Z","title_canon_sha256":"efe84471e9087fa3d2f4e36a74508124e4c3aa51873ea86337bf98b0fb703471"},"schema_version":"1.0","source":{"id":"2308.04430","kind":"arxiv","version":2}},"canonical_sha256":"7c469a4be77892e3a61cb257b7086e5c5127c1f2f0d88c201e53bb5a381d0b20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c469a4be77892e3a61cb257b7086e5c5127c1f2f0d88c201e53bb5a381d0b20","first_computed_at":"2026-07-05T08:50:24.063080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:24.063080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GxdaDLyMlrIZJHNj8jwQBd/X/wP3f37tPVXMWDzIXB75W7LgOmRw/AhaOuE2tBtjN17MH+gbee8vtwe3t5PxDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:24.063496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.04430","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d246ff9a66cba6c0e0827a9b28acf0686785cfb3614868aac31efbd50b6f1a4","sha256:4fccb8ad6f5b59f789d7fbc2aa65f15c425814a8b876a68aa1b9b14ee7b2fad9"],"state_sha256":"972b50bf113a69646047d9b70b970e93027d8ee3eda53f666a3202eeef28716a"}