{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GLLQJZOTV554HQ6Z7BBMR72IQH","short_pith_number":"pith:GLLQJZOT","schema_version":"1.0","canonical_sha256":"32d704e5d3af7bc3c3d9f842c8ff4881e84916e2a0aaaa9eab29654a46685e80","source":{"kind":"arxiv","id":"2505.24455","version":1},"attestation_state":"computed","paper":{"title":"Domain Pre-training Impact on Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ariadna Quattoni, Cesar Gonzalez-Gutierrez","submitted_at":"2025-05-30T10:42:43Z","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."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.24455","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T10:42:43Z","cross_cats_sorted":[],"title_canon_sha256":"1c2f7b9919e5137053c3ca969c8e2394c4e2d324aa728e3d539f27abcbab4ee3","abstract_canon_sha256":"176d0f218d4a3016bfd5684758647e13639a5cfb9e3f9a7b6c58a5e71a8e5715"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:50.078100Z","signature_b64":"A7ZrpE06U5mIj1TBzt7yiOoW4wTyshg2iTWvXQhGWJq4d0egOacxFnzv2kptQCBTyl6WYBRACIbbZwlQnp3HAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32d704e5d3af7bc3c3d9f842c8ff4881e84916e2a0aaaa9eab29654a46685e80","last_reissued_at":"2026-07-05T11:12:50.077560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:50.077560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Pre-training Impact on Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ariadna Quattoni, Cesar Gonzalez-Gutierrez","submitted_at":"2025-05-30T10:42:43Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24455","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/2505.24455/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.24455","created_at":"2026-07-05T11:12:50.077623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24455v1","created_at":"2026-07-05T11:12:50.077623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24455","created_at":"2026-07-05T11:12:50.077623+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLLQJZOTV554","created_at":"2026-07-05T11:12:50.077623+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLLQJZOTV554HQ6Z","created_at":"2026-07-05T11:12:50.077623+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLLQJZOT","created_at":"2026-07-05T11:12:50.077623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH","json":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH.json","graph_json":"https://pith.science/api/pith-number/GLLQJZOTV554HQ6Z7BBMR72IQH/graph.json","events_json":"https://pith.science/api/pith-number/GLLQJZOTV554HQ6Z7BBMR72IQH/events.json","paper":"https://pith.science/paper/GLLQJZOT"},"agent_actions":{"view_html":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH","download_json":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH.json","view_paper":"https://pith.science/paper/GLLQJZOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24455&json=true","fetch_graph":"https://pith.science/api/pith-number/GLLQJZOTV554HQ6Z7BBMR72IQH/graph.json","fetch_events":"https://pith.science/api/pith-number/GLLQJZOTV554HQ6Z7BBMR72IQH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH/action/storage_attestation","attest_author":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH/action/author_attestation","sign_citation":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH/action/citation_signature","submit_replication":"https://pith.science/pith/GLLQJZOTV554HQ6Z7BBMR72IQH/action/replication_record"}},"created_at":"2026-07-05T11:12:50.077623+00:00","updated_at":"2026-07-05T11:12:50.077623+00:00"}