{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HQRS7RUREXBZXECPSOCLOLUQCO","short_pith_number":"pith:HQRS7RUR","schema_version":"1.0","canonical_sha256":"3c232fc69125c39b904f9384b72e9013b82560da978b8ce2f19b3ca3f8cbda2d","source":{"kind":"arxiv","id":"2302.10093","version":2},"attestation_state":"computed","paper":{"title":"Progressive Ensemble Distillation: Building Ensembles for Efficient Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhishek Shetty, Anish Sevekari, Don Kurian Dennis, Kazuhito Koishida, Virginia Smith","submitted_at":"2023-02-20T16:57:44Z","abstract_excerpt":"We study the problem of progressive ensemble distillation: Given a large, pretrained teacher model $g$, we seek to decompose the model into smaller, low-inference cost student models $f_i$, such that progressively evaluating additional models in this ensemble leads to improved predictions. The resulting ensemble allows for flexibly tuning accuracy vs. inference cost at runtime, which is useful for a number of applications in on-device inference. The method we propose, B-DISTIL , relies on an algorithmic procedure that uses function composition over intermediate activations to construct express"},"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":"2302.10093","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-20T16:57:44Z","cross_cats_sorted":[],"title_canon_sha256":"67bba45c35e886c940b3a1ea9b1a34233df937277e147fb2ebac01ea3e9ef559","abstract_canon_sha256":"9f0fd52c1f02c0f76dfa9fcc2270a875d14f7f271fd3872c1aff229b62ed46e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:05.042209Z","signature_b64":"fvejbJ4JmGkqH0CwBYg+v3EwX8GOsUPzAt5S5bfc4UeT7XpYTdNDqA/x9A80/c6uIBsabbbLsm9EXVESsHv6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c232fc69125c39b904f9384b72e9013b82560da978b8ce2f19b3ca3f8cbda2d","last_reissued_at":"2026-07-05T07:11:05.041643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:05.041643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Ensemble Distillation: Building Ensembles for Efficient Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abhishek Shetty, Anish Sevekari, Don Kurian Dennis, Kazuhito Koishida, Virginia Smith","submitted_at":"2023-02-20T16:57:44Z","abstract_excerpt":"We study the problem of progressive ensemble distillation: Given a large, pretrained teacher model $g$, we seek to decompose the model into smaller, low-inference cost student models $f_i$, such that progressively evaluating additional models in this ensemble leads to improved predictions. The resulting ensemble allows for flexibly tuning accuracy vs. inference cost at runtime, which is useful for a number of applications in on-device inference. The method we propose, B-DISTIL , relies on an algorithmic procedure that uses function composition over intermediate activations to construct express"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10093","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/2302.10093/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":"2302.10093","created_at":"2026-07-05T07:11:05.041705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10093v2","created_at":"2026-07-05T07:11:05.041705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10093","created_at":"2026-07-05T07:11:05.041705+00:00"},{"alias_kind":"pith_short_12","alias_value":"HQRS7RUREXBZ","created_at":"2026-07-05T07:11:05.041705+00:00"},{"alias_kind":"pith_short_16","alias_value":"HQRS7RUREXBZXECP","created_at":"2026-07-05T07:11:05.041705+00:00"},{"alias_kind":"pith_short_8","alias_value":"HQRS7RUR","created_at":"2026-07-05T07:11:05.041705+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/HQRS7RUREXBZXECPSOCLOLUQCO","json":"https://pith.science/pith/HQRS7RUREXBZXECPSOCLOLUQCO.json","graph_json":"https://pith.science/api/pith-number/HQRS7RUREXBZXECPSOCLOLUQCO/graph.json","events_json":"https://pith.science/api/pith-number/HQRS7RUREXBZXECPSOCLOLUQCO/events.json","paper":"https://pith.science/paper/HQRS7RUR"},"agent_actions":{"view_html":"https://pith.science/pith/HQRS7RUREXBZXECPSOCLOLUQCO","download_json":"https://pith.science/pith/HQRS7RUREXBZXECPSOCLOLUQCO.json","view_paper":"https://pith.science/paper/HQRS7RUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10093&json=true","fetch_graph":"https://pith.science/api/pith-number/HQRS7RUREXBZXECPSOCLOLUQCO/graph.json","fetch_events":"https://pith.science/api/pith-number/HQRS7RUREXBZXECPSOCLOLUQCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HQRS7RUREXBZXECPSOCLOLUQCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HQRS7RUREXBZXECPSOCLOLUQCO/action/storage_attestation","attest_author":"https://pith.science/pith/HQRS7RUREXBZXECPSOCLOLUQCO/action/author_attestation","sign_citation":"https://pith.science/pith/HQRS7RUREXBZXECPSOCLOLUQCO/action/citation_signature","submit_replication":"https://pith.science/pith/HQRS7RUREXBZXECPSOCLOLUQCO/action/replication_record"}},"created_at":"2026-07-05T07:11:05.041705+00:00","updated_at":"2026-07-05T07:11:05.041705+00:00"}