{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H63NPTPLZI4MD2GP27PVXK7TCI","short_pith_number":"pith:H63NPTPL","schema_version":"1.0","canonical_sha256":"3fb6d7cdebca38c1e8cfd7df5babf3120a31b9720cafb802dcddc108fda1c661","source":{"kind":"arxiv","id":"2209.11785","version":3},"attestation_state":"computed","paper":{"title":"Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex-Fit Florea, Chen-Han Yu, Denys Fridman, Mateusz Sieniawski, Pawe{\\l} Morkisz, S{\\l}awomir Kierat, Szymon Migacz","submitted_at":"2022-09-23T18:03:54Z","abstract_excerpt":"We propose three novel pruning techniques to improve the cost and results of inference-aware Differentiable Neural Architecture Search (DNAS). First, we introduce Prunode, a stochastic bi-path building block for DNAS, which can search over inner hidden dimensions with O(1) memory and compute complexity. Second, we present an algorithm for pruning blocks within a stochastic layer of the SuperNet during the search. Third, we describe a novel technique for pruning unnecessary stochastic layers during the search. The optimized models resulting from the search are called PruNet and establishes a ne"},"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":"2209.11785","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-23T18:03:54Z","cross_cats_sorted":[],"title_canon_sha256":"2a6de5df042b46204cff1a4ea4933d81c639f7c2db18be408d79b0ba7c4089d9","abstract_canon_sha256":"1a1986bd6369fe1afc915cf648703713bfc102e0813f1558dea2ebaf33accd61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:44.232790Z","signature_b64":"EiYQWtoLGMkV1x3aHwhW1JT2eDSUZG+5pMRSUlEbZvpAeEAbTung245TidNX7hV2WSogC9WTNxt1KdOS07MkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fb6d7cdebca38c1e8cfd7df5babf3120a31b9720cafb802dcddc108fda1c661","last_reissued_at":"2026-07-05T05:30:44.232214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:44.232214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex-Fit Florea, Chen-Han Yu, Denys Fridman, Mateusz Sieniawski, Pawe{\\l} Morkisz, S{\\l}awomir Kierat, Szymon Migacz","submitted_at":"2022-09-23T18:03:54Z","abstract_excerpt":"We propose three novel pruning techniques to improve the cost and results of inference-aware Differentiable Neural Architecture Search (DNAS). First, we introduce Prunode, a stochastic bi-path building block for DNAS, which can search over inner hidden dimensions with O(1) memory and compute complexity. Second, we present an algorithm for pruning blocks within a stochastic layer of the SuperNet during the search. Third, we describe a novel technique for pruning unnecessary stochastic layers during the search. The optimized models resulting from the search are called PruNet and establishes a ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11785","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/2209.11785/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":"2209.11785","created_at":"2026-07-05T05:30:44.232287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11785v3","created_at":"2026-07-05T05:30:44.232287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11785","created_at":"2026-07-05T05:30:44.232287+00:00"},{"alias_kind":"pith_short_12","alias_value":"H63NPTPLZI4M","created_at":"2026-07-05T05:30:44.232287+00:00"},{"alias_kind":"pith_short_16","alias_value":"H63NPTPLZI4MD2GP","created_at":"2026-07-05T05:30:44.232287+00:00"},{"alias_kind":"pith_short_8","alias_value":"H63NPTPL","created_at":"2026-07-05T05:30:44.232287+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/H63NPTPLZI4MD2GP27PVXK7TCI","json":"https://pith.science/pith/H63NPTPLZI4MD2GP27PVXK7TCI.json","graph_json":"https://pith.science/api/pith-number/H63NPTPLZI4MD2GP27PVXK7TCI/graph.json","events_json":"https://pith.science/api/pith-number/H63NPTPLZI4MD2GP27PVXK7TCI/events.json","paper":"https://pith.science/paper/H63NPTPL"},"agent_actions":{"view_html":"https://pith.science/pith/H63NPTPLZI4MD2GP27PVXK7TCI","download_json":"https://pith.science/pith/H63NPTPLZI4MD2GP27PVXK7TCI.json","view_paper":"https://pith.science/paper/H63NPTPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11785&json=true","fetch_graph":"https://pith.science/api/pith-number/H63NPTPLZI4MD2GP27PVXK7TCI/graph.json","fetch_events":"https://pith.science/api/pith-number/H63NPTPLZI4MD2GP27PVXK7TCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H63NPTPLZI4MD2GP27PVXK7TCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H63NPTPLZI4MD2GP27PVXK7TCI/action/storage_attestation","attest_author":"https://pith.science/pith/H63NPTPLZI4MD2GP27PVXK7TCI/action/author_attestation","sign_citation":"https://pith.science/pith/H63NPTPLZI4MD2GP27PVXK7TCI/action/citation_signature","submit_replication":"https://pith.science/pith/H63NPTPLZI4MD2GP27PVXK7TCI/action/replication_record"}},"created_at":"2026-07-05T05:30:44.232287+00:00","updated_at":"2026-07-05T05:30:44.232287+00:00"}