{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GLLQJZOTV554HQ6Z7BBMR72IQH","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":"176d0f218d4a3016bfd5684758647e13639a5cfb9e3f9a7b6c58a5e71a8e5715","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T10:42:43Z","title_canon_sha256":"1c2f7b9919e5137053c3ca969c8e2394c4e2d324aa728e3d539f27abcbab4ee3"},"schema_version":"1.0","source":{"id":"2505.24455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24455","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24455v1","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24455","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"GLLQJZOTV554","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"GLLQJZOTV554HQ6Z","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"GLLQJZOT","created_at":"2026-07-05T11:12:50Z"}],"graph_snapshots":[{"event_id":"sha256:2f9eb0d7eb6efe86f87c216571df2633dc90cfc603ba82ee3a4676a239edd936","target":"graph","created_at":"2026-07-05T11:12:50Z","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/2505.24455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This empirical study analyzes the effects of the pre-training corpus on the quality of learned transformer representations. We focus on the representation quality induced solely through pre-training. Our experiments show that pre-training on a small, specialized corpus can yield effective representations, and that the success of combining a generic and a specialized corpus depends on the distributional similarity between the target task and the specialized corpus.","authors_text":"Ariadna Quattoni, Cesar Gonzalez-Gutierrez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T10:42:43Z","title":"Domain Pre-training Impact on Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24455","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":"sha256:67722c3b4bdf35e0bb70f1a84d8027020964cf00917f34e34b590b49a3b85aa2","target":"record","created_at":"2026-07-05T11:12:50Z","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":"176d0f218d4a3016bfd5684758647e13639a5cfb9e3f9a7b6c58a5e71a8e5715","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T10:42:43Z","title_canon_sha256":"1c2f7b9919e5137053c3ca969c8e2394c4e2d324aa728e3d539f27abcbab4ee3"},"schema_version":"1.0","source":{"id":"2505.24455","kind":"arxiv","version":1}},"canonical_sha256":"32d704e5d3af7bc3c3d9f842c8ff4881e84916e2a0aaaa9eab29654a46685e80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32d704e5d3af7bc3c3d9f842c8ff4881e84916e2a0aaaa9eab29654a46685e80","first_computed_at":"2026-07-05T11:12:50.077560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:50.077560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A7ZrpE06U5mIj1TBzt7yiOoW4wTyshg2iTWvXQhGWJq4d0egOacxFnzv2kptQCBTyl6WYBRACIbbZwlQnp3HAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:50.078100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67722c3b4bdf35e0bb70f1a84d8027020964cf00917f34e34b590b49a3b85aa2","sha256:2f9eb0d7eb6efe86f87c216571df2633dc90cfc603ba82ee3a4676a239edd936"],"state_sha256":"a861faedd30b8eed3d89d5776d4feed49d7f20f1e95e98f8f262867f3f013177"}