{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OHT47LTL677YHMITHO3DA6IAA4","short_pith_number":"pith:OHT47LTL","schema_version":"1.0","canonical_sha256":"71e7cfae6bf7ff83b1133bb63079000702163358470065d8c2c87529f0756e5e","source":{"kind":"arxiv","id":"2401.06827","version":2},"attestation_state":"computed","paper":{"title":"APLe: Token-Wise Adaptive for Multi-Modal Prompt Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Guandong Xu, Guiming Cao, Hong Fu, Huaiwen Zhang, Kaize Shi","submitted_at":"2024-01-12T04:54:01Z","abstract_excerpt":"Pre-trained Vision-Language (V-L) models set the benchmark for generalization to downstream tasks among the noteworthy contenders. Many characteristics of the V-L model have been explored in existing research including the challenge of the sensitivity to text input and the tuning process across multi-modal prompts. With the advanced utilization of the V-L model like CLIP, recent approaches deploy learnable prompts instead of hand-craft prompts to boost the generalization performance and address the aforementioned challenges. Inspired by layer-wise training, which is wildly used in image fusion"},"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":"2401.06827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-12T04:54:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8d53e8418ada96ddf7631b93d0c392fe639e5f3d097cb4ab907b68603fb53bb7","abstract_canon_sha256":"8f227a2cf47102398db1b45e8e9011899e36ee8b986a764f8943d8dc8d89e978"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:26.372604Z","signature_b64":"CGf0ab0dqrNLDP9ZnabFzg4dIw5sGjmZcd/xeNfJrQsUq37kHQUzkfETnGrq/vHWR3Y/3SXReXn3JRA1JahhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71e7cfae6bf7ff83b1133bb63079000702163358470065d8c2c87529f0756e5e","last_reissued_at":"2026-07-05T07:36:26.372178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:26.372178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"APLe: Token-Wise Adaptive for Multi-Modal Prompt Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Guandong Xu, Guiming Cao, Hong Fu, Huaiwen Zhang, Kaize Shi","submitted_at":"2024-01-12T04:54:01Z","abstract_excerpt":"Pre-trained Vision-Language (V-L) models set the benchmark for generalization to downstream tasks among the noteworthy contenders. Many characteristics of the V-L model have been explored in existing research including the challenge of the sensitivity to text input and the tuning process across multi-modal prompts. With the advanced utilization of the V-L model like CLIP, recent approaches deploy learnable prompts instead of hand-craft prompts to boost the generalization performance and address the aforementioned challenges. Inspired by layer-wise training, which is wildly used in image fusion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06827","kind":"arxiv","version":2},"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/2401.06827/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":"2401.06827","created_at":"2026-07-05T07:36:26.372233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06827v2","created_at":"2026-07-05T07:36:26.372233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06827","created_at":"2026-07-05T07:36:26.372233+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHT47LTL677Y","created_at":"2026-07-05T07:36:26.372233+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHT47LTL677YHMIT","created_at":"2026-07-05T07:36:26.372233+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHT47LTL","created_at":"2026-07-05T07:36:26.372233+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/OHT47LTL677YHMITHO3DA6IAA4","json":"https://pith.science/pith/OHT47LTL677YHMITHO3DA6IAA4.json","graph_json":"https://pith.science/api/pith-number/OHT47LTL677YHMITHO3DA6IAA4/graph.json","events_json":"https://pith.science/api/pith-number/OHT47LTL677YHMITHO3DA6IAA4/events.json","paper":"https://pith.science/paper/OHT47LTL"},"agent_actions":{"view_html":"https://pith.science/pith/OHT47LTL677YHMITHO3DA6IAA4","download_json":"https://pith.science/pith/OHT47LTL677YHMITHO3DA6IAA4.json","view_paper":"https://pith.science/paper/OHT47LTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06827&json=true","fetch_graph":"https://pith.science/api/pith-number/OHT47LTL677YHMITHO3DA6IAA4/graph.json","fetch_events":"https://pith.science/api/pith-number/OHT47LTL677YHMITHO3DA6IAA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHT47LTL677YHMITHO3DA6IAA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHT47LTL677YHMITHO3DA6IAA4/action/storage_attestation","attest_author":"https://pith.science/pith/OHT47LTL677YHMITHO3DA6IAA4/action/author_attestation","sign_citation":"https://pith.science/pith/OHT47LTL677YHMITHO3DA6IAA4/action/citation_signature","submit_replication":"https://pith.science/pith/OHT47LTL677YHMITHO3DA6IAA4/action/replication_record"}},"created_at":"2026-07-05T07:36:26.372233+00:00","updated_at":"2026-07-05T07:36:26.372233+00:00"}