{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2MPWK4YITSHSOQPH4VQMDKPM5P","short_pith_number":"pith:2MPWK4YI","schema_version":"1.0","canonical_sha256":"d31f6573089c8f2741e7e560c1a9ecebca035bcc75f0728e37a1a85b722895a8","source":{"kind":"arxiv","id":"2407.03463","version":1},"attestation_state":"computed","paper":{"title":"Precision at Scale: Domain-Specific Datasets On-Demand","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bhalaji Nagarajan, Ignacio Saras\\'ua, Imanol G Estepa, Jes\\'us M Rodr\\'iguez-de-Vera, Petia Radeva","submitted_at":"2024-07-03T19:17:42Z","abstract_excerpt":"In the realm of self-supervised learning (SSL), conventional wisdom has gravitated towards the utility of massive, general domain datasets for pretraining robust backbones. In this paper, we challenge this idea by exploring if it is possible to bridge the scale between general-domain datasets and (traditionally smaller) domain-specific datasets to reduce the current performance gap. More specifically, we propose Precision at Scale (PaS), a novel method for the autonomous creation of domain-specific datasets on-demand. The modularity of the PaS pipeline enables leveraging state-of-the-art found"},"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":"2407.03463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T19:17:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d873377234d13e6651b68746e892831ebad6c3471cbcda5c67d4348ab2ee84f","abstract_canon_sha256":"d7bc06fe6876fd7d817cfa0a5aef63a805c083c2a1461e95c39a6f2a42ee1d20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:55.347795Z","signature_b64":"Ye31aw3gDmN9tMz9keKzuFFa5JCF4Tyssn30Sw7zSqi3uKxfCBUZ0si638eESXHk+WfsHkxn5ma7TO7ipk5gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d31f6573089c8f2741e7e560c1a9ecebca035bcc75f0728e37a1a85b722895a8","last_reissued_at":"2026-07-05T08:39:55.347379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:55.347379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precision at Scale: Domain-Specific Datasets On-Demand","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bhalaji Nagarajan, Ignacio Saras\\'ua, Imanol G Estepa, Jes\\'us M Rodr\\'iguez-de-Vera, Petia Radeva","submitted_at":"2024-07-03T19:17:42Z","abstract_excerpt":"In the realm of self-supervised learning (SSL), conventional wisdom has gravitated towards the utility of massive, general domain datasets for pretraining robust backbones. In this paper, we challenge this idea by exploring if it is possible to bridge the scale between general-domain datasets and (traditionally smaller) domain-specific datasets to reduce the current performance gap. More specifically, we propose Precision at Scale (PaS), a novel method for the autonomous creation of domain-specific datasets on-demand. The modularity of the PaS pipeline enables leveraging state-of-the-art found"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03463","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/2407.03463/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":"2407.03463","created_at":"2026-07-05T08:39:55.347437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03463v1","created_at":"2026-07-05T08:39:55.347437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03463","created_at":"2026-07-05T08:39:55.347437+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MPWK4YITSHS","created_at":"2026-07-05T08:39:55.347437+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MPWK4YITSHSOQPH","created_at":"2026-07-05T08:39:55.347437+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MPWK4YI","created_at":"2026-07-05T08:39:55.347437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.15714","citing_title":"TrustDataFilter:Leveraging Trusted Knowledge Base Data for More Effective Filtering of Unknown Information","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P","json":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P.json","graph_json":"https://pith.science/api/pith-number/2MPWK4YITSHSOQPH4VQMDKPM5P/graph.json","events_json":"https://pith.science/api/pith-number/2MPWK4YITSHSOQPH4VQMDKPM5P/events.json","paper":"https://pith.science/paper/2MPWK4YI"},"agent_actions":{"view_html":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P","download_json":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P.json","view_paper":"https://pith.science/paper/2MPWK4YI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03463&json=true","fetch_graph":"https://pith.science/api/pith-number/2MPWK4YITSHSOQPH4VQMDKPM5P/graph.json","fetch_events":"https://pith.science/api/pith-number/2MPWK4YITSHSOQPH4VQMDKPM5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P/action/storage_attestation","attest_author":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P/action/author_attestation","sign_citation":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P/action/citation_signature","submit_replication":"https://pith.science/pith/2MPWK4YITSHSOQPH4VQMDKPM5P/action/replication_record"}},"created_at":"2026-07-05T08:39:55.347437+00:00","updated_at":"2026-07-05T08:39:55.347437+00:00"}