{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AE46AS25523M3ALHWDQ3QSFXYO","short_pith_number":"pith:AE46AS25","schema_version":"1.0","canonical_sha256":"0139e04b5deeb6cd8167b0e1b848b7c3bc38c234b7be9bac55867d27ab171d7c","source":{"kind":"arxiv","id":"2505.06270","version":1},"attestation_state":"computed","paper":{"title":"Importance Analysis for Dynamic Control of Balancing Parameter in a Simple Knowledge Distillation Setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kanghyun Jo, Kwanho Kim, Minseung Kim, Seongmin Kim","submitted_at":"2025-05-06T04:04:30Z","abstract_excerpt":"Although deep learning models owe their remarkable success to deep and complex architectures, this very complexity typically comes at the expense of real-time performance. To address this issue, a variety of model compression techniques have been proposed, among which knowledge distillation (KD) stands out for its strong empirical performance. The KD contains two concurrent processes: (i) matching the outputs of a large, pre-trained teacher network and a lightweight student network, and (ii) training the student to solve its designated downstream task. The associated loss functions are termed "},"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":"2505.06270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T04:04:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d336196725117998ef6022972ba07663b873491ac914cf0f8fce4783d9a134e2","abstract_canon_sha256":"67e7a5ef9f970f4297cd8c574c41c59c9bb02eccc385d21a1dcdaa2280ae01b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:06.357453Z","signature_b64":"LC0Cu1ZYeErlgeqp9fF2ijuwe1yl0uJ8qZN5DmZvsc3/OwKK667BECECXnVMzzfDni3eYZQaE2v+F5xglsSlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0139e04b5deeb6cd8167b0e1b848b7c3bc38c234b7be9bac55867d27ab171d7c","last_reissued_at":"2026-07-05T11:01:06.356973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:06.356973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Importance Analysis for Dynamic Control of Balancing Parameter in a Simple Knowledge Distillation Setting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kanghyun Jo, Kwanho Kim, Minseung Kim, Seongmin Kim","submitted_at":"2025-05-06T04:04:30Z","abstract_excerpt":"Although deep learning models owe their remarkable success to deep and complex architectures, this very complexity typically comes at the expense of real-time performance. To address this issue, a variety of model compression techniques have been proposed, among which knowledge distillation (KD) stands out for its strong empirical performance. The KD contains two concurrent processes: (i) matching the outputs of a large, pre-trained teacher network and a lightweight student network, and (ii) training the student to solve its designated downstream task. The associated loss functions are termed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06270","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/2505.06270/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":"2505.06270","created_at":"2026-07-05T11:01:06.357031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06270v1","created_at":"2026-07-05T11:01:06.357031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06270","created_at":"2026-07-05T11:01:06.357031+00:00"},{"alias_kind":"pith_short_12","alias_value":"AE46AS25523M","created_at":"2026-07-05T11:01:06.357031+00:00"},{"alias_kind":"pith_short_16","alias_value":"AE46AS25523M3ALH","created_at":"2026-07-05T11:01:06.357031+00:00"},{"alias_kind":"pith_short_8","alias_value":"AE46AS25","created_at":"2026-07-05T11:01:06.357031+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/AE46AS25523M3ALHWDQ3QSFXYO","json":"https://pith.science/pith/AE46AS25523M3ALHWDQ3QSFXYO.json","graph_json":"https://pith.science/api/pith-number/AE46AS25523M3ALHWDQ3QSFXYO/graph.json","events_json":"https://pith.science/api/pith-number/AE46AS25523M3ALHWDQ3QSFXYO/events.json","paper":"https://pith.science/paper/AE46AS25"},"agent_actions":{"view_html":"https://pith.science/pith/AE46AS25523M3ALHWDQ3QSFXYO","download_json":"https://pith.science/pith/AE46AS25523M3ALHWDQ3QSFXYO.json","view_paper":"https://pith.science/paper/AE46AS25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06270&json=true","fetch_graph":"https://pith.science/api/pith-number/AE46AS25523M3ALHWDQ3QSFXYO/graph.json","fetch_events":"https://pith.science/api/pith-number/AE46AS25523M3ALHWDQ3QSFXYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AE46AS25523M3ALHWDQ3QSFXYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AE46AS25523M3ALHWDQ3QSFXYO/action/storage_attestation","attest_author":"https://pith.science/pith/AE46AS25523M3ALHWDQ3QSFXYO/action/author_attestation","sign_citation":"https://pith.science/pith/AE46AS25523M3ALHWDQ3QSFXYO/action/citation_signature","submit_replication":"https://pith.science/pith/AE46AS25523M3ALHWDQ3QSFXYO/action/replication_record"}},"created_at":"2026-07-05T11:01:06.357031+00:00","updated_at":"2026-07-05T11:01:06.357031+00:00"}