{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UQ6OE76CMCRLITW22TK4XFBSI3","short_pith_number":"pith:UQ6OE76C","schema_version":"1.0","canonical_sha256":"a43ce27fc260a2b44edad4d5cb943246effd4fa4b8344d3d64e31db4c70cc287","source":{"kind":"arxiv","id":"2412.13859","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Fischer, Anna Scius-Bertrand, Jean-Marc Spat, Lars V\\\"ogtlin, Michael Jungo","submitted_at":"2024-12-18T13:53:16Z","abstract_excerpt":"Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to near-perfect performance when considering hundreds of thousands of training samples. With the advent of large language models (LLMs), which are excellent few-shot learners, the question arises to what extent the document classification problem can be addressed with only a few training samples, or even none at all. In this paper, we investigate this question in the c"},"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":"2412.13859","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T13:53:16Z","cross_cats_sorted":[],"title_canon_sha256":"197e8971d680b22d352a0fd2d5fb645ab1f227653f48a1d7812484e4c928c81a","abstract_canon_sha256":"081f50a1b57ba4136050619a8e29bf348d302f0980e5fc6d30d6b23190e34d7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:09.854401Z","signature_b64":"60FT7CXkzjhRVW3IahlJLmdrk060KDwW0DnNjptYcqFied7u0KY5JSPs8pQ90d/ReAdijGWCBZCHaUvSIQocBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a43ce27fc260a2b44edad4d5cb943246effd4fa4b8344d3d64e31db4c70cc287","last_reissued_at":"2026-07-05T09:51:09.853811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:09.853811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Fischer, Anna Scius-Bertrand, Jean-Marc Spat, Lars V\\\"ogtlin, Michael Jungo","submitted_at":"2024-12-18T13:53:16Z","abstract_excerpt":"Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to near-perfect performance when considering hundreds of thousands of training samples. With the advent of large language models (LLMs), which are excellent few-shot learners, the question arises to what extent the document classification problem can be addressed with only a few training samples, or even none at all. In this paper, we investigate this question in the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13859","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/2412.13859/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":"2412.13859","created_at":"2026-07-05T09:51:09.853889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13859v1","created_at":"2026-07-05T09:51:09.853889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13859","created_at":"2026-07-05T09:51:09.853889+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQ6OE76CMCRL","created_at":"2026-07-05T09:51:09.853889+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQ6OE76CMCRLITW2","created_at":"2026-07-05T09:51:09.853889+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQ6OE76C","created_at":"2026-07-05T09:51:09.853889+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/UQ6OE76CMCRLITW22TK4XFBSI3","json":"https://pith.science/pith/UQ6OE76CMCRLITW22TK4XFBSI3.json","graph_json":"https://pith.science/api/pith-number/UQ6OE76CMCRLITW22TK4XFBSI3/graph.json","events_json":"https://pith.science/api/pith-number/UQ6OE76CMCRLITW22TK4XFBSI3/events.json","paper":"https://pith.science/paper/UQ6OE76C"},"agent_actions":{"view_html":"https://pith.science/pith/UQ6OE76CMCRLITW22TK4XFBSI3","download_json":"https://pith.science/pith/UQ6OE76CMCRLITW22TK4XFBSI3.json","view_paper":"https://pith.science/paper/UQ6OE76C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13859&json=true","fetch_graph":"https://pith.science/api/pith-number/UQ6OE76CMCRLITW22TK4XFBSI3/graph.json","fetch_events":"https://pith.science/api/pith-number/UQ6OE76CMCRLITW22TK4XFBSI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQ6OE76CMCRLITW22TK4XFBSI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQ6OE76CMCRLITW22TK4XFBSI3/action/storage_attestation","attest_author":"https://pith.science/pith/UQ6OE76CMCRLITW22TK4XFBSI3/action/author_attestation","sign_citation":"https://pith.science/pith/UQ6OE76CMCRLITW22TK4XFBSI3/action/citation_signature","submit_replication":"https://pith.science/pith/UQ6OE76CMCRLITW22TK4XFBSI3/action/replication_record"}},"created_at":"2026-07-05T09:51:09.853889+00:00","updated_at":"2026-07-05T09:51:09.853889+00:00"}