{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AMIHPEZKW4CL3QMF6I3PEVHEBM","short_pith_number":"pith:AMIHPEZK","schema_version":"1.0","canonical_sha256":"031077932ab704bdc185f236f254e40b2731a6f3a89f84a1a3617c7926a17c4a","source":{"kind":"arxiv","id":"2509.00509","version":1},"attestation_state":"computed","paper":{"title":"Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Imad Eddine Marouf, Khalid Oublal, Slim Essid, St\\'ephane Lathuili\\`ere, Subhankar Roy, Vicky Kalogeiton, Yasser Benigmim","submitted_at":"2025-08-30T14:03:09Z","abstract_excerpt":"The rise of Artificial Intelligence as a Service (AIaaS) democratizes access to pre-trained models via Application Programming Interfaces (APIs), but also raises a fundamental question: how can local models be effectively trained using black-box models that do not expose their weights, training data, or logits, a constraint in which current domain adaptation paradigms are impractical ? To address this challenge, we introduce the Black-Box Distillation (B2D) setting, which enables local model adaptation under realistic constraints: (1) the API model is open-vocabulary and trained on large-scale"},"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":"2509.00509","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-30T14:03:09Z","cross_cats_sorted":[],"title_canon_sha256":"683699f4604297c36784a5d87b8f3926d35fd0a7b5d4ea7cc10bbe1d3f769f94","abstract_canon_sha256":"b1278a7a43d9d24d6ef9965eff75479cf94428d7ee623a7b4db8ba0921efbafd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:17.472382Z","signature_b64":"CClBZ82Syo53NupDa1Lqi9CFpOkte39sRoMOuXuemcJzynQc+mxLU1LhacKA7KkPW65sPF1SwuDcL73dH1MBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"031077932ab704bdc185f236f254e40b2731a6f3a89f84a1a3617c7926a17c4a","last_reissued_at":"2026-07-05T12:02:17.471954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:17.471954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Imad Eddine Marouf, Khalid Oublal, Slim Essid, St\\'ephane Lathuili\\`ere, Subhankar Roy, Vicky Kalogeiton, Yasser Benigmim","submitted_at":"2025-08-30T14:03:09Z","abstract_excerpt":"The rise of Artificial Intelligence as a Service (AIaaS) democratizes access to pre-trained models via Application Programming Interfaces (APIs), but also raises a fundamental question: how can local models be effectively trained using black-box models that do not expose their weights, training data, or logits, a constraint in which current domain adaptation paradigms are impractical ? To address this challenge, we introduce the Black-Box Distillation (B2D) setting, which enables local model adaptation under realistic constraints: (1) the API model is open-vocabulary and trained on large-scale"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00509","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/2509.00509/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":"2509.00509","created_at":"2026-07-05T12:02:17.472015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00509v1","created_at":"2026-07-05T12:02:17.472015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00509","created_at":"2026-07-05T12:02:17.472015+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMIHPEZKW4CL","created_at":"2026-07-05T12:02:17.472015+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMIHPEZKW4CL3QMF","created_at":"2026-07-05T12:02:17.472015+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMIHPEZK","created_at":"2026-07-05T12:02:17.472015+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/AMIHPEZKW4CL3QMF6I3PEVHEBM","json":"https://pith.science/pith/AMIHPEZKW4CL3QMF6I3PEVHEBM.json","graph_json":"https://pith.science/api/pith-number/AMIHPEZKW4CL3QMF6I3PEVHEBM/graph.json","events_json":"https://pith.science/api/pith-number/AMIHPEZKW4CL3QMF6I3PEVHEBM/events.json","paper":"https://pith.science/paper/AMIHPEZK"},"agent_actions":{"view_html":"https://pith.science/pith/AMIHPEZKW4CL3QMF6I3PEVHEBM","download_json":"https://pith.science/pith/AMIHPEZKW4CL3QMF6I3PEVHEBM.json","view_paper":"https://pith.science/paper/AMIHPEZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00509&json=true","fetch_graph":"https://pith.science/api/pith-number/AMIHPEZKW4CL3QMF6I3PEVHEBM/graph.json","fetch_events":"https://pith.science/api/pith-number/AMIHPEZKW4CL3QMF6I3PEVHEBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMIHPEZKW4CL3QMF6I3PEVHEBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMIHPEZKW4CL3QMF6I3PEVHEBM/action/storage_attestation","attest_author":"https://pith.science/pith/AMIHPEZKW4CL3QMF6I3PEVHEBM/action/author_attestation","sign_citation":"https://pith.science/pith/AMIHPEZKW4CL3QMF6I3PEVHEBM/action/citation_signature","submit_replication":"https://pith.science/pith/AMIHPEZKW4CL3QMF6I3PEVHEBM/action/replication_record"}},"created_at":"2026-07-05T12:02:17.472015+00:00","updated_at":"2026-07-05T12:02:17.472015+00:00"}