{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JMRP7AW352R457O3V6S3QKLRMH","short_pith_number":"pith:JMRP7AW3","schema_version":"1.0","canonical_sha256":"4b22ff82dbeea3cefddbafa5b8297161f587a0a51f70ebcc0668572a662ad280","source":{"kind":"arxiv","id":"2204.11526","version":3},"attestation_state":"computed","paper":{"title":"Selective Cross-Task Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Su Lu","submitted_at":"2022-04-25T09:34:37Z","abstract_excerpt":"The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of teachers pre-trained on diverse tasks, we must surmount two obstacles when using knowledge distillation to learn a new task. First, given a fixed computing budget, it is not affordable to try each teacher and train the student repeatedly, making it necessary to seek out the most contributive teacher precisely and efficiently. Second, semantic gaps exist betwee"},"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":"2204.11526","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T09:34:37Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9ced1f0a05d44d4d92a1b753d15d338dbcc9e067b88a83f5a3fecca4ff7d74bd","abstract_canon_sha256":"1c1fa81df239c0a3277ce335e5420e536b01e9ba5b3a7739e89a226c1ce0c22e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:38.956330Z","signature_b64":"qqgmI5TpTFOWGsQSYIlPuADJTqsEXCjXfwz2PAkR+Csi3ZnxNF6fu0rf1cfbroUr7WQlTrAFKAyuPPWeiUiADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b22ff82dbeea3cefddbafa5b8297161f587a0a51f70ebcc0668572a662ad280","last_reissued_at":"2026-07-05T05:01:38.955753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:38.955753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective Cross-Task Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"De-Chuan Zhan, Han-Jia Ye, Su Lu","submitted_at":"2022-04-25T09:34:37Z","abstract_excerpt":"The outpouring of various pre-trained models empowers knowledge distillation by providing abundant teacher resources, but there lacks a developed mechanism to utilize these teachers adequately. With a massive model repository composed of teachers pre-trained on diverse tasks, we must surmount two obstacles when using knowledge distillation to learn a new task. First, given a fixed computing budget, it is not affordable to try each teacher and train the student repeatedly, making it necessary to seek out the most contributive teacher precisely and efficiently. Second, semantic gaps exist betwee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11526","kind":"arxiv","version":3},"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/2204.11526/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":"2204.11526","created_at":"2026-07-05T05:01:38.955834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.11526v3","created_at":"2026-07-05T05:01:38.955834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11526","created_at":"2026-07-05T05:01:38.955834+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMRP7AW352R4","created_at":"2026-07-05T05:01:38.955834+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMRP7AW352R457O3","created_at":"2026-07-05T05:01:38.955834+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMRP7AW3","created_at":"2026-07-05T05:01:38.955834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14528","citing_title":"Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH","json":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH.json","graph_json":"https://pith.science/api/pith-number/JMRP7AW352R457O3V6S3QKLRMH/graph.json","events_json":"https://pith.science/api/pith-number/JMRP7AW352R457O3V6S3QKLRMH/events.json","paper":"https://pith.science/paper/JMRP7AW3"},"agent_actions":{"view_html":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH","download_json":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH.json","view_paper":"https://pith.science/paper/JMRP7AW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.11526&json=true","fetch_graph":"https://pith.science/api/pith-number/JMRP7AW352R457O3V6S3QKLRMH/graph.json","fetch_events":"https://pith.science/api/pith-number/JMRP7AW352R457O3V6S3QKLRMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH/action/storage_attestation","attest_author":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH/action/author_attestation","sign_citation":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH/action/citation_signature","submit_replication":"https://pith.science/pith/JMRP7AW352R457O3V6S3QKLRMH/action/replication_record"}},"created_at":"2026-07-05T05:01:38.955834+00:00","updated_at":"2026-07-05T05:01:38.955834+00:00"}