{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4QBGXCP7HJHWKJS7UKXZ3TMMJ4","short_pith_number":"pith:4QBGXCP7","canonical_record":{"source":{"id":"2504.21423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T08:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"d77e33c052fc51b7f4285c262cb69fb2df2b67699c5ed7a75bb0af0bcbe6bc4a","abstract_canon_sha256":"9dc2c28d87e61a5f1afa9efada1b5e6fa0efe13d1f209bfc65bd6c9ef54919c5"},"schema_version":"1.0"},"canonical_sha256":"e4026b89ff3a4f65265fa2af9dcd8c4f35170eb50ef1c7d14df511c3de5e3c74","source":{"kind":"arxiv","id":"2504.21423","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21423","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21423v1","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21423","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"pith_short_12","alias_value":"4QBGXCP7HJHW","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"pith_short_16","alias_value":"4QBGXCP7HJHWKJS7","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"pith_short_8","alias_value":"4QBGXCP7","created_at":"2026-07-05T10:56:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4QBGXCP7HJHWKJS7UKXZ3TMMJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2504.21423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T08:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"d77e33c052fc51b7f4285c262cb69fb2df2b67699c5ed7a75bb0af0bcbe6bc4a","abstract_canon_sha256":"9dc2c28d87e61a5f1afa9efada1b5e6fa0efe13d1f209bfc65bd6c9ef54919c5"},"schema_version":"1.0"},"canonical_sha256":"e4026b89ff3a4f65265fa2af9dcd8c4f35170eb50ef1c7d14df511c3de5e3c74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:23.601082Z","signature_b64":"A79xINT07IXY5xzTnN/EQLpfnaU3k6ZAMdqf/HNALsZtG0by3Jy0eI28Gm4mFzHhSA/Tow/SWHMLzUADdOORBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4026b89ff3a4f65265fa2af9dcd8c4f35170eb50ef1c7d14df511c3de5e3c74","last_reissued_at":"2026-07-05T10:56:23.600570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:23.600570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.21423","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":"2026-07-05T10:56:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UlrCQ8TIGq5SVVqasHGImwAD1/WJ5t5h1ReXcdJOdKCUjqFMtSYeajBtm91/IyTTuKJ0JB92HmkxV8y1BPBGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:53:55.342949Z"},"content_sha256":"3ef250d5be090bbae68ff376575b483c3edec71b26cfaddeb131c33f60da7726","schema_version":"1.0","event_id":"sha256:3ef250d5be090bbae68ff376575b483c3edec71b26cfaddeb131c33f60da7726"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4QBGXCP7HJHWKJS7UKXZ3TMMJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fangming Feng, Tao Jin, Wang Lin, Weicai Yan, Xiaoda Yang, Ye Wang, Zehan Wang, Zirun Guo","submitted_at":"2025-04-30T08:28:38Z","abstract_excerpt":"Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods directly optimize the parameters involved in the prompt generation process through loss backpropagation, which constrains the richness and specificity of the prompt representations. In this paper, we propose Diffusion-Driven Prompt Generator (Diff-Prompt), aiming to use the diffusion model to generate rich and fine-grained prompt information for complex downs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21423","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/2504.21423/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":"2026-07-05T10:56:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ACueVOGJPcoh20u/AcSgMLH0YREF3La12J8n31DS1EbxhZ922OG79t7162y/29lgKPuEO19cY1pLMcM3pZ5vCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:53:55.343835Z"},"content_sha256":"ff90b99d6ab3c3279d2a9723f848473ffcfe719199bccaa3d6ce841405865838","schema_version":"1.0","event_id":"sha256:ff90b99d6ab3c3279d2a9723f848473ffcfe719199bccaa3d6ce841405865838"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4QBGXCP7HJHWKJS7UKXZ3TMMJ4/bundle.json","state_url":"https://pith.science/pith/4QBGXCP7HJHWKJS7UKXZ3TMMJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4QBGXCP7HJHWKJS7UKXZ3TMMJ4/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":"2026-08-07T19:53:55Z","links":{"resolver":"https://pith.science/pith/4QBGXCP7HJHWKJS7UKXZ3TMMJ4","bundle":"https://pith.science/pith/4QBGXCP7HJHWKJS7UKXZ3TMMJ4/bundle.json","state":"https://pith.science/pith/4QBGXCP7HJHWKJS7UKXZ3TMMJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4QBGXCP7HJHWKJS7UKXZ3TMMJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4QBGXCP7HJHWKJS7UKXZ3TMMJ4","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":"9dc2c28d87e61a5f1afa9efada1b5e6fa0efe13d1f209bfc65bd6c9ef54919c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T08:28:38Z","title_canon_sha256":"d77e33c052fc51b7f4285c262cb69fb2df2b67699c5ed7a75bb0af0bcbe6bc4a"},"schema_version":"1.0","source":{"id":"2504.21423","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.21423","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.21423v1","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21423","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"pith_short_12","alias_value":"4QBGXCP7HJHW","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"pith_short_16","alias_value":"4QBGXCP7HJHWKJS7","created_at":"2026-07-05T10:56:23Z"},{"alias_kind":"pith_short_8","alias_value":"4QBGXCP7","created_at":"2026-07-05T10:56:23Z"}],"graph_snapshots":[{"event_id":"sha256:ff90b99d6ab3c3279d2a9723f848473ffcfe719199bccaa3d6ce841405865838","target":"graph","created_at":"2026-07-05T10:56:23Z","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/2504.21423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt learning has demonstrated promising results in fine-tuning pre-trained multimodal models. However, the performance improvement is limited when applied to more complex and fine-grained tasks. The reason is that most existing methods directly optimize the parameters involved in the prompt generation process through loss backpropagation, which constrains the richness and specificity of the prompt representations. In this paper, we propose Diffusion-Driven Prompt Generator (Diff-Prompt), aiming to use the diffusion model to generate rich and fine-grained prompt information for complex downs","authors_text":"Fangming Feng, Tao Jin, Wang Lin, Weicai Yan, Xiaoda Yang, Ye Wang, Zehan Wang, Zirun Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T08:28:38Z","title":"Diff-Prompt: Diffusion-Driven Prompt Generator with Mask Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21423","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":"sha256:3ef250d5be090bbae68ff376575b483c3edec71b26cfaddeb131c33f60da7726","target":"record","created_at":"2026-07-05T10:56:23Z","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":"9dc2c28d87e61a5f1afa9efada1b5e6fa0efe13d1f209bfc65bd6c9ef54919c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T08:28:38Z","title_canon_sha256":"d77e33c052fc51b7f4285c262cb69fb2df2b67699c5ed7a75bb0af0bcbe6bc4a"},"schema_version":"1.0","source":{"id":"2504.21423","kind":"arxiv","version":1}},"canonical_sha256":"e4026b89ff3a4f65265fa2af9dcd8c4f35170eb50ef1c7d14df511c3de5e3c74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4026b89ff3a4f65265fa2af9dcd8c4f35170eb50ef1c7d14df511c3de5e3c74","first_computed_at":"2026-07-05T10:56:23.600570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:23.600570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A79xINT07IXY5xzTnN/EQLpfnaU3k6ZAMdqf/HNALsZtG0by3Jy0eI28Gm4mFzHhSA/Tow/SWHMLzUADdOORBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:23.601082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.21423","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ef250d5be090bbae68ff376575b483c3edec71b26cfaddeb131c33f60da7726","sha256:ff90b99d6ab3c3279d2a9723f848473ffcfe719199bccaa3d6ce841405865838"],"state_sha256":"fe36728d0d6e0baf90c48641b9cd36d7e91d59d941b600193b8c23a16bf26ec7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k7RiEFmK79MfvKiTGREjK+hn2LZlP273zTA/jUq7qB23S4YtguqmU0YNq/BcXorTnyZ6YtNwMJUh5VwS+jH6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:53:55.349617Z","bundle_sha256":"417adabb7b3e8668b062147615a998627395f3dee857abbc04e03f8d977e4376"}}