{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FRSP3A5ZOFZFBYKNJ2HO4HGOJE","short_pith_number":"pith:FRSP3A5Z","schema_version":"1.0","canonical_sha256":"2c64fd83b9717250e14d4e8eee1cce491ab5231106724319513824a7926046a4","source":{"kind":"arxiv","id":"2606.30516","version":1},"attestation_state":"computed","paper":{"title":"HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandru Paul Condurache, Jens Mehnert, Lukas Meiner","submitted_at":"2026-06-29T16:24:17Z","abstract_excerpt":"Deploying large convolutional neural networks (CNNs) on resource-constrained devices is challenging due to their high computational cost. While dynamic execution methods are promising, existing approaches for CNNs typically require specialized training or fine-tuning, limiting their effectiveness when applied to pre-trained models and requiring data access. To address this gap, we propose HASTE (Hashing for Tractable Efficiency), a plug-and-play convolution module that enables training-free, dynamic compression of large pre-trained CNNs. At inference time, HASTE uses locality-sensitive hashing"},"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":"2606.30516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T16:24:17Z","cross_cats_sorted":[],"title_canon_sha256":"c39b285294199d8cc099bd079235eaee64a381f74a22cd6bf13984ef40c08a55","abstract_canon_sha256":"0b0718c38709f1966fec8d57b24983c35f80f17b932e94cc9ea2e059460d8adc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:18.347735Z","signature_b64":"++/+dsfxqwnENfjZrn5mEXxiGD5GwxEQv2BRiG+7qP9edVSFG2gj9ZdzWowQimb4Vnkz6fVKtvFqc1EDJ6ZoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c64fd83b9717250e14d4e8eee1cce491ab5231106724319513824a7926046a4","last_reissued_at":"2026-06-30T02:18:18.347267Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:18.347267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandru Paul Condurache, Jens Mehnert, Lukas Meiner","submitted_at":"2026-06-29T16:24:17Z","abstract_excerpt":"Deploying large convolutional neural networks (CNNs) on resource-constrained devices is challenging due to their high computational cost. While dynamic execution methods are promising, existing approaches for CNNs typically require specialized training or fine-tuning, limiting their effectiveness when applied to pre-trained models and requiring data access. To address this gap, we propose HASTE (Hashing for Tractable Efficiency), a plug-and-play convolution module that enables training-free, dynamic compression of large pre-trained CNNs. At inference time, HASTE uses locality-sensitive hashing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30516","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/2606.30516/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":"2606.30516","created_at":"2026-06-30T02:18:18.347337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30516v1","created_at":"2026-06-30T02:18:18.347337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30516","created_at":"2026-06-30T02:18:18.347337+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRSP3A5ZOFZF","created_at":"2026-06-30T02:18:18.347337+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRSP3A5ZOFZFBYKN","created_at":"2026-06-30T02:18:18.347337+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRSP3A5Z","created_at":"2026-06-30T02:18:18.347337+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/FRSP3A5ZOFZFBYKNJ2HO4HGOJE","json":"https://pith.science/pith/FRSP3A5ZOFZFBYKNJ2HO4HGOJE.json","graph_json":"https://pith.science/api/pith-number/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/graph.json","events_json":"https://pith.science/api/pith-number/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/events.json","paper":"https://pith.science/paper/FRSP3A5Z"},"agent_actions":{"view_html":"https://pith.science/pith/FRSP3A5ZOFZFBYKNJ2HO4HGOJE","download_json":"https://pith.science/pith/FRSP3A5ZOFZFBYKNJ2HO4HGOJE.json","view_paper":"https://pith.science/paper/FRSP3A5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30516&json=true","fetch_graph":"https://pith.science/api/pith-number/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/graph.json","fetch_events":"https://pith.science/api/pith-number/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/action/storage_attestation","attest_author":"https://pith.science/pith/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/action/author_attestation","sign_citation":"https://pith.science/pith/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/action/citation_signature","submit_replication":"https://pith.science/pith/FRSP3A5ZOFZFBYKNJ2HO4HGOJE/action/replication_record"}},"created_at":"2026-06-30T02:18:18.347337+00:00","updated_at":"2026-06-30T02:18:18.347337+00:00"}