{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LWFNJ7ARCFRWI3BFPTULG3RF32","short_pith_number":"pith:LWFNJ7AR","schema_version":"1.0","canonical_sha256":"5d8ad4fc111163646c257ce8b36e25dea0087d506f02d3ad6621360d968a9b4e","source":{"kind":"arxiv","id":"2412.06419","version":1},"attestation_state":"computed","paper":{"title":"LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haihang Wu","submitted_at":"2024-12-09T11:57:16Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance across various language tasks, but their widespread deployment is impeded by their large size and high computational costs. Structural pruning is a prevailing technique used to introduce sparsity into pre-trained models and facilitate direct hardware acceleration during inference by removing redundant connections (structurally-grouped parameters), such as channels and attention heads. Existing structural pruning approaches often employ either global or layer-wise pruning criteria; however, they are hindered by ineffectivenes"},"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":"2412.06419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T11:57:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73e68accb755e15f17f196b1e17e5964da49cde11d6415e5bc7d772975a4d632","abstract_canon_sha256":"13cf415b886d42486a4b098445828b721702794f5c65f3532c450194325aa9d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:20.344238Z","signature_b64":"yTBsnMHH+T8DxRAgHOJMDQ0ra94VZ42zR3ACvHaAEExPqPQKUYD04GmBD8k+ALSmOpTMxiA4i451LjCcZA2NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d8ad4fc111163646c257ce8b36e25dea0087d506f02d3ad6621360d968a9b4e","last_reissued_at":"2026-07-05T09:46:20.343841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:20.343841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-BIP: Structured Pruning for Large Language Models with Block-Wise Forward Importance Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haihang Wu","submitted_at":"2024-12-09T11:57:16Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable performance across various language tasks, but their widespread deployment is impeded by their large size and high computational costs. Structural pruning is a prevailing technique used to introduce sparsity into pre-trained models and facilitate direct hardware acceleration during inference by removing redundant connections (structurally-grouped parameters), such as channels and attention heads. Existing structural pruning approaches often employ either global or layer-wise pruning criteria; however, they are hindered by ineffectivenes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06419","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/2412.06419/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":"2412.06419","created_at":"2026-07-05T09:46:20.343898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06419v1","created_at":"2026-07-05T09:46:20.343898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06419","created_at":"2026-07-05T09:46:20.343898+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWFNJ7ARCFRW","created_at":"2026-07-05T09:46:20.343898+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWFNJ7ARCFRWI3BF","created_at":"2026-07-05T09:46:20.343898+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWFNJ7AR","created_at":"2026-07-05T09:46:20.343898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19398","citing_title":"GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32","json":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32.json","graph_json":"https://pith.science/api/pith-number/LWFNJ7ARCFRWI3BFPTULG3RF32/graph.json","events_json":"https://pith.science/api/pith-number/LWFNJ7ARCFRWI3BFPTULG3RF32/events.json","paper":"https://pith.science/paper/LWFNJ7AR"},"agent_actions":{"view_html":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32","download_json":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32.json","view_paper":"https://pith.science/paper/LWFNJ7AR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06419&json=true","fetch_graph":"https://pith.science/api/pith-number/LWFNJ7ARCFRWI3BFPTULG3RF32/graph.json","fetch_events":"https://pith.science/api/pith-number/LWFNJ7ARCFRWI3BFPTULG3RF32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/action/storage_attestation","attest_author":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/action/author_attestation","sign_citation":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/action/citation_signature","submit_replication":"https://pith.science/pith/LWFNJ7ARCFRWI3BFPTULG3RF32/action/replication_record"}},"created_at":"2026-07-05T09:46:20.343898+00:00","updated_at":"2026-07-05T09:46:20.343898+00:00"}