{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FESQ3MSVYUEOTJPP4JEE52WUCK","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":"4a5ccbab7e649dd0180206c7cc7f9b7c2c1dabe67f3db479cd51d4a792241a94","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T00:00:36Z","title_canon_sha256":"bd5071b038c919fa1a20cb6a3e3527b89388f9dba570013c05461307d2b7842d"},"schema_version":"1.0","source":{"id":"2504.05571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.05571","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2504.05571v1","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05571","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"FESQ3MSVYUEO","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"FESQ3MSVYUEOTJPP","created_at":"2026-07-05T10:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"FESQ3MSV","created_at":"2026-07-05T10:46:05Z"}],"graph_snapshots":[{"event_id":"sha256:9ac6dc5ca2ec13ac43fd4487b802ea6c96b2191f99f90c520d7acc36d3de3ef5","target":"graph","created_at":"2026-07-05T10:46:05Z","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/2504.05571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Models (LLMs) acquire vast knowledge during pre-training, they often lack domain-specific, new, or niche information. Continual pre-training (CPT) attempts to address this gap but suffers from catastrophic forgetting and inefficiencies in low-data regimes. We introduce Knowledge-Instruct, a novel approach to efficiently inject knowledge from limited corpora through pure instruction-tuning. By generating information-dense synthetic instruction data, it effectively integrates new knowledge while preserving general reasoning and instruction-following abilities. Knowledge-Inst","authors_text":"Eitam Sheetrit, Meni Brief, Oded Ovadia, Rachel Lemberg","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T00:00:36Z","title":"Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05571","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":"sha256:63edc5542df235d6ac110aafe90e58bd7f362d732e77a97b917cee1d25d7351f","target":"record","created_at":"2026-07-05T10:46:05Z","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":"4a5ccbab7e649dd0180206c7cc7f9b7c2c1dabe67f3db479cd51d4a792241a94","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-08T00:00:36Z","title_canon_sha256":"bd5071b038c919fa1a20cb6a3e3527b89388f9dba570013c05461307d2b7842d"},"schema_version":"1.0","source":{"id":"2504.05571","kind":"arxiv","version":1}},"canonical_sha256":"29250db255c508e9a5efe2484eead4129e4153e6fc7b2a2337b795808715e08c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29250db255c508e9a5efe2484eead4129e4153e6fc7b2a2337b795808715e08c","first_computed_at":"2026-07-05T10:46:05.950590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:05.950590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A0syGJMMsX05ZBKQoa201jIVwEL/oz9fwKP9zk60kmCUImQ7kVP2dSFu30HdC0jE5hPG4/mhE0RtsoHP2omfBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:05.951087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.05571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63edc5542df235d6ac110aafe90e58bd7f362d732e77a97b917cee1d25d7351f","sha256:9ac6dc5ca2ec13ac43fd4487b802ea6c96b2191f99f90c520d7acc36d3de3ef5"],"state_sha256":"89ba90e20481835bf09edf68b9751c7ae0291cafe68b3a48c152aedc5538bcbf"}