{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LIP7SVXJULAILELDBKYKFAA7L5","short_pith_number":"pith:LIP7SVXJ","schema_version":"1.0","canonical_sha256":"5a1ff956e9a2c08591630ab0a2801f5f769e96a0de6af103be35aa2cef82a6ea","source":{"kind":"arxiv","id":"2607.00125","version":1},"attestation_state":"computed","paper":{"title":"Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edson Araujo, Eshika Khandelwal, Hilde Kuehne, Nina Shvetsova, Walid Bousselham, Yunhan Wang","submitted_at":"2026-06-30T20:00:50Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-shot classifiers without any additional training. Our approach builds on the idea of few-shot classification as a set of pairwise image comparisons, decomposing the task into a set of binary decisions. Given a query image and a support image from a candidate class, the MLLM is prom"},"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":"2607.00125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T20:00:50Z","cross_cats_sorted":[],"title_canon_sha256":"fc7040608f10d350a41695143a67bba5a1f07f6c1f28ca642fe0f0b4b7b199c1","abstract_canon_sha256":"cf60b8b70155e3807bba0ff41f82a0622d6b3ee56c28d30e91955c4556f06780"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:35.665981Z","signature_b64":"59yOb+B/xxOOQ153eZr18OvEcQp71ByBkAkUco4oYq7PIlS+61KvFnun/VIBpuy1aAuutY5eilACVvrwguBSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a1ff956e9a2c08591630ab0a2801f5f769e96a0de6af103be35aa2cef82a6ea","last_reissued_at":"2026-07-02T00:18:35.665324Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:35.665324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Edson Araujo, Eshika Khandelwal, Hilde Kuehne, Nina Shvetsova, Walid Bousselham, Yunhan Wang","submitted_at":"2026-06-30T20:00:50Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-shot classifiers without any additional training. Our approach builds on the idea of few-shot classification as a set of pairwise image comparisons, decomposing the task into a set of binary decisions. Given a query image and a support image from a candidate class, the MLLM is prom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00125","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/2607.00125/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":"2607.00125","created_at":"2026-07-02T00:18:35.665408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00125v1","created_at":"2026-07-02T00:18:35.665408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00125","created_at":"2026-07-02T00:18:35.665408+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIP7SVXJULAI","created_at":"2026-07-02T00:18:35.665408+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIP7SVXJULAILELD","created_at":"2026-07-02T00:18:35.665408+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIP7SVXJ","created_at":"2026-07-02T00:18:35.665408+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/LIP7SVXJULAILELDBKYKFAA7L5","json":"https://pith.science/pith/LIP7SVXJULAILELDBKYKFAA7L5.json","graph_json":"https://pith.science/api/pith-number/LIP7SVXJULAILELDBKYKFAA7L5/graph.json","events_json":"https://pith.science/api/pith-number/LIP7SVXJULAILELDBKYKFAA7L5/events.json","paper":"https://pith.science/paper/LIP7SVXJ"},"agent_actions":{"view_html":"https://pith.science/pith/LIP7SVXJULAILELDBKYKFAA7L5","download_json":"https://pith.science/pith/LIP7SVXJULAILELDBKYKFAA7L5.json","view_paper":"https://pith.science/paper/LIP7SVXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00125&json=true","fetch_graph":"https://pith.science/api/pith-number/LIP7SVXJULAILELDBKYKFAA7L5/graph.json","fetch_events":"https://pith.science/api/pith-number/LIP7SVXJULAILELDBKYKFAA7L5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIP7SVXJULAILELDBKYKFAA7L5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIP7SVXJULAILELDBKYKFAA7L5/action/storage_attestation","attest_author":"https://pith.science/pith/LIP7SVXJULAILELDBKYKFAA7L5/action/author_attestation","sign_citation":"https://pith.science/pith/LIP7SVXJULAILELDBKYKFAA7L5/action/citation_signature","submit_replication":"https://pith.science/pith/LIP7SVXJULAILELDBKYKFAA7L5/action/replication_record"}},"created_at":"2026-07-02T00:18:35.665408+00:00","updated_at":"2026-07-02T00:18:35.665408+00:00"}