{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TAWN2OBKV62PELB73LL43E2BRI","short_pith_number":"pith:TAWN2OBK","schema_version":"1.0","canonical_sha256":"982cdd382aafb4f22c3fdad7cd93418a1b5610f8000e7d32cc833796ec448b94","source":{"kind":"arxiv","id":"2607.23346","version":1},"attestation_state":"computed","paper":{"title":"SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Dewan, Arjun Yogeswaran, Benjamin Fedoruk","submitted_at":"2026-07-25T19:53:58Z","abstract_excerpt":"Modern deep neural networks are potent catalysts for scientific and industrial impact, yet excessive parameter counts impede deployment in low-compute settings such as hospital equipment and energy infrastructure. Predominant knowledge distillation (KD) methods favor replication: smaller students mimic teacher output logits, yet empirically yield low task performance, hamper convergence, and act merely as regularization rather than substantive knowledge transfer. We propose Saddle Point Recruitment for Knowledge Distillation (SPRKD), reframing distillation from replication to employing teacher"},"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":"2607.23346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-25T19:53:58Z","cross_cats_sorted":[],"title_canon_sha256":"7cdc44f43aa18b352171a633365f0c4e8389d9da6d2605c1b072a6c512a6622a","abstract_canon_sha256":"9e153682c3e653cafca3e992bc154eafb62f83715291aeb6faad478aadd203ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:48.626403Z","signature_b64":"VCaOfpCJQC0N3qV0y7bd9LeLIBTu5q8uQJ5vxSsjEkmZYyXBqDukEy4Y5Acwj3eqPrBEaoFuzE/N44ZZM9vtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"982cdd382aafb4f22c3fdad7cd93418a1b5610f8000e7d32cc833796ec448b94","last_reissued_at":"2026-07-28T01:22:48.625581Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:48.625581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Dewan, Arjun Yogeswaran, Benjamin Fedoruk","submitted_at":"2026-07-25T19:53:58Z","abstract_excerpt":"Modern deep neural networks are potent catalysts for scientific and industrial impact, yet excessive parameter counts impede deployment in low-compute settings such as hospital equipment and energy infrastructure. Predominant knowledge distillation (KD) methods favor replication: smaller students mimic teacher output logits, yet empirically yield low task performance, hamper convergence, and act merely as regularization rather than substantive knowledge transfer. We propose Saddle Point Recruitment for Knowledge Distillation (SPRKD), reframing distillation from replication to employing teacher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23346","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/2607.23346/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":"2607.23346","created_at":"2026-07-28T01:22:48.626007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23346v1","created_at":"2026-07-28T01:22:48.626007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23346","created_at":"2026-07-28T01:22:48.626007+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAWN2OBKV62P","created_at":"2026-07-28T01:22:48.626007+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAWN2OBKV62PELB7","created_at":"2026-07-28T01:22:48.626007+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAWN2OBK","created_at":"2026-07-28T01:22:48.626007+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/TAWN2OBKV62PELB73LL43E2BRI","json":"https://pith.science/pith/TAWN2OBKV62PELB73LL43E2BRI.json","graph_json":"https://pith.science/api/pith-number/TAWN2OBKV62PELB73LL43E2BRI/graph.json","events_json":"https://pith.science/api/pith-number/TAWN2OBKV62PELB73LL43E2BRI/events.json","paper":"https://pith.science/paper/TAWN2OBK"},"agent_actions":{"view_html":"https://pith.science/pith/TAWN2OBKV62PELB73LL43E2BRI","download_json":"https://pith.science/pith/TAWN2OBKV62PELB73LL43E2BRI.json","view_paper":"https://pith.science/paper/TAWN2OBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23346&json=true","fetch_graph":"https://pith.science/api/pith-number/TAWN2OBKV62PELB73LL43E2BRI/graph.json","fetch_events":"https://pith.science/api/pith-number/TAWN2OBKV62PELB73LL43E2BRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAWN2OBKV62PELB73LL43E2BRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAWN2OBKV62PELB73LL43E2BRI/action/storage_attestation","attest_author":"https://pith.science/pith/TAWN2OBKV62PELB73LL43E2BRI/action/author_attestation","sign_citation":"https://pith.science/pith/TAWN2OBKV62PELB73LL43E2BRI/action/citation_signature","submit_replication":"https://pith.science/pith/TAWN2OBKV62PELB73LL43E2BRI/action/replication_record"}},"created_at":"2026-07-28T01:22:48.626007+00:00","updated_at":"2026-07-28T01:22:48.626007+00:00"}