{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KUZDBGZKBOOAV5B5ZM5ONGGSHS","short_pith_number":"pith:KUZDBGZK","schema_version":"1.0","canonical_sha256":"5532309b2a0b9c0af43dcb3ae698d23c85ed23b6a0232a7a499273638be4e503","source":{"kind":"arxiv","id":"2406.12317","version":1},"attestation_state":"computed","paper":{"title":"Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2024-06-18T06:39:41Z","abstract_excerpt":"Recently, multi-task spoken language understanding (SLU) models have emerged, designed to address various speech processing tasks. However, these models often rely on a large number of parameters. Also, they often encounter difficulties in adapting to new data for a specific task without experiencing catastrophic forgetting of previously trained tasks. In this study, we propose finding task-specific subnetworks within a multi-task SLU model via neural network pruning. In addition to model compression, we expect that the forgetting of previously trained tasks can be mitigated by updating only a"},"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":"2406.12317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T06:39:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"65781fc7171b7e10c8d8a91670ff2e67ef00944c4cb9e21c08ac4eb8495171bd","abstract_canon_sha256":"21ed37c36b6badd7102e13f013558935b9eb08af923aab0e797d93a9529ae944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:44.390997Z","signature_b64":"nj31vwAu0fMqy7+9CQBYwbUxhnhzn4R8XWQN0l+Mp/wK4BD+6aADO3Z50shqA9q7QoF2UUkMXCgjhT3FhESVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5532309b2a0b9c0af43dcb3ae698d23c85ed23b6a0232a7a499273638be4e503","last_reissued_at":"2026-07-05T08:33:44.390604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:44.390604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2024-06-18T06:39:41Z","abstract_excerpt":"Recently, multi-task spoken language understanding (SLU) models have emerged, designed to address various speech processing tasks. However, these models often rely on a large number of parameters. Also, they often encounter difficulties in adapting to new data for a specific task without experiencing catastrophic forgetting of previously trained tasks. In this study, we propose finding task-specific subnetworks within a multi-task SLU model via neural network pruning. In addition to model compression, we expect that the forgetting of previously trained tasks can be mitigated by updating only a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12317","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/2406.12317/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":"2406.12317","created_at":"2026-07-05T08:33:44.390661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12317v1","created_at":"2026-07-05T08:33:44.390661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12317","created_at":"2026-07-05T08:33:44.390661+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUZDBGZKBOOA","created_at":"2026-07-05T08:33:44.390661+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUZDBGZKBOOAV5B5","created_at":"2026-07-05T08:33:44.390661+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUZDBGZK","created_at":"2026-07-05T08:33:44.390661+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/KUZDBGZKBOOAV5B5ZM5ONGGSHS","json":"https://pith.science/pith/KUZDBGZKBOOAV5B5ZM5ONGGSHS.json","graph_json":"https://pith.science/api/pith-number/KUZDBGZKBOOAV5B5ZM5ONGGSHS/graph.json","events_json":"https://pith.science/api/pith-number/KUZDBGZKBOOAV5B5ZM5ONGGSHS/events.json","paper":"https://pith.science/paper/KUZDBGZK"},"agent_actions":{"view_html":"https://pith.science/pith/KUZDBGZKBOOAV5B5ZM5ONGGSHS","download_json":"https://pith.science/pith/KUZDBGZKBOOAV5B5ZM5ONGGSHS.json","view_paper":"https://pith.science/paper/KUZDBGZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12317&json=true","fetch_graph":"https://pith.science/api/pith-number/KUZDBGZKBOOAV5B5ZM5ONGGSHS/graph.json","fetch_events":"https://pith.science/api/pith-number/KUZDBGZKBOOAV5B5ZM5ONGGSHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUZDBGZKBOOAV5B5ZM5ONGGSHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUZDBGZKBOOAV5B5ZM5ONGGSHS/action/storage_attestation","attest_author":"https://pith.science/pith/KUZDBGZKBOOAV5B5ZM5ONGGSHS/action/author_attestation","sign_citation":"https://pith.science/pith/KUZDBGZKBOOAV5B5ZM5ONGGSHS/action/citation_signature","submit_replication":"https://pith.science/pith/KUZDBGZKBOOAV5B5ZM5ONGGSHS/action/replication_record"}},"created_at":"2026-07-05T08:33:44.390661+00:00","updated_at":"2026-07-05T08:33:44.390661+00:00"}