{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FFQQY5UW6BY4B32CWLWOEYL3Q6","short_pith_number":"pith:FFQQY5UW","schema_version":"1.0","canonical_sha256":"29610c7696f071c0ef42b2ece2617b8783dbb0ff95f92023402da42664178409","source":{"kind":"arxiv","id":"2211.00107","version":3},"attestation_state":"computed","paper":{"title":"Where to start? Analyzing the potential value of intermediate models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Elad Venezian, Leshem Choshen, Noam Slonim, Shachar Don-Yehia, Yoav Katz","submitted_at":"2022-10-31T19:24:02Z","abstract_excerpt":"Previous studies observed that finetuned models may be better base models than the vanilla pretrained model. Such a model, finetuned on some source dataset, may provide a better starting point for a new finetuning process on a desired target dataset. Here, we perform a systematic analysis of this intertraining scheme, over a wide range of English classification tasks. Surprisingly, our analysis suggests that the potential intertraining gain can be analyzed independently for the target dataset under consideration, and for a base model being considered as a starting point. This is in contrast to"},"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":"2211.00107","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T19:24:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"712ba63fc80f9836f6d162d4d8de1fadc1fc2a59cd4b4bf669ec065e72e93121","abstract_canon_sha256":"9cf6d609a6fa39d5291a14c5d66987795b7d18bd0335214d86341fab297146aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:00.717913Z","signature_b64":"dWb9KK863+E6+vGcXGCb7gErxjqvxO8i0D8xOA3b5Hd3uA383qah9z4lbzHPajyHM/c3cQfBWC8KLuHUAj6XBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29610c7696f071c0ef42b2ece2617b8783dbb0ff95f92023402da42664178409","last_reissued_at":"2026-07-05T05:15:00.717422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:00.717422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where to start? Analyzing the potential value of intermediate models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Elad Venezian, Leshem Choshen, Noam Slonim, Shachar Don-Yehia, Yoav Katz","submitted_at":"2022-10-31T19:24:02Z","abstract_excerpt":"Previous studies observed that finetuned models may be better base models than the vanilla pretrained model. Such a model, finetuned on some source dataset, may provide a better starting point for a new finetuning process on a desired target dataset. Here, we perform a systematic analysis of this intertraining scheme, over a wide range of English classification tasks. Surprisingly, our analysis suggests that the potential intertraining gain can be analyzed independently for the target dataset under consideration, and for a base model being considered as a starting point. This is in contrast to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00107","kind":"arxiv","version":3},"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/2211.00107/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":"2211.00107","created_at":"2026-07-05T05:15:00.717484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00107v3","created_at":"2026-07-05T05:15:00.717484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00107","created_at":"2026-07-05T05:15:00.717484+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFQQY5UW6BY4","created_at":"2026-07-05T05:15:00.717484+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFQQY5UW6BY4B32C","created_at":"2026-07-05T05:15:00.717484+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFQQY5UW","created_at":"2026-07-05T05:15:00.717484+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/FFQQY5UW6BY4B32CWLWOEYL3Q6","json":"https://pith.science/pith/FFQQY5UW6BY4B32CWLWOEYL3Q6.json","graph_json":"https://pith.science/api/pith-number/FFQQY5UW6BY4B32CWLWOEYL3Q6/graph.json","events_json":"https://pith.science/api/pith-number/FFQQY5UW6BY4B32CWLWOEYL3Q6/events.json","paper":"https://pith.science/paper/FFQQY5UW"},"agent_actions":{"view_html":"https://pith.science/pith/FFQQY5UW6BY4B32CWLWOEYL3Q6","download_json":"https://pith.science/pith/FFQQY5UW6BY4B32CWLWOEYL3Q6.json","view_paper":"https://pith.science/paper/FFQQY5UW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00107&json=true","fetch_graph":"https://pith.science/api/pith-number/FFQQY5UW6BY4B32CWLWOEYL3Q6/graph.json","fetch_events":"https://pith.science/api/pith-number/FFQQY5UW6BY4B32CWLWOEYL3Q6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFQQY5UW6BY4B32CWLWOEYL3Q6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFQQY5UW6BY4B32CWLWOEYL3Q6/action/storage_attestation","attest_author":"https://pith.science/pith/FFQQY5UW6BY4B32CWLWOEYL3Q6/action/author_attestation","sign_citation":"https://pith.science/pith/FFQQY5UW6BY4B32CWLWOEYL3Q6/action/citation_signature","submit_replication":"https://pith.science/pith/FFQQY5UW6BY4B32CWLWOEYL3Q6/action/replication_record"}},"created_at":"2026-07-05T05:15:00.717484+00:00","updated_at":"2026-07-05T05:15:00.717484+00:00"}