{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GHLSUVJ56FRR3NAZ2W4MZLNXX7","short_pith_number":"pith:GHLSUVJ5","canonical_record":{"source":{"id":"2605.26421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T01:20:18Z","cross_cats_sorted":[],"title_canon_sha256":"dfc2241e4901a9f9dc4336b5cf07d4a46f55935bcf90108061019eaea72966d3","abstract_canon_sha256":"4827bbd057e7ff13dc10020fbb0a0b811f0eef854cb28229af98314930b7579c"},"schema_version":"1.0"},"canonical_sha256":"31d72a553df1631db419d5b8ccadb7bfc15da7bf772ae9d432d77d1b722b36e0","source":{"kind":"arxiv","id":"2605.26421","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26421","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26421v1","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26421","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"GHLSUVJ56FRR","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"GHLSUVJ56FRR3NAZ","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"GHLSUVJ5","created_at":"2026-05-27T01:05:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GHLSUVJ56FRR3NAZ2W4MZLNXX7","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26421","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T01:20:18Z","cross_cats_sorted":[],"title_canon_sha256":"dfc2241e4901a9f9dc4336b5cf07d4a46f55935bcf90108061019eaea72966d3","abstract_canon_sha256":"4827bbd057e7ff13dc10020fbb0a0b811f0eef854cb28229af98314930b7579c"},"schema_version":"1.0"},"canonical_sha256":"31d72a553df1631db419d5b8ccadb7bfc15da7bf772ae9d432d77d1b722b36e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:16.970689Z","signature_b64":"pvFicOSaWIyaxeosnaLcAy1cHhws40UaXQcJ3JmYZTa5VZf8UtsZzqCANkKhKY283oz+QtarUi3MfmUKT8nHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d72a553df1631db419d5b8ccadb7bfc15da7bf772ae9d432d77d1b722b36e0","last_reissued_at":"2026-05-27T01:05:16.969883Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:16.969883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26421","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":"2026-05-27T01:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H+SdwYzs59gIACbA3U4J29JLZOM2u6jp//928lM20v0KcDGI6hld/JmlnpOIIxEo50fcK+bbfDigKL5wPzG+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:30:35.928908Z"},"content_sha256":"36ef98a5d078517fe56b07ac069f43b2033ba17876e275b454d8e23b406be18b","schema_version":"1.0","event_id":"sha256:36ef98a5d078517fe56b07ac069f43b2033ba17876e275b454d8e23b406be18b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GHLSUVJ56FRR3NAZ2W4MZLNXX7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ajian Liu, Hao Tan, Jun Wan, Senyuan Shi, Sergio Escalera, Shuhan Feng, Zichang Tan","submitted_at":"2026-05-26T01:20:18Z","abstract_excerpt":"The rapid evolution of generative models has precipitated a proliferation of fabricated content, posing significant challenges to existing Synthetic Image Detection (SID) methods. Capitalizing on advancements in vision-language models (e.g., CLIP), recent attempts have leveraged learnable textual prompts to identify synthetic images. However, they still leverage static prompt as a fixed boundary for real and fake images, failing to adapt to the varying types of forgery that emerge during inference. To overcome this issue, we propose **HydraPrompt**, an asymmetric prompting framework that dynam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26421","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/2605.26421/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":"2026-05-27T01:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGHRKLH7hy7Pz0yEMfvXOLaiiFCbjFqyKrCsYQ9npDT4le/A+4SlMyuwZjJy+FtSEwJKidBsz3+Yj0sb5eYRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T06:30:35.929284Z"},"content_sha256":"54f1e856626eee96a42df33ec4d9f0add5fc7794e82a033be5262fe98057a4d8","schema_version":"1.0","event_id":"sha256:54f1e856626eee96a42df33ec4d9f0add5fc7794e82a033be5262fe98057a4d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHLSUVJ56FRR3NAZ2W4MZLNXX7/bundle.json","state_url":"https://pith.science/pith/GHLSUVJ56FRR3NAZ2W4MZLNXX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHLSUVJ56FRR3NAZ2W4MZLNXX7/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":"2026-06-04T06:30:35Z","links":{"resolver":"https://pith.science/pith/GHLSUVJ56FRR3NAZ2W4MZLNXX7","bundle":"https://pith.science/pith/GHLSUVJ56FRR3NAZ2W4MZLNXX7/bundle.json","state":"https://pith.science/pith/GHLSUVJ56FRR3NAZ2W4MZLNXX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHLSUVJ56FRR3NAZ2W4MZLNXX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHLSUVJ56FRR3NAZ2W4MZLNXX7","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":"4827bbd057e7ff13dc10020fbb0a0b811f0eef854cb28229af98314930b7579c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T01:20:18Z","title_canon_sha256":"dfc2241e4901a9f9dc4336b5cf07d4a46f55935bcf90108061019eaea72966d3"},"schema_version":"1.0","source":{"id":"2605.26421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26421","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26421v1","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26421","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"GHLSUVJ56FRR","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"GHLSUVJ56FRR3NAZ","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"GHLSUVJ5","created_at":"2026-05-27T01:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:54f1e856626eee96a42df33ec4d9f0add5fc7794e82a033be5262fe98057a4d8","target":"graph","created_at":"2026-05-27T01:05:16Z","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/2605.26421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid evolution of generative models has precipitated a proliferation of fabricated content, posing significant challenges to existing Synthetic Image Detection (SID) methods. Capitalizing on advancements in vision-language models (e.g., CLIP), recent attempts have leveraged learnable textual prompts to identify synthetic images. However, they still leverage static prompt as a fixed boundary for real and fake images, failing to adapt to the varying types of forgery that emerge during inference. To overcome this issue, we propose **HydraPrompt**, an asymmetric prompting framework that dynam","authors_text":"Ajian Liu, Hao Tan, Jun Wan, Senyuan Shi, Sergio Escalera, Shuhan Feng, Zichang Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T01:20:18Z","title":"HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26421","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":"sha256:36ef98a5d078517fe56b07ac069f43b2033ba17876e275b454d8e23b406be18b","target":"record","created_at":"2026-05-27T01:05:16Z","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":"4827bbd057e7ff13dc10020fbb0a0b811f0eef854cb28229af98314930b7579c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T01:20:18Z","title_canon_sha256":"dfc2241e4901a9f9dc4336b5cf07d4a46f55935bcf90108061019eaea72966d3"},"schema_version":"1.0","source":{"id":"2605.26421","kind":"arxiv","version":1}},"canonical_sha256":"31d72a553df1631db419d5b8ccadb7bfc15da7bf772ae9d432d77d1b722b36e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31d72a553df1631db419d5b8ccadb7bfc15da7bf772ae9d432d77d1b722b36e0","first_computed_at":"2026-05-27T01:05:16.969883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:16.969883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pvFicOSaWIyaxeosnaLcAy1cHhws40UaXQcJ3JmYZTa5VZf8UtsZzqCANkKhKY283oz+QtarUi3MfmUKT8nHDQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:16.970689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36ef98a5d078517fe56b07ac069f43b2033ba17876e275b454d8e23b406be18b","sha256:54f1e856626eee96a42df33ec4d9f0add5fc7794e82a033be5262fe98057a4d8"],"state_sha256":"610870fc5fe12ba15ffc7659230acc207e41ecb45d7729d61296746b9520387d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cXYajCSZOWSFGNR55eb4/BnQNJn0QHTbKpxS7289Zx2jbX764N6PSeVx8A8RyCC6g+jD4snBTKeVBEWi9Uy6Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T06:30:35.931360Z","bundle_sha256":"e734cb03d713764ee89147f493c6abda919f69236398045249140503682c3fd4"}}