{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KTMV44XZ6YYHPZ7GJHUWKYZUMB","short_pith_number":"pith:KTMV44XZ","canonical_record":{"source":{"id":"2210.03117","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-06T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"4807122f6a965abe4c2bd2ad13b6cdc712f1c198198c2b797140ab33fefac06e","abstract_canon_sha256":"fe001d0100706a4331c39578a67cf32953e6f3cdaabb18b9f59d4cb4c1fdd370"},"schema_version":"1.0"},"canonical_sha256":"54d95e72f9f63077e7e649e9656334605d8e74c870f7b5d1dcaa794ead64c41a","source":{"kind":"arxiv","id":"2210.03117","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03117","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03117v3","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03117","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"KTMV44XZ6YYH","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"KTMV44XZ6YYHPZ7G","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"KTMV44XZ","created_at":"2026-07-05T05:56:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KTMV44XZ6YYHPZ7GJHUWKYZUMB","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03117","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-06T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"4807122f6a965abe4c2bd2ad13b6cdc712f1c198198c2b797140ab33fefac06e","abstract_canon_sha256":"fe001d0100706a4331c39578a67cf32953e6f3cdaabb18b9f59d4cb4c1fdd370"},"schema_version":"1.0"},"canonical_sha256":"54d95e72f9f63077e7e649e9656334605d8e74c870f7b5d1dcaa794ead64c41a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:54.793733Z","signature_b64":"kqRTjS1NFI1z+/tDbExWqt79F0fyJxBV10gBGeq4eDbwiOLKFCud/eTd1g0GYFV+kLpwJK0zt4hXwh8JeKdKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54d95e72f9f63077e7e649e9656334605d8e74c870f7b5d1dcaa794ead64c41a","last_reissued_at":"2026-07-05T05:56:54.793275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:54.793275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03117","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFanc4QD+35L4BYFenkSHYzFicQ5ZKoYC/UuEIMPB2DShFw2H+wE5cTYYgAjwNe+vxZTqbGBqD3vjyJbvF6pCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T23:59:29.889879Z"},"content_sha256":"332cbd17f26c61301e715921183437703744f4adf2d1f71f99a14b86aefcb3d2","schema_version":"1.0","event_id":"sha256:332cbd17f26c61301e715921183437703744f4adf2d1f71f99a14b86aefcb3d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KTMV44XZ6YYHPZ7GJHUWKYZUMB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaPLe: Multi-modal Prompt Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","submitted_at":"2022-10-06T17:59:56Z","abstract_excerpt":"Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well. Inspired by the Natural Language Processing (NLP) literature, recent CLIP adaptation approaches learn prompts as the textual inputs to fine-tune CLIP for downstream tasks. We note that using prompting to adapt representations in a single branch of CLIP (language or vision) is sub-optimal since it does not allow the flexibility to dynamically adjust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03117","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/2210.03117/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2lzpZAwO72RlyJbCwAUOwbB+51uiXS17zpDAMeqhvM/X33FMGykojGK/aoTA1QiUmcfXxRLyb3FIcit/DyHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T23:59:29.890375Z"},"content_sha256":"914d1748ac5bab2cfc975478a1ea4f155547f860a8762e32faaad0edb12387a4","schema_version":"1.0","event_id":"sha256:914d1748ac5bab2cfc975478a1ea4f155547f860a8762e32faaad0edb12387a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/bundle.json","state_url":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T23:59:29Z","links":{"resolver":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB","bundle":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/bundle.json","state":"https://pith.science/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTMV44XZ6YYHPZ7GJHUWKYZUMB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KTMV44XZ6YYHPZ7GJHUWKYZUMB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe001d0100706a4331c39578a67cf32953e6f3cdaabb18b9f59d4cb4c1fdd370","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-06T17:59:56Z","title_canon_sha256":"4807122f6a965abe4c2bd2ad13b6cdc712f1c198198c2b797140ab33fefac06e"},"schema_version":"1.0","source":{"id":"2210.03117","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03117","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03117v3","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03117","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"KTMV44XZ6YYH","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"KTMV44XZ6YYHPZ7G","created_at":"2026-07-05T05:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"KTMV44XZ","created_at":"2026-07-05T05:56:54Z"}],"graph_snapshots":[{"event_id":"sha256:914d1748ac5bab2cfc975478a1ea4f155547f860a8762e32faaad0edb12387a4","target":"graph","created_at":"2026-07-05T05:56:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.03117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well. Inspired by the Natural Language Processing (NLP) literature, recent CLIP adaptation approaches learn prompts as the textual inputs to fine-tune CLIP for downstream tasks. We note that using prompting to adapt representations in a single branch of CLIP (language or vision) is sub-optimal since it does not allow the flexibility to dynamically adjust","authors_text":"Fahad Shahbaz Khan, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-06T17:59:56Z","title":"MaPLe: Multi-modal Prompt Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03117","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:332cbd17f26c61301e715921183437703744f4adf2d1f71f99a14b86aefcb3d2","target":"record","created_at":"2026-07-05T05:56:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fe001d0100706a4331c39578a67cf32953e6f3cdaabb18b9f59d4cb4c1fdd370","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-06T17:59:56Z","title_canon_sha256":"4807122f6a965abe4c2bd2ad13b6cdc712f1c198198c2b797140ab33fefac06e"},"schema_version":"1.0","source":{"id":"2210.03117","kind":"arxiv","version":3}},"canonical_sha256":"54d95e72f9f63077e7e649e9656334605d8e74c870f7b5d1dcaa794ead64c41a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54d95e72f9f63077e7e649e9656334605d8e74c870f7b5d1dcaa794ead64c41a","first_computed_at":"2026-07-05T05:56:54.793275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:54.793275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kqRTjS1NFI1z+/tDbExWqt79F0fyJxBV10gBGeq4eDbwiOLKFCud/eTd1g0GYFV+kLpwJK0zt4hXwh8JeKdKBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:54.793733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03117","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:332cbd17f26c61301e715921183437703744f4adf2d1f71f99a14b86aefcb3d2","sha256:914d1748ac5bab2cfc975478a1ea4f155547f860a8762e32faaad0edb12387a4"],"state_sha256":"1da420ee50191d8cff4e080515c280636ab9e86f97ac725c9bd074d7f5bba9fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q1n0e5amlvsoPx9EmGLj1DhMJ4+9KchEdval1qTJb5zoyPRzIm/aMfHb0Si034hipjC+wJCRgIq/495sMsP4CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T23:59:29.895192Z","bundle_sha256":"2ed20e023571385c1b5175edea36cc900c9cff7719c826822ee1bb4519151344"}}