{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UXZXNP2Q5K7LKUIOBGRN7CC7XG","short_pith_number":"pith:UXZXNP2Q","schema_version":"1.0","canonical_sha256":"a5f376bf50eabeb5510e09a2df885fb98b8c5da51bd3e8ecda6b88ab81bf1222","source":{"kind":"arxiv","id":"2108.01561","version":2},"attestation_state":"computed","paper":{"title":"Learning a Neural Diff for Speech Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ariya Rastrow, Grant P. Strimel, Jonathan Macoskey","submitted_at":"2021-08-03T15:14:00Z","abstract_excerpt":"As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered. In this work we address one of these constraints, namely over-the-network data budgets for transferring models from server to device. We present neural update approaches for release of subsequent speech model generations abiding by a data budget. We detail two architecture-agnostic methods which learn compact representations for transmission to devices. We experimentally validate our techniques with results on two tasks (automatic speech recognition and spoken language unde"},"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":"2108.01561","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-08-03T15:14:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"2db67b92a8c69a1825cbbd8bb4202c5c13ce1b786eb56496e18e86e0712bdc31","abstract_canon_sha256":"b692d5c2834729cd4bb2a7c44d5e6ba76c2b282f60405e283de31fb918ec116a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:34.579028Z","signature_b64":"WBAvlGxzlJ2r6GquPu1y7o32ECNsJ9atmxJkA1oE/dxifVTXjet0tQ96ZUrmz1UtJe2HCM9t4DDhFGDkX9T0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5f376bf50eabeb5510e09a2df885fb98b8c5da51bd3e8ecda6b88ab81bf1222","last_reissued_at":"2026-07-05T03:06:34.578527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:34.578527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Neural Diff for Speech Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ariya Rastrow, Grant P. Strimel, Jonathan Macoskey","submitted_at":"2021-08-03T15:14:00Z","abstract_excerpt":"As more speech processing applications execute locally on edge devices, a set of resource constraints must be considered. In this work we address one of these constraints, namely over-the-network data budgets for transferring models from server to device. We present neural update approaches for release of subsequent speech model generations abiding by a data budget. We detail two architecture-agnostic methods which learn compact representations for transmission to devices. We experimentally validate our techniques with results on two tasks (automatic speech recognition and spoken language unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01561","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/2108.01561/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":"2108.01561","created_at":"2026-07-05T03:06:34.578592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01561v2","created_at":"2026-07-05T03:06:34.578592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01561","created_at":"2026-07-05T03:06:34.578592+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXZXNP2Q5K7L","created_at":"2026-07-05T03:06:34.578592+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXZXNP2Q5K7LKUIO","created_at":"2026-07-05T03:06:34.578592+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXZXNP2Q","created_at":"2026-07-05T03:06:34.578592+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/UXZXNP2Q5K7LKUIOBGRN7CC7XG","json":"https://pith.science/pith/UXZXNP2Q5K7LKUIOBGRN7CC7XG.json","graph_json":"https://pith.science/api/pith-number/UXZXNP2Q5K7LKUIOBGRN7CC7XG/graph.json","events_json":"https://pith.science/api/pith-number/UXZXNP2Q5K7LKUIOBGRN7CC7XG/events.json","paper":"https://pith.science/paper/UXZXNP2Q"},"agent_actions":{"view_html":"https://pith.science/pith/UXZXNP2Q5K7LKUIOBGRN7CC7XG","download_json":"https://pith.science/pith/UXZXNP2Q5K7LKUIOBGRN7CC7XG.json","view_paper":"https://pith.science/paper/UXZXNP2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01561&json=true","fetch_graph":"https://pith.science/api/pith-number/UXZXNP2Q5K7LKUIOBGRN7CC7XG/graph.json","fetch_events":"https://pith.science/api/pith-number/UXZXNP2Q5K7LKUIOBGRN7CC7XG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXZXNP2Q5K7LKUIOBGRN7CC7XG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXZXNP2Q5K7LKUIOBGRN7CC7XG/action/storage_attestation","attest_author":"https://pith.science/pith/UXZXNP2Q5K7LKUIOBGRN7CC7XG/action/author_attestation","sign_citation":"https://pith.science/pith/UXZXNP2Q5K7LKUIOBGRN7CC7XG/action/citation_signature","submit_replication":"https://pith.science/pith/UXZXNP2Q5K7LKUIOBGRN7CC7XG/action/replication_record"}},"created_at":"2026-07-05T03:06:34.578592+00:00","updated_at":"2026-07-05T03:06:34.578592+00:00"}