{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YDUWQSOG43YQSU23KOO5BZPLIV","short_pith_number":"pith:YDUWQSOG","schema_version":"1.0","canonical_sha256":"c0e96849c6e6f109535b539dd0e5eb4543281772553bec879e5c1228a6a746b7","source":{"kind":"arxiv","id":"2402.03119","version":2},"attestation_state":"computed","paper":{"title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amin Parchami-Araghi, Bernt Schiele, Moritz B\\\"ohle, Sukrut Rao","submitted_at":"2024-02-05T15:47:54Z","abstract_excerpt":"Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar accuracies as the teachers, it has also been shown that they nonetheless often do not learn the same function. It is, however, often highly desirable that the student's and teacher's functions share similar properties such as basing the prediction on the same input features, as this ensures that students learn the 'right features' from the teachers. In this work, we explore whether this can be achieved by not only opti"},"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":"2402.03119","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-05T15:47:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b853486e027ec7e1a80b58041dbd1a9008ceaba1e0735d205adf771fe6014bd5","abstract_canon_sha256":"61e62aca33045a88de8bc3113899e2c3c00aa2297996b309e0714d85b4db405d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:21.249100Z","signature_b64":"8Ec/vbLsqkW+Gi9Swu1BP4/1CXO8tUeQllmWEks/ZsSnDgu/mLJaiR4UwYdstF6UiZlhtTIl6K23+0EgTSZGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0e96849c6e6f109535b539dd0e5eb4543281772553bec879e5c1228a6a746b7","last_reissued_at":"2026-07-05T08:46:21.248638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:21.248638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amin Parchami-Araghi, Bernt Schiele, Moritz B\\\"ohle, Sukrut Rao","submitted_at":"2024-02-05T15:47:54Z","abstract_excerpt":"Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar accuracies as the teachers, it has also been shown that they nonetheless often do not learn the same function. It is, however, often highly desirable that the student's and teacher's functions share similar properties such as basing the prediction on the same input features, as this ensures that students learn the 'right features' from the teachers. In this work, we explore whether this can be achieved by not only opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03119","kind":"arxiv","version":2},"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/2402.03119/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":"2402.03119","created_at":"2026-07-05T08:46:21.248692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03119v2","created_at":"2026-07-05T08:46:21.248692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03119","created_at":"2026-07-05T08:46:21.248692+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDUWQSOG43YQ","created_at":"2026-07-05T08:46:21.248692+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDUWQSOG43YQSU23","created_at":"2026-07-05T08:46:21.248692+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDUWQSOG","created_at":"2026-07-05T08:46:21.248692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02399","citing_title":"OMENN: One Matrix to Explain Neural Networks","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV","json":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV.json","graph_json":"https://pith.science/api/pith-number/YDUWQSOG43YQSU23KOO5BZPLIV/graph.json","events_json":"https://pith.science/api/pith-number/YDUWQSOG43YQSU23KOO5BZPLIV/events.json","paper":"https://pith.science/paper/YDUWQSOG"},"agent_actions":{"view_html":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV","download_json":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV.json","view_paper":"https://pith.science/paper/YDUWQSOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03119&json=true","fetch_graph":"https://pith.science/api/pith-number/YDUWQSOG43YQSU23KOO5BZPLIV/graph.json","fetch_events":"https://pith.science/api/pith-number/YDUWQSOG43YQSU23KOO5BZPLIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV/action/storage_attestation","attest_author":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV/action/author_attestation","sign_citation":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV/action/citation_signature","submit_replication":"https://pith.science/pith/YDUWQSOG43YQSU23KOO5BZPLIV/action/replication_record"}},"created_at":"2026-07-05T08:46:21.248692+00:00","updated_at":"2026-07-05T08:46:21.248692+00:00"}