{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QBUECWOVNNMHAQZHFUKLXLY4C2","short_pith_number":"pith:QBUECWOV","canonical_record":{"source":{"id":"2509.05949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-07T07:07:59Z","cross_cats_sorted":[],"title_canon_sha256":"69d817dedc815b4e7b36d3ac625c60023c13bf19ec280fda8aa0b46e9a9c6be2","abstract_canon_sha256":"cd83938965213721cfaee5d933876776ec5cecbf68697ab856214fa3c325babf"},"schema_version":"1.0"},"canonical_sha256":"80684159d56b587043272d14bbaf1c168c12588a7037fb9ff650c48fbaa354a3","source":{"kind":"arxiv","id":"2509.05949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05949","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05949v1","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05949","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"QBUECWOVNNMH","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"QBUECWOVNNMHAQZH","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"QBUECWOV","created_at":"2026-07-05T12:06:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QBUECWOVNNMHAQZHFUKLXLY4C2","target":"record","payload":{"canonical_record":{"source":{"id":"2509.05949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-07T07:07:59Z","cross_cats_sorted":[],"title_canon_sha256":"69d817dedc815b4e7b36d3ac625c60023c13bf19ec280fda8aa0b46e9a9c6be2","abstract_canon_sha256":"cd83938965213721cfaee5d933876776ec5cecbf68697ab856214fa3c325babf"},"schema_version":"1.0"},"canonical_sha256":"80684159d56b587043272d14bbaf1c168c12588a7037fb9ff650c48fbaa354a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:27.059542Z","signature_b64":"+bEI8gQCUL2f80f9OrmZrrKJctrAVEzJpqo4bAPJ9PO4fLJa4q1G5AS94dUSpoCDA1wcdVIFCnaRhDoqTY1nBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80684159d56b587043272d14bbaf1c168c12588a7037fb9ff650c48fbaa354a3","last_reissued_at":"2026-07-05T12:06:27.058987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:27.058987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.05949","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Elwtf0pClom6uzO3An7gpOEIcZrLpj3nhGRJRt2H/l5jQiWZqS6G6sIgRhGHAFtwoAGZ12dvXZtQUSip3D5pCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:18:53.721283Z"},"content_sha256":"279ffd27450eaa3e0cc2d6675073ac87096db3c2f26218d0d17c21aadffc08d6","schema_version":"1.0","event_id":"sha256:279ffd27450eaa3e0cc2d6675073ac87096db3c2f26218d0d17c21aadffc08d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QBUECWOVNNMHAQZHFUKLXLY4C2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AttriPrompt: Dynamic Prompt Composition Learning for CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qingjie Liu, Qiqi Zhan, Shiwei Li, Yunhong Wang","submitted_at":"2025-09-07T07:07:59Z","abstract_excerpt":"The evolution of prompt learning methodologies has driven exploration of deeper prompt designs to enhance model performance. However, current deep text prompting approaches suffer from two critical limitations: Over-reliance on constrastive learning objectives that prioritize high-level semantic alignment, neglecting fine-grained feature optimization; Static prompts across all input categories, preventing content-aware adaptation. To address these limitations, we propose AttriPrompt-a novel framework that enhances and refines textual semantic representations by leveraging the intermediate-laye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05949","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/2509.05949/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":"2026-07-05T12:06:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"he2aCdVymJUVZwKWXEqcFQUTYrZpXhxBoe6OC+8lAcZ6BQJseomE3TJaWj2ScdUT/cdFqWbgeBJru2RH8Pa0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:18:53.721824Z"},"content_sha256":"8af49a3c8b5dbe1ac20ccbde93320722b5998bb1db5d142d65ee7bccccb1b058","schema_version":"1.0","event_id":"sha256:8af49a3c8b5dbe1ac20ccbde93320722b5998bb1db5d142d65ee7bccccb1b058"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QBUECWOVNNMHAQZHFUKLXLY4C2/bundle.json","state_url":"https://pith.science/pith/QBUECWOVNNMHAQZHFUKLXLY4C2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QBUECWOVNNMHAQZHFUKLXLY4C2/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":"2026-08-15T20:18:53Z","links":{"resolver":"https://pith.science/pith/QBUECWOVNNMHAQZHFUKLXLY4C2","bundle":"https://pith.science/pith/QBUECWOVNNMHAQZHFUKLXLY4C2/bundle.json","state":"https://pith.science/pith/QBUECWOVNNMHAQZHFUKLXLY4C2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QBUECWOVNNMHAQZHFUKLXLY4C2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QBUECWOVNNMHAQZHFUKLXLY4C2","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":"cd83938965213721cfaee5d933876776ec5cecbf68697ab856214fa3c325babf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-07T07:07:59Z","title_canon_sha256":"69d817dedc815b4e7b36d3ac625c60023c13bf19ec280fda8aa0b46e9a9c6be2"},"schema_version":"1.0","source":{"id":"2509.05949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05949","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05949v1","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05949","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"QBUECWOVNNMH","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"QBUECWOVNNMHAQZH","created_at":"2026-07-05T12:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"QBUECWOV","created_at":"2026-07-05T12:06:27Z"}],"graph_snapshots":[{"event_id":"sha256:8af49a3c8b5dbe1ac20ccbde93320722b5998bb1db5d142d65ee7bccccb1b058","target":"graph","created_at":"2026-07-05T12:06:27Z","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/2509.05949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evolution of prompt learning methodologies has driven exploration of deeper prompt designs to enhance model performance. However, current deep text prompting approaches suffer from two critical limitations: Over-reliance on constrastive learning objectives that prioritize high-level semantic alignment, neglecting fine-grained feature optimization; Static prompts across all input categories, preventing content-aware adaptation. To address these limitations, we propose AttriPrompt-a novel framework that enhances and refines textual semantic representations by leveraging the intermediate-laye","authors_text":"Qingjie Liu, Qiqi Zhan, Shiwei Li, Yunhong Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-07T07:07:59Z","title":"AttriPrompt: Dynamic Prompt Composition Learning for CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05949","kind":"arxiv","version":1},"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":"sha256:279ffd27450eaa3e0cc2d6675073ac87096db3c2f26218d0d17c21aadffc08d6","target":"record","created_at":"2026-07-05T12:06:27Z","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":"cd83938965213721cfaee5d933876776ec5cecbf68697ab856214fa3c325babf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-07T07:07:59Z","title_canon_sha256":"69d817dedc815b4e7b36d3ac625c60023c13bf19ec280fda8aa0b46e9a9c6be2"},"schema_version":"1.0","source":{"id":"2509.05949","kind":"arxiv","version":1}},"canonical_sha256":"80684159d56b587043272d14bbaf1c168c12588a7037fb9ff650c48fbaa354a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80684159d56b587043272d14bbaf1c168c12588a7037fb9ff650c48fbaa354a3","first_computed_at":"2026-07-05T12:06:27.058987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:27.058987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+bEI8gQCUL2f80f9OrmZrrKJctrAVEzJpqo4bAPJ9PO4fLJa4q1G5AS94dUSpoCDA1wcdVIFCnaRhDoqTY1nBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:27.059542Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:279ffd27450eaa3e0cc2d6675073ac87096db3c2f26218d0d17c21aadffc08d6","sha256:8af49a3c8b5dbe1ac20ccbde93320722b5998bb1db5d142d65ee7bccccb1b058"],"state_sha256":"de698ca160af1d905a2afaa4a47f1e0b3a475964d0de5e5479b20e89ae3b1fa4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUeNqf5AqcohoPrHISkEKSAmk+m3pub05JYYNlZgVrdsxm/mZpXwbKm7N6pWY2b7BMu9oMiRB2gAkF6Sa6wBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T20:18:53.727363Z","bundle_sha256":"a7463019c28bc72e2bc317ed6d12c739d490951d56f5329ee9ac9a4ae6fa29dc"}}