{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ASGWYQVBGNEZFZ6ZSC3VV3PDTQ","short_pith_number":"pith:ASGWYQVB","schema_version":"1.0","canonical_sha256":"048d6c42a1334992e7d990b75aede39c0a499200873c17a85ec8b801534675f4","source":{"kind":"arxiv","id":"2310.02998","version":2},"attestation_state":"computed","paper":{"title":"ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaehong Yoon, Mohit Bansal, Yi-Lin Sung","submitted_at":"2023-10-04T17:34:00Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) can understand the world comprehensively by integrating rich information from different modalities, achieving remarkable advancements on various multimodal downstream tasks. However, deploying LVLMs is often problematic due to their massive computational/energy costs and carbon consumption. Such issues make it infeasible to adopt conventional iterative global pruning, which is costly due to computing the Hessian matrix of the entire large model for sparsification. Alternatively, several studies have recently proposed layer-wise pruning approaches to avoid t"},"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":"2310.02998","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-04T17:34:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"484422d4fef9fe93a808cff09fa4e389a6bfcdaf7311e8c3e80095a96cb9e4b6","abstract_canon_sha256":"1b7eea4ecbbd68400c7ba010aed95aed31ab29b239202130cfa923e4db51e68c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:52.101135Z","signature_b64":"n0dF/CAicsdg+I2t9CNgMkE/TLqpvdCkzlEX1XyaOnoHOW5g34AytFsZmDn5ajAp302ZbyeoIOrEFNvBXNtoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"048d6c42a1334992e7d990b75aede39c0a499200873c17a85ec8b801534675f4","last_reissued_at":"2026-07-05T07:37:52.100633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:52.100633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaehong Yoon, Mohit Bansal, Yi-Lin Sung","submitted_at":"2023-10-04T17:34:00Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) can understand the world comprehensively by integrating rich information from different modalities, achieving remarkable advancements on various multimodal downstream tasks. However, deploying LVLMs is often problematic due to their massive computational/energy costs and carbon consumption. Such issues make it infeasible to adopt conventional iterative global pruning, which is costly due to computing the Hessian matrix of the entire large model for sparsification. Alternatively, several studies have recently proposed layer-wise pruning approaches to avoid t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02998","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/2310.02998/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":"2310.02998","created_at":"2026-07-05T07:37:52.100692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02998v2","created_at":"2026-07-05T07:37:52.100692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02998","created_at":"2026-07-05T07:37:52.100692+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASGWYQVBGNEZ","created_at":"2026-07-05T07:37:52.100692+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASGWYQVBGNEZFZ6Z","created_at":"2026-07-05T07:37:52.100692+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASGWYQVB","created_at":"2026-07-05T07:37:52.100692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28438","citing_title":"When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01322","citing_title":"LinMU: Multimodal Understanding Made Linear","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ","json":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ.json","graph_json":"https://pith.science/api/pith-number/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/graph.json","events_json":"https://pith.science/api/pith-number/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/events.json","paper":"https://pith.science/paper/ASGWYQVB"},"agent_actions":{"view_html":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ","download_json":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ.json","view_paper":"https://pith.science/paper/ASGWYQVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02998&json=true","fetch_graph":"https://pith.science/api/pith-number/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/action/storage_attestation","attest_author":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/action/author_attestation","sign_citation":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/action/citation_signature","submit_replication":"https://pith.science/pith/ASGWYQVBGNEZFZ6ZSC3VV3PDTQ/action/replication_record"}},"created_at":"2026-07-05T07:37:52.100692+00:00","updated_at":"2026-07-05T07:37:52.100692+00:00"}