{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZMD5LVANKAFQU4XMVSCQSR37GV","short_pith_number":"pith:ZMD5LVAN","canonical_record":{"source":{"id":"2504.04510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T14:54:10Z","cross_cats_sorted":[],"title_canon_sha256":"4b32e8d879c5f7b29f08f28c544074850f8600d2ee5c6bffd4c72aa188bfd45a","abstract_canon_sha256":"2fac23be41eec45dbedd3d95b41becc90804ed7e31cc03d2fb12a80c5cd18ec7"},"schema_version":"1.0"},"canonical_sha256":"cb07d5d40d500b0a72ecac8509477f3565940d5799982b91c8e069dc8d229fc6","source":{"kind":"arxiv","id":"2504.04510","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04510","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04510v1","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04510","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZMD5LVANKAFQ","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZMD5LVANKAFQU4XM","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZMD5LVAN","created_at":"2026-07-05T10:45:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZMD5LVANKAFQU4XMVSCQSR37GV","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04510","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T14:54:10Z","cross_cats_sorted":[],"title_canon_sha256":"4b32e8d879c5f7b29f08f28c544074850f8600d2ee5c6bffd4c72aa188bfd45a","abstract_canon_sha256":"2fac23be41eec45dbedd3d95b41becc90804ed7e31cc03d2fb12a80c5cd18ec7"},"schema_version":"1.0"},"canonical_sha256":"cb07d5d40d500b0a72ecac8509477f3565940d5799982b91c8e069dc8d229fc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:25.244669Z","signature_b64":"MgRN8c68Qik2Gn1uI97gfnhHsWRwCXFKyvQ/DxLzH8PnN2uJ7+I0M3bOdBQOROZU/VvtEAmjwE6vznvYSWMsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb07d5d40d500b0a72ecac8509477f3565940d5799982b91c8e069dc8d229fc6","last_reissued_at":"2026-07-05T10:45:25.244044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:25.244044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04510","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":"2026-07-05T10:45:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qPZp7mU9Hd/2DGjSpuUlf8t9VoCkzq0mdi49X/08u6Y9MlHkZ/+SIyXm7KWFm2vxaiksXl2BQC5pS1XioEEMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T13:10:07.558481Z"},"content_sha256":"69a44339793dcbb7afcfc5873a3b30d01a8076cf09bc4d89ce944d7e926f4bfb","schema_version":"1.0","event_id":"sha256:69a44339793dcbb7afcfc5873a3b30d01a8076cf09bc4d89ce944d7e926f4bfb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZMD5LVANKAFQU4XMVSCQSR37GV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanqian Wu, Linxin Song, Masayuki Goto, Ryotaro Shimizu, Shijian Wang","submitted_at":"2025-04-06T14:54:10Z","abstract_excerpt":"Zero-shot domain-specific image classification is challenging in classifying real images without ground-truth in-domain training examples. Recent research involved knowledge from texts with a text-to-image model to generate in-domain training images in zero-shot scenarios. However, existing methods heavily rely on simple prompt strategies, limiting the diversity of synthetic training images, thus leading to inferior performance compared to real images. In this paper, we propose AttrSyn, which leverages large language models to generate attributed prompts. These prompts allow for the generation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04510","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/2504.04510/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":"2026-07-05T10:45:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zLWMGfVwpOv/NgkuxJoCYRdH34Kjkj6BiOOJSQ/PoN9mX95BfrZ11TZJcEOsB0gjziQBNurEpSUFgRha5fxpCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T13:10:07.558863Z"},"content_sha256":"9e1dc784697b2a92fa3f571dd36b449095c2234d7f35484444535d8223e6bf13","schema_version":"1.0","event_id":"sha256:9e1dc784697b2a92fa3f571dd36b449095c2234d7f35484444535d8223e6bf13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZMD5LVANKAFQU4XMVSCQSR37GV/bundle.json","state_url":"https://pith.science/pith/ZMD5LVANKAFQU4XMVSCQSR37GV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZMD5LVANKAFQU4XMVSCQSR37GV/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":"2026-07-16T13:10:07Z","links":{"resolver":"https://pith.science/pith/ZMD5LVANKAFQU4XMVSCQSR37GV","bundle":"https://pith.science/pith/ZMD5LVANKAFQU4XMVSCQSR37GV/bundle.json","state":"https://pith.science/pith/ZMD5LVANKAFQU4XMVSCQSR37GV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZMD5LVANKAFQU4XMVSCQSR37GV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZMD5LVANKAFQU4XMVSCQSR37GV","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":"2fac23be41eec45dbedd3d95b41becc90804ed7e31cc03d2fb12a80c5cd18ec7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T14:54:10Z","title_canon_sha256":"4b32e8d879c5f7b29f08f28c544074850f8600d2ee5c6bffd4c72aa188bfd45a"},"schema_version":"1.0","source":{"id":"2504.04510","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04510","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04510v1","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04510","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZMD5LVANKAFQ","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZMD5LVANKAFQU4XM","created_at":"2026-07-05T10:45:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZMD5LVAN","created_at":"2026-07-05T10:45:25Z"}],"graph_snapshots":[{"event_id":"sha256:9e1dc784697b2a92fa3f571dd36b449095c2234d7f35484444535d8223e6bf13","target":"graph","created_at":"2026-07-05T10:45:25Z","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/2504.04510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot domain-specific image classification is challenging in classifying real images without ground-truth in-domain training examples. Recent research involved knowledge from texts with a text-to-image model to generate in-domain training images in zero-shot scenarios. However, existing methods heavily rely on simple prompt strategies, limiting the diversity of synthetic training images, thus leading to inferior performance compared to real images. In this paper, we propose AttrSyn, which leverages large language models to generate attributed prompts. These prompts allow for the generation","authors_text":"Hanqian Wu, Linxin Song, Masayuki Goto, Ryotaro Shimizu, Shijian Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T14:54:10Z","title":"Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04510","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":"sha256:69a44339793dcbb7afcfc5873a3b30d01a8076cf09bc4d89ce944d7e926f4bfb","target":"record","created_at":"2026-07-05T10:45:25Z","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":"2fac23be41eec45dbedd3d95b41becc90804ed7e31cc03d2fb12a80c5cd18ec7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-06T14:54:10Z","title_canon_sha256":"4b32e8d879c5f7b29f08f28c544074850f8600d2ee5c6bffd4c72aa188bfd45a"},"schema_version":"1.0","source":{"id":"2504.04510","kind":"arxiv","version":1}},"canonical_sha256":"cb07d5d40d500b0a72ecac8509477f3565940d5799982b91c8e069dc8d229fc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb07d5d40d500b0a72ecac8509477f3565940d5799982b91c8e069dc8d229fc6","first_computed_at":"2026-07-05T10:45:25.244044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:25.244044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MgRN8c68Qik2Gn1uI97gfnhHsWRwCXFKyvQ/DxLzH8PnN2uJ7+I0M3bOdBQOROZU/VvtEAmjwE6vznvYSWMsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:25.244669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04510","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69a44339793dcbb7afcfc5873a3b30d01a8076cf09bc4d89ce944d7e926f4bfb","sha256:9e1dc784697b2a92fa3f571dd36b449095c2234d7f35484444535d8223e6bf13"],"state_sha256":"705545a2150375a94e0f1107fe48e526875b0a290fe0590d30e666f0da4e9a20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7L3MiFSBN/LE/MGI7HWSsspsZjIAvcGsF7PvXFIsme46Mj7iYtibZUUfj8y76Bv+1Qu9ORTw92iazdo167O2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T13:10:07.561484Z","bundle_sha256":"e13ecf51f4a4bf5718a211fa9b9a33b8c26ebfe9cec48dd5a19763bb6dba5f4f"}}