{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5LH52RYNADNEO5SCGINQPXY4GW","short_pith_number":"pith:5LH52RYN","schema_version":"1.0","canonical_sha256":"eacfdd470d00da477642321b07df1c35a7fc48744f3cabbf4ea23c0e34b80cdd","source":{"kind":"arxiv","id":"2505.10551","version":1},"attestation_state":"computed","paper":{"title":"Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jae Myung Kim, Jessica Bader, Yiwen Liu","submitted_at":"2025-05-15T17:57:38Z","abstract_excerpt":"With the development of photorealistic diffusion models, models trained in part or fully on synthetic data achieve progressively better results. However, diffusion models still routinely generate images that would not exist in reality, such as a dog floating above the ground or with unrealistic texture artifacts. We define the concept of feasibility as whether attributes in a synthetic image could realistically exist in the real-world domain; synthetic images containing attributes that violate this criterion are considered infeasible. Intuitively, infeasible images are typically considered out"},"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":"2505.10551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:57:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca89573bd9afdc39c21a2000ecfa8834df5e4de54a70c3a6097b4a877404a661","abstract_canon_sha256":"1578e838906a9fe3e66ab59c4c1831ec18342338bb74ad12016e0db0f90c9db5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:45.533926Z","signature_b64":"VxKRJAARN22wy3mYeTNJObm6pUnaaUi8p8YYIHPf0ZvgUviXZo+K11y+c1So2q3LvsePOvLU3RnHpGSVuYowBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eacfdd470d00da477642321b07df1c35a7fc48744f3cabbf4ea23c0e34b80cdd","last_reissued_at":"2026-07-05T11:03:45.533428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:45.533428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jae Myung Kim, Jessica Bader, Yiwen Liu","submitted_at":"2025-05-15T17:57:38Z","abstract_excerpt":"With the development of photorealistic diffusion models, models trained in part or fully on synthetic data achieve progressively better results. However, diffusion models still routinely generate images that would not exist in reality, such as a dog floating above the ground or with unrealistic texture artifacts. We define the concept of feasibility as whether attributes in a synthetic image could realistically exist in the real-world domain; synthetic images containing attributes that violate this criterion are considered infeasible. Intuitively, infeasible images are typically considered out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10551","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/2505.10551/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":"2505.10551","created_at":"2026-07-05T11:03:45.533489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10551v1","created_at":"2026-07-05T11:03:45.533489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10551","created_at":"2026-07-05T11:03:45.533489+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LH52RYNADNE","created_at":"2026-07-05T11:03:45.533489+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LH52RYNADNEO5SC","created_at":"2026-07-05T11:03:45.533489+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LH52RYN","created_at":"2026-07-05T11:03:45.533489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00571","citing_title":"On the Difficulty of Learning a Meta-network for Training Data Selection","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW","json":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW.json","graph_json":"https://pith.science/api/pith-number/5LH52RYNADNEO5SCGINQPXY4GW/graph.json","events_json":"https://pith.science/api/pith-number/5LH52RYNADNEO5SCGINQPXY4GW/events.json","paper":"https://pith.science/paper/5LH52RYN"},"agent_actions":{"view_html":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW","download_json":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW.json","view_paper":"https://pith.science/paper/5LH52RYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10551&json=true","fetch_graph":"https://pith.science/api/pith-number/5LH52RYNADNEO5SCGINQPXY4GW/graph.json","fetch_events":"https://pith.science/api/pith-number/5LH52RYNADNEO5SCGINQPXY4GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW/action/storage_attestation","attest_author":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW/action/author_attestation","sign_citation":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW/action/citation_signature","submit_replication":"https://pith.science/pith/5LH52RYNADNEO5SCGINQPXY4GW/action/replication_record"}},"created_at":"2026-07-05T11:03:45.533489+00:00","updated_at":"2026-07-05T11:03:45.533489+00:00"}