{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G7ZLI73ZDFZCCTA6XCHMAMWSWG","short_pith_number":"pith:G7ZLI73Z","schema_version":"1.0","canonical_sha256":"37f2b47f791972214c1eb88ec032d2b18519676d7ed9364ca0fc593c5f0c7fbe","source":{"kind":"arxiv","id":"2607.02637","version":1},"attestation_state":"computed","paper":{"title":"Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaoda Song, Disheng Liu, Tuo Liang, Yu Yin","submitted_at":"2026-07-02T15:34:46Z","abstract_excerpt":"Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models. Existing approaches to exploiting this potential typically involve 1) training or fine-tuning generators, or 2) using lightweight post-hoc adaptation like prompt engineering or inference-time guidance, making them generator-specific and expertise-intensive. We study a complementary question: given a fixed pool of generated images, can downstream utility be improved purely by selecting an informative subset? The answer is yes. We show that effective selection must"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.02637","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T15:34:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c966d9a60cbe48ee89e29f319dbca09e9bdf290c3951d4ad2d3ed242d72f1b38","abstract_canon_sha256":"c2537446f6c06d266e5d258f8cc962b6d223fc3b57c687709936c709f322f994"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:04.752224Z","signature_b64":"NhxwULfB1esfsR4vvrG0+VKXAlokXdVOYuoXgrSJvYxLlPzo8tC9QPP7n4E/Eo15A8jSetr2DUnw5l1uFUxgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37f2b47f791972214c1eb88ec032d2b18519676d7ed9364ca0fc593c5f0c7fbe","last_reissued_at":"2026-07-07T00:16:04.751543Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:04.751543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chaoda Song, Disheng Liu, Tuo Liang, Yu Yin","submitted_at":"2026-07-02T15:34:46Z","abstract_excerpt":"Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models. Existing approaches to exploiting this potential typically involve 1) training or fine-tuning generators, or 2) using lightweight post-hoc adaptation like prompt engineering or inference-time guidance, making them generator-specific and expertise-intensive. We study a complementary question: given a fixed pool of generated images, can downstream utility be improved purely by selecting an informative subset? The answer is yes. We show that effective selection must"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02637","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/2607.02637/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.02637","created_at":"2026-07-07T00:16:04.751655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02637v1","created_at":"2026-07-07T00:16:04.751655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02637","created_at":"2026-07-07T00:16:04.751655+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7ZLI73ZDFZC","created_at":"2026-07-07T00:16:04.751655+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7ZLI73ZDFZCCTA6","created_at":"2026-07-07T00:16:04.751655+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7ZLI73Z","created_at":"2026-07-07T00:16:04.751655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG","json":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG.json","graph_json":"https://pith.science/api/pith-number/G7ZLI73ZDFZCCTA6XCHMAMWSWG/graph.json","events_json":"https://pith.science/api/pith-number/G7ZLI73ZDFZCCTA6XCHMAMWSWG/events.json","paper":"https://pith.science/paper/G7ZLI73Z"},"agent_actions":{"view_html":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG","download_json":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG.json","view_paper":"https://pith.science/paper/G7ZLI73Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02637&json=true","fetch_graph":"https://pith.science/api/pith-number/G7ZLI73ZDFZCCTA6XCHMAMWSWG/graph.json","fetch_events":"https://pith.science/api/pith-number/G7ZLI73ZDFZCCTA6XCHMAMWSWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG/action/storage_attestation","attest_author":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG/action/author_attestation","sign_citation":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG/action/citation_signature","submit_replication":"https://pith.science/pith/G7ZLI73ZDFZCCTA6XCHMAMWSWG/action/replication_record"}},"created_at":"2026-07-07T00:16:04.751655+00:00","updated_at":"2026-07-07T00:16:04.751655+00:00"}