{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7CEMXHIMANILKYQGOHJAWOGRA3","short_pith_number":"pith:7CEMXHIM","schema_version":"1.0","canonical_sha256":"f888cb9d0c0350b5620671d20b38d106df0901aa7b87184b808df75a9854648e","source":{"kind":"arxiv","id":"2310.10054","version":1},"attestation_state":"computed","paper":{"title":"NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Du-Seong Chang, Euijai Ahn, Jongwoo Ko, Seungjoon Park, Se-Young Yun, Sumyeong Ahn, Yujin Kim","submitted_at":"2023-10-16T04:27:36Z","abstract_excerpt":"Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures such as Transformers. Despite the versatility of encoder-decoder models in numerous NLP tasks, the structured pruning methods on such models are relatively less explored compared to encoder-only models. In this study, we investigate the behavior of the structured pruning of the encoder-decoder models in the decoupled pruning perspective of the encoder and decoder component, respectively. Our findings highlight two insights: (1) the number of decoder laye"},"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":"2310.10054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T04:27:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"94aa72548630c1caaa062148b702b3d3385e7784e80d89bcce8e376460d6caeb","abstract_canon_sha256":"edbdf59e3300d573a9087e48c2aed254273b049e065bc87f5fc9a932bcfdc6ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:14.618784Z","signature_b64":"U2T1kzK0wiYeJxqvr+8BCmqM7FQijH/AtoJhTD0LGvA6+HpsIzxiPtbAWuhN19r704kCXoCey7aoaBqLn0FfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f888cb9d0c0350b5620671d20b38d106df0901aa7b87184b808df75a9854648e","last_reissued_at":"2026-07-05T07:01:14.618306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:14.618306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Du-Seong Chang, Euijai Ahn, Jongwoo Ko, Seungjoon Park, Se-Young Yun, Sumyeong Ahn, Yujin Kim","submitted_at":"2023-10-16T04:27:36Z","abstract_excerpt":"Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures such as Transformers. Despite the versatility of encoder-decoder models in numerous NLP tasks, the structured pruning methods on such models are relatively less explored compared to encoder-only models. In this study, we investigate the behavior of the structured pruning of the encoder-decoder models in the decoupled pruning perspective of the encoder and decoder component, respectively. Our findings highlight two insights: (1) the number of decoder laye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10054","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/2310.10054/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":"2310.10054","created_at":"2026-07-05T07:01:14.618371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10054v1","created_at":"2026-07-05T07:01:14.618371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10054","created_at":"2026-07-05T07:01:14.618371+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CEMXHIMANIL","created_at":"2026-07-05T07:01:14.618371+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CEMXHIMANILKYQG","created_at":"2026-07-05T07:01:14.618371+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CEMXHIM","created_at":"2026-07-05T07:01:14.618371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.12876","citing_title":"MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3","json":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3.json","graph_json":"https://pith.science/api/pith-number/7CEMXHIMANILKYQGOHJAWOGRA3/graph.json","events_json":"https://pith.science/api/pith-number/7CEMXHIMANILKYQGOHJAWOGRA3/events.json","paper":"https://pith.science/paper/7CEMXHIM"},"agent_actions":{"view_html":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3","download_json":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3.json","view_paper":"https://pith.science/paper/7CEMXHIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10054&json=true","fetch_graph":"https://pith.science/api/pith-number/7CEMXHIMANILKYQGOHJAWOGRA3/graph.json","fetch_events":"https://pith.science/api/pith-number/7CEMXHIMANILKYQGOHJAWOGRA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3/action/storage_attestation","attest_author":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3/action/author_attestation","sign_citation":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3/action/citation_signature","submit_replication":"https://pith.science/pith/7CEMXHIMANILKYQGOHJAWOGRA3/action/replication_record"}},"created_at":"2026-07-05T07:01:14.618371+00:00","updated_at":"2026-07-05T07:01:14.618371+00:00"}