{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7FMNFWF3ZYA5OKSGPKRBIUKJOM","short_pith_number":"pith:7FMNFWF3","schema_version":"1.0","canonical_sha256":"f958d2d8bbce01d72a467aa21451497312d79ad0969cfa8174aafcb98951991d","source":{"kind":"arxiv","id":"2306.07200","version":1},"attestation_state":"computed","paper":{"title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaesik Park, Joonghyuk Shin, Minguk Kang","submitted_at":"2023-06-12T16:01:20Z","abstract_excerpt":"Modern text-to-image synthesis models have achieved an exceptional level of photorealism, generating high-quality images from arbitrary text descriptions. In light of the impressive synthesis ability, several studies have exhibited promising results in exploiting generated data for image recognition. However, directly supplementing data-hungry situations in the real-world (e.g. few-shot or long-tailed scenarios) with existing approaches result in marginal performance gains, as they suffer to thoroughly reflect the distribution of the real data. Through extensive experiments, this paper propose"},"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":"2306.07200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T16:01:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a710dbe5647d3b3baf1a9b21b3bcfde1660164448aca15449f729346163b7468","abstract_canon_sha256":"268ac325cf502cc9d5a782ee7196876c6512cd260cc00cbd472eee82ae61159b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:48.819091Z","signature_b64":"byRdCtSRft/rp4p8eWqCPkQZlkDHV96evERjaFzE01vM4iqHrxs3mugN6vgp6vMgt7k+BLVv3neWXHF6/hW6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f958d2d8bbce01d72a467aa21451497312d79ad0969cfa8174aafcb98951991d","last_reissued_at":"2026-07-05T06:19:48.818624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:48.818624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaesik Park, Joonghyuk Shin, Minguk Kang","submitted_at":"2023-06-12T16:01:20Z","abstract_excerpt":"Modern text-to-image synthesis models have achieved an exceptional level of photorealism, generating high-quality images from arbitrary text descriptions. In light of the impressive synthesis ability, several studies have exhibited promising results in exploiting generated data for image recognition. However, directly supplementing data-hungry situations in the real-world (e.g. few-shot or long-tailed scenarios) with existing approaches result in marginal performance gains, as they suffer to thoroughly reflect the distribution of the real data. Through extensive experiments, this paper propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07200","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/2306.07200/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":"2306.07200","created_at":"2026-07-05T06:19:48.818681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07200v1","created_at":"2026-07-05T06:19:48.818681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07200","created_at":"2026-07-05T06:19:48.818681+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FMNFWF3ZYA5","created_at":"2026-07-05T06:19:48.818681+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FMNFWF3ZYA5OKSG","created_at":"2026-07-05T06:19:48.818681+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FMNFWF3","created_at":"2026-07-05T06:19:48.818681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.00918","citing_title":"Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM","json":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM.json","graph_json":"https://pith.science/api/pith-number/7FMNFWF3ZYA5OKSGPKRBIUKJOM/graph.json","events_json":"https://pith.science/api/pith-number/7FMNFWF3ZYA5OKSGPKRBIUKJOM/events.json","paper":"https://pith.science/paper/7FMNFWF3"},"agent_actions":{"view_html":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM","download_json":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM.json","view_paper":"https://pith.science/paper/7FMNFWF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07200&json=true","fetch_graph":"https://pith.science/api/pith-number/7FMNFWF3ZYA5OKSGPKRBIUKJOM/graph.json","fetch_events":"https://pith.science/api/pith-number/7FMNFWF3ZYA5OKSGPKRBIUKJOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM/action/storage_attestation","attest_author":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM/action/author_attestation","sign_citation":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM/action/citation_signature","submit_replication":"https://pith.science/pith/7FMNFWF3ZYA5OKSGPKRBIUKJOM/action/replication_record"}},"created_at":"2026-07-05T06:19:48.818681+00:00","updated_at":"2026-07-05T06:19:48.818681+00:00"}