{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2ILPWV45ZCVD3PKUKQJI7URNJR","short_pith_number":"pith:2ILPWV45","canonical_record":{"source":{"id":"2409.11233","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"2211d27c36cc26b4b1239ce57386bacc6b7ccebbc243dc519130a352dec65223","abstract_canon_sha256":"da99c5795fe728a0c5c96d7025b5c695c8ee65bbaf593cb5582de8a65a17bf3a"},"schema_version":"1.0"},"canonical_sha256":"d216fb579dc8aa3dbd5454128fd22d4c5e8c6cfb50515df48698e6965b9eb66f","source":{"kind":"arxiv","id":"2409.11233","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11233","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11233v1","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11233","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"pith_short_12","alias_value":"2ILPWV45ZCVD","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"pith_short_16","alias_value":"2ILPWV45ZCVD3PKU","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"pith_short_8","alias_value":"2ILPWV45","created_at":"2026-07-05T09:08:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2ILPWV45ZCVD3PKUKQJI7URNJR","target":"record","payload":{"canonical_record":{"source":{"id":"2409.11233","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:34:11Z","cross_cats_sorted":[],"title_canon_sha256":"2211d27c36cc26b4b1239ce57386bacc6b7ccebbc243dc519130a352dec65223","abstract_canon_sha256":"da99c5795fe728a0c5c96d7025b5c695c8ee65bbaf593cb5582de8a65a17bf3a"},"schema_version":"1.0"},"canonical_sha256":"d216fb579dc8aa3dbd5454128fd22d4c5e8c6cfb50515df48698e6965b9eb66f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:04.074701Z","signature_b64":"keb7mgASKsxaE2zaSRNjmdVIXFulG718ajr4A/rlHY+G1We/KVPN6qe/t6nysliL2gK+0A2GIlwdS6/+2fOcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d216fb579dc8aa3dbd5454128fd22d4c5e8c6cfb50515df48698e6965b9eb66f","last_reissued_at":"2026-07-05T09:08:04.074263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:04.074263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.11233","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KVjw42DSKBFkg3rKYja+/zBLIJSueurL39nlnJ/Bps5yCAAP6Yc67d6wdfiKRRif92A07a7qceDuM94oVyAMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:22:46.861412Z"},"content_sha256":"cea0fe702e43b50348aef1ad520711afbeb74c3cf0c4ed6dbca8d5883fa606e9","schema_version":"1.0","event_id":"sha256:cea0fe702e43b50348aef1ad520711afbeb74c3cf0c4ed6dbca8d5883fa606e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2ILPWV45ZCVD3PKUKQJI7URNJR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating the Impact of Compression Techniques on Task-Specific Performance of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bishwash Khanal, Jeffery M. Capone","submitted_at":"2024-09-17T14:34:11Z","abstract_excerpt":"Large language models (LLMs) offer powerful capabilities but incur substantial computational costs, driving the need for efficient compression techniques. This study evaluates the impact of popular compression methods - Magnitude Pruning, SparseGPT, and Wanda - on the LLaMA-2-7B model, focusing on the trade-offs between model size reduction, downstream task performance, and the role of calibration data. Our findings reveal that while SparseGPT and Wanda preserve perplexity even at 50% sparsity, they suffer significant degradation on downstream tasks, highlighting the inadequacy of perplexity a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11233","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/2409.11233/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C3RgbRyqA9q2s+ifyRYixRct7YKiiUJWrW6gl4wUOlMzFkGMW+jsYRDhyl/beoD02FAHf0/kjR+Xz1q1kPsYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T11:22:46.862496Z"},"content_sha256":"f5ba49a11f0f79cff8224a5840fa269358f1af21b482fa26f1fdf9b5aa610939","schema_version":"1.0","event_id":"sha256:f5ba49a11f0f79cff8224a5840fa269358f1af21b482fa26f1fdf9b5aa610939"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ILPWV45ZCVD3PKUKQJI7URNJR/bundle.json","state_url":"https://pith.science/pith/2ILPWV45ZCVD3PKUKQJI7URNJR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ILPWV45ZCVD3PKUKQJI7URNJR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T11:22:46Z","links":{"resolver":"https://pith.science/pith/2ILPWV45ZCVD3PKUKQJI7URNJR","bundle":"https://pith.science/pith/2ILPWV45ZCVD3PKUKQJI7URNJR/bundle.json","state":"https://pith.science/pith/2ILPWV45ZCVD3PKUKQJI7URNJR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ILPWV45ZCVD3PKUKQJI7URNJR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2ILPWV45ZCVD3PKUKQJI7URNJR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"da99c5795fe728a0c5c96d7025b5c695c8ee65bbaf593cb5582de8a65a17bf3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:34:11Z","title_canon_sha256":"2211d27c36cc26b4b1239ce57386bacc6b7ccebbc243dc519130a352dec65223"},"schema_version":"1.0","source":{"id":"2409.11233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11233","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11233v1","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11233","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"pith_short_12","alias_value":"2ILPWV45ZCVD","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"pith_short_16","alias_value":"2ILPWV45ZCVD3PKU","created_at":"2026-07-05T09:08:04Z"},{"alias_kind":"pith_short_8","alias_value":"2ILPWV45","created_at":"2026-07-05T09:08:04Z"}],"graph_snapshots":[{"event_id":"sha256:f5ba49a11f0f79cff8224a5840fa269358f1af21b482fa26f1fdf9b5aa610939","target":"graph","created_at":"2026-07-05T09:08:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.11233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) offer powerful capabilities but incur substantial computational costs, driving the need for efficient compression techniques. This study evaluates the impact of popular compression methods - Magnitude Pruning, SparseGPT, and Wanda - on the LLaMA-2-7B model, focusing on the trade-offs between model size reduction, downstream task performance, and the role of calibration data. Our findings reveal that while SparseGPT and Wanda preserve perplexity even at 50% sparsity, they suffer significant degradation on downstream tasks, highlighting the inadequacy of perplexity a","authors_text":"Bishwash Khanal, Jeffery M. Capone","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:34:11Z","title":"Evaluating the Impact of Compression Techniques on Task-Specific Performance of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11233","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cea0fe702e43b50348aef1ad520711afbeb74c3cf0c4ed6dbca8d5883fa606e9","target":"record","created_at":"2026-07-05T09:08:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"da99c5795fe728a0c5c96d7025b5c695c8ee65bbaf593cb5582de8a65a17bf3a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T14:34:11Z","title_canon_sha256":"2211d27c36cc26b4b1239ce57386bacc6b7ccebbc243dc519130a352dec65223"},"schema_version":"1.0","source":{"id":"2409.11233","kind":"arxiv","version":1}},"canonical_sha256":"d216fb579dc8aa3dbd5454128fd22d4c5e8c6cfb50515df48698e6965b9eb66f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d216fb579dc8aa3dbd5454128fd22d4c5e8c6cfb50515df48698e6965b9eb66f","first_computed_at":"2026-07-05T09:08:04.074263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:04.074263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"keb7mgASKsxaE2zaSRNjmdVIXFulG718ajr4A/rlHY+G1We/KVPN6qe/t6nysliL2gK+0A2GIlwdS6/+2fOcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:04.074701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cea0fe702e43b50348aef1ad520711afbeb74c3cf0c4ed6dbca8d5883fa606e9","sha256:f5ba49a11f0f79cff8224a5840fa269358f1af21b482fa26f1fdf9b5aa610939"],"state_sha256":"62ec4e835bc284b92c7e29fbea5b15d1ecddfc2ad1bad9ce4300df45a12d7526"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4VaNcOmtjpDQLdXGyq4peMoXWJOnDyvoNhOsfNyI8bghc44N4N1y3vdgZ4jpjOD6wEl1O8H+BLhHkKEBHvATAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T11:22:46.867823Z","bundle_sha256":"98aafd1544747a6dec53e26b675895be2625ede58456d19e02014c92ea81d1a9"}}