{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MXG43QGQPGMF6IWANIUUYLPSYS","short_pith_number":"pith:MXG43QGQ","canonical_record":{"source":{"id":"2501.16376","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T02:50:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8284e8d110b868d96e3ffe905c0ea6288683d41da19cf7d2d76da376e95dca4","abstract_canon_sha256":"7e685975cd743af24b54bc17e784c2205387ee36625cb43f556b83492745deab"},"schema_version":"1.0"},"canonical_sha256":"65cdcdc0d079985f22c06a294c2df2c4bc9214b71000d54090e11db190e08294","source":{"kind":"arxiv","id":"2501.16376","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16376","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16376v2","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16376","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"MXG43QGQPGMF","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"MXG43QGQPGMF6IWA","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"MXG43QGQ","created_at":"2026-07-05T11:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MXG43QGQPGMF6IWANIUUYLPSYS","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16376","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T02:50:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8284e8d110b868d96e3ffe905c0ea6288683d41da19cf7d2d76da376e95dca4","abstract_canon_sha256":"7e685975cd743af24b54bc17e784c2205387ee36625cb43f556b83492745deab"},"schema_version":"1.0"},"canonical_sha256":"65cdcdc0d079985f22c06a294c2df2c4bc9214b71000d54090e11db190e08294","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:44.501330Z","signature_b64":"/NJ6bKxk2XDYuAg2QcSACDHNDkdPTsy6h6g5lBB3iMSLxug/kegXmok2Y9Mqc7BGuFiJPdGfvRpGaxr6gIl0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65cdcdc0d079985f22c06a294c2df2c4bc9214b71000d54090e11db190e08294","last_reissued_at":"2026-07-05T11:04:44.500774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:44.500774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16376","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nh2SkjXtsT6eFu+gt5jKosZbHDyPfTpJEW7vpD0oJw/5KXANxg+6wthNUFNZkAE7QxhMiz86UEQ1vOnBQKJQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:45:09.532443Z"},"content_sha256":"8f06d612865af9efb06fbfcece653f6c502edb84e7087be4aaee570c13e0b009","schema_version":"1.0","event_id":"sha256:8f06d612865af9efb06fbfcece653f6c502edb84e7087be4aaee570c13e0b009"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MXG43QGQPGMF6IWANIUUYLPSYS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SwiftPrune: Hessian-Free Weight Pruning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jianchao Yang, Jing Feng, Jun He, Mei We, Xinwang Liu, Yang Shi, Yuhan Kang, Zeyu Xue","submitted_at":"2025-01-24T02:50:13Z","abstract_excerpt":"Post-training pruning, as one of the key techniques for compressing large language models, plays a vital role in lightweight model deployment and model sparsity. However, current mainstream pruning methods dependent on the Hessian matrix face significant limitations in both pruning speed and practical effectiveness due to the computationally intensive nature of second-order derivative calculations. This paper presents SwiftPrune, a novel Hessian-free weight pruning method that achieves hardware-efficient model compression through two key innovations: 1) SwiftPrune eliminates the need for compu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16376","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/2501.16376/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":"2026-07-05T11:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b81wCA4fR1fPm5hg/x5u2fs5PbzhpMmBcT/SBjKShagyV7977Yc5tGg+/fu3iFrnZhk3H4B9FDPBWIfTAZNFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:45:09.532968Z"},"content_sha256":"f6c75254bfe52f448ef4d4252cd47ce72c5ccd63308cff856c25efbdcaba44e4","schema_version":"1.0","event_id":"sha256:f6c75254bfe52f448ef4d4252cd47ce72c5ccd63308cff856c25efbdcaba44e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MXG43QGQPGMF6IWANIUUYLPSYS/bundle.json","state_url":"https://pith.science/pith/MXG43QGQPGMF6IWANIUUYLPSYS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MXG43QGQPGMF6IWANIUUYLPSYS/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":"2026-08-10T17:45:09Z","links":{"resolver":"https://pith.science/pith/MXG43QGQPGMF6IWANIUUYLPSYS","bundle":"https://pith.science/pith/MXG43QGQPGMF6IWANIUUYLPSYS/bundle.json","state":"https://pith.science/pith/MXG43QGQPGMF6IWANIUUYLPSYS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MXG43QGQPGMF6IWANIUUYLPSYS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MXG43QGQPGMF6IWANIUUYLPSYS","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":"7e685975cd743af24b54bc17e784c2205387ee36625cb43f556b83492745deab","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T02:50:13Z","title_canon_sha256":"d8284e8d110b868d96e3ffe905c0ea6288683d41da19cf7d2d76da376e95dca4"},"schema_version":"1.0","source":{"id":"2501.16376","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16376","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16376v2","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16376","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"MXG43QGQPGMF","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"MXG43QGQPGMF6IWA","created_at":"2026-07-05T11:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"MXG43QGQ","created_at":"2026-07-05T11:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:f6c75254bfe52f448ef4d4252cd47ce72c5ccd63308cff856c25efbdcaba44e4","target":"graph","created_at":"2026-07-05T11:04:44Z","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/2501.16376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training pruning, as one of the key techniques for compressing large language models, plays a vital role in lightweight model deployment and model sparsity. However, current mainstream pruning methods dependent on the Hessian matrix face significant limitations in both pruning speed and practical effectiveness due to the computationally intensive nature of second-order derivative calculations. This paper presents SwiftPrune, a novel Hessian-free weight pruning method that achieves hardware-efficient model compression through two key innovations: 1) SwiftPrune eliminates the need for compu","authors_text":"Jianchao Yang, Jing Feng, Jun He, Mei We, Xinwang Liu, Yang Shi, Yuhan Kang, Zeyu Xue","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T02:50:13Z","title":"SwiftPrune: Hessian-Free Weight Pruning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16376","kind":"arxiv","version":2},"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":"sha256:8f06d612865af9efb06fbfcece653f6c502edb84e7087be4aaee570c13e0b009","target":"record","created_at":"2026-07-05T11:04:44Z","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":"7e685975cd743af24b54bc17e784c2205387ee36625cb43f556b83492745deab","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T02:50:13Z","title_canon_sha256":"d8284e8d110b868d96e3ffe905c0ea6288683d41da19cf7d2d76da376e95dca4"},"schema_version":"1.0","source":{"id":"2501.16376","kind":"arxiv","version":2}},"canonical_sha256":"65cdcdc0d079985f22c06a294c2df2c4bc9214b71000d54090e11db190e08294","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65cdcdc0d079985f22c06a294c2df2c4bc9214b71000d54090e11db190e08294","first_computed_at":"2026-07-05T11:04:44.500774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:44.500774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/NJ6bKxk2XDYuAg2QcSACDHNDkdPTsy6h6g5lBB3iMSLxug/kegXmok2Y9Mqc7BGuFiJPdGfvRpGaxr6gIl0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:44.501330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16376","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f06d612865af9efb06fbfcece653f6c502edb84e7087be4aaee570c13e0b009","sha256:f6c75254bfe52f448ef4d4252cd47ce72c5ccd63308cff856c25efbdcaba44e4"],"state_sha256":"7cd57b8ad524feb57c64f2104b2b1b8e3f3d99be9ec0b3defb2391e3c7904d72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fWdEnOU7Lrf/gmKzJTy4Fn6hDRLoW5qr85utCbPSVzbcYZyBYjaKyr7zxRRCINSGU7FAhTBJTEnYn0xY8+DIAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:45:09.537622Z","bundle_sha256":"aed8fe7ae412644684c377f4ffb0f0a4ee853090f8c230b337518d92619b5646"}}