{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SGYGLW7BRMBCVXS765RX66GGUU","short_pith_number":"pith:SGYGLW7B","schema_version":"1.0","canonical_sha256":"91b065dbe18b022ade5ff7637f78c6a51baf5274cb3bdf9f58f8fa85b9ff51e0","source":{"kind":"arxiv","id":"2509.00305","version":1},"attestation_state":"computed","paper":{"title":"Language-Aware Information Maximization for Transductive Few-Shot CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ghassen Baklouti, Ismail Ben Ayed, Maxime Zanella","submitted_at":"2025-08-30T01:46:31Z","abstract_excerpt":"Transductive few-shot learning has triggered an abundant literature focusing on vision-only models, but is still at a nascent stage within the recent context of foundational vision-language models (VLMs). Only a few recent methods addressed the problem, pointing to the potential of tranduction in VLMs and to the need for VLM-tailored methods. Building on this momentum, we leverage information-theoretic concepts and recent progress in parameter-efficient fine-tuning (PEFT), developing a highly competitive transductive few-shot CLIP method. Specifically, we introduce a novel Language-aware Infor"},"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":"2509.00305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-30T01:46:31Z","cross_cats_sorted":[],"title_canon_sha256":"0af4e38b7acae588308e0ce1ea751a180cddefa6b9c3f3dbabf1893544658c49","abstract_canon_sha256":"e476852649d3d8a43cdea61f1f7a2d50747652df6b425f0c7d6bdd8685236308"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:13.346708Z","signature_b64":"PzZem0NIbbJMnyr4RYPhfvxhL81JhSD7INBNZtskc/LkNCao2eIol561tF03xSeVttM+3EmJfA/Dwd6g83DsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91b065dbe18b022ade5ff7637f78c6a51baf5274cb3bdf9f58f8fa85b9ff51e0","last_reissued_at":"2026-07-05T12:02:13.346277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:13.346277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-Aware Information Maximization for Transductive Few-Shot CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ghassen Baklouti, Ismail Ben Ayed, Maxime Zanella","submitted_at":"2025-08-30T01:46:31Z","abstract_excerpt":"Transductive few-shot learning has triggered an abundant literature focusing on vision-only models, but is still at a nascent stage within the recent context of foundational vision-language models (VLMs). Only a few recent methods addressed the problem, pointing to the potential of tranduction in VLMs and to the need for VLM-tailored methods. Building on this momentum, we leverage information-theoretic concepts and recent progress in parameter-efficient fine-tuning (PEFT), developing a highly competitive transductive few-shot CLIP method. Specifically, we introduce a novel Language-aware Infor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00305","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/2509.00305/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":"2509.00305","created_at":"2026-07-05T12:02:13.346342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00305v1","created_at":"2026-07-05T12:02:13.346342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00305","created_at":"2026-07-05T12:02:13.346342+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGYGLW7BRMBC","created_at":"2026-07-05T12:02:13.346342+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGYGLW7BRMBCVXS7","created_at":"2026-07-05T12:02:13.346342+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGYGLW7B","created_at":"2026-07-05T12:02:13.346342+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/SGYGLW7BRMBCVXS765RX66GGUU","json":"https://pith.science/pith/SGYGLW7BRMBCVXS765RX66GGUU.json","graph_json":"https://pith.science/api/pith-number/SGYGLW7BRMBCVXS765RX66GGUU/graph.json","events_json":"https://pith.science/api/pith-number/SGYGLW7BRMBCVXS765RX66GGUU/events.json","paper":"https://pith.science/paper/SGYGLW7B"},"agent_actions":{"view_html":"https://pith.science/pith/SGYGLW7BRMBCVXS765RX66GGUU","download_json":"https://pith.science/pith/SGYGLW7BRMBCVXS765RX66GGUU.json","view_paper":"https://pith.science/paper/SGYGLW7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00305&json=true","fetch_graph":"https://pith.science/api/pith-number/SGYGLW7BRMBCVXS765RX66GGUU/graph.json","fetch_events":"https://pith.science/api/pith-number/SGYGLW7BRMBCVXS765RX66GGUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGYGLW7BRMBCVXS765RX66GGUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGYGLW7BRMBCVXS765RX66GGUU/action/storage_attestation","attest_author":"https://pith.science/pith/SGYGLW7BRMBCVXS765RX66GGUU/action/author_attestation","sign_citation":"https://pith.science/pith/SGYGLW7BRMBCVXS765RX66GGUU/action/citation_signature","submit_replication":"https://pith.science/pith/SGYGLW7BRMBCVXS765RX66GGUU/action/replication_record"}},"created_at":"2026-07-05T12:02:13.346342+00:00","updated_at":"2026-07-05T12:02:13.346342+00:00"}