{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3CM3A443BIJK2B452VY7CMQ4XK","short_pith_number":"pith:3CM3A443","canonical_record":{"source":{"id":"2407.20584","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T06:33:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64ae67cf497a20b5211c17fea180dc520784f3fc6ad842e5ef6347e67d81be5e","abstract_canon_sha256":"0e97dc2764c76ab73eb70dc47ba8f77bedb31844cec64fd84b3ec5c71c130db4"},"schema_version":"1.0"},"canonical_sha256":"d899b0739b0a12ad079dd571f1321cbabebd34bcfc1d65de93494fe116a639de","source":{"kind":"arxiv","id":"2407.20584","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20584","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20584v3","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20584","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"3CM3A443BIJK","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"pith_short_16","alias_value":"3CM3A443BIJK2B45","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"pith_short_8","alias_value":"3CM3A443","created_at":"2026-07-05T09:50:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3CM3A443BIJK2B452VY7CMQ4XK","target":"record","payload":{"canonical_record":{"source":{"id":"2407.20584","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T06:33:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64ae67cf497a20b5211c17fea180dc520784f3fc6ad842e5ef6347e67d81be5e","abstract_canon_sha256":"0e97dc2764c76ab73eb70dc47ba8f77bedb31844cec64fd84b3ec5c71c130db4"},"schema_version":"1.0"},"canonical_sha256":"d899b0739b0a12ad079dd571f1321cbabebd34bcfc1d65de93494fe116a639de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:50.548895Z","signature_b64":"5a718QZLYV+oChPHlyQ42BeVK9DA2ub5LMAU3zMZx3nqHZAe6wDLOOsRByn03R24Q9/vtnQ+KAimziHgoWNvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d899b0739b0a12ad079dd571f1321cbabebd34bcfc1d65de93494fe116a639de","last_reissued_at":"2026-07-05T09:50:50.548275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:50.548275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.20584","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vfQCuE1DhZf4EjOFsDbF0/8vAqZLZmreL1/iR3KLgOnGwST9evMGGpDyXo0XgsK3eUn+2rUIuYrIg6aGQ4eoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:36:06.931462Z"},"content_sha256":"97a2f73bfd496756c3c511c3a975d556cc3958cb241cdd4f667b6158e68555d1","schema_version":"1.0","event_id":"sha256:97a2f73bfd496756c3c511c3a975d556cc3958cb241cdd4f667b6158e68555d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3CM3A443BIJK2B452VY7CMQ4XK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pruning Large Language Models with Semi-Structural Adaptive Sparse Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guohao Jian, Jianfei Chen, Jun Zhu, Weiyu Huang, Yuezhou Hu","submitted_at":"2024-07-30T06:33:44Z","abstract_excerpt":"The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have attempted to compress LLMs using one-shot pruning methods. However, these methods often suffer from considerable performance degradation on complex language understanding tasks, raising concerns about the feasibility of pruning in LLMs. To address this issue, we propose Adaptive Sparse Trainer (AST), a novel and efficient retraining framework tailored for semi-stru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20584","kind":"arxiv","version":3},"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/2407.20584/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":"2026-07-05T09:50:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IN/Z/+w+dqJTphUd4CePIMWMEe/KFjBmodHZaJa3CW1E3xicAyRndE1dE98eDZrHfh+ydWYI3RQfCTm/TE5DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:36:06.932363Z"},"content_sha256":"aeef0b13a6cc0ce93ee86090248c7325f2bc971920be301ff6aaea73200072dc","schema_version":"1.0","event_id":"sha256:aeef0b13a6cc0ce93ee86090248c7325f2bc971920be301ff6aaea73200072dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CM3A443BIJK2B452VY7CMQ4XK/bundle.json","state_url":"https://pith.science/pith/3CM3A443BIJK2B452VY7CMQ4XK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CM3A443BIJK2B452VY7CMQ4XK/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":"2026-08-10T07:36:06Z","links":{"resolver":"https://pith.science/pith/3CM3A443BIJK2B452VY7CMQ4XK","bundle":"https://pith.science/pith/3CM3A443BIJK2B452VY7CMQ4XK/bundle.json","state":"https://pith.science/pith/3CM3A443BIJK2B452VY7CMQ4XK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CM3A443BIJK2B452VY7CMQ4XK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3CM3A443BIJK2B452VY7CMQ4XK","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":"0e97dc2764c76ab73eb70dc47ba8f77bedb31844cec64fd84b3ec5c71c130db4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T06:33:44Z","title_canon_sha256":"64ae67cf497a20b5211c17fea180dc520784f3fc6ad842e5ef6347e67d81be5e"},"schema_version":"1.0","source":{"id":"2407.20584","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20584","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20584v3","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20584","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"pith_short_12","alias_value":"3CM3A443BIJK","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"pith_short_16","alias_value":"3CM3A443BIJK2B45","created_at":"2026-07-05T09:50:50Z"},{"alias_kind":"pith_short_8","alias_value":"3CM3A443","created_at":"2026-07-05T09:50:50Z"}],"graph_snapshots":[{"event_id":"sha256:aeef0b13a6cc0ce93ee86090248c7325f2bc971920be301ff6aaea73200072dc","target":"graph","created_at":"2026-07-05T09:50:50Z","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/2407.20584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have attempted to compress LLMs using one-shot pruning methods. However, these methods often suffer from considerable performance degradation on complex language understanding tasks, raising concerns about the feasibility of pruning in LLMs. To address this issue, we propose Adaptive Sparse Trainer (AST), a novel and efficient retraining framework tailored for semi-stru","authors_text":"Guohao Jian, Jianfei Chen, Jun Zhu, Weiyu Huang, Yuezhou Hu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T06:33:44Z","title":"Pruning Large Language Models with Semi-Structural Adaptive Sparse Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20584","kind":"arxiv","version":3},"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":"sha256:97a2f73bfd496756c3c511c3a975d556cc3958cb241cdd4f667b6158e68555d1","target":"record","created_at":"2026-07-05T09:50:50Z","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":"0e97dc2764c76ab73eb70dc47ba8f77bedb31844cec64fd84b3ec5c71c130db4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-30T06:33:44Z","title_canon_sha256":"64ae67cf497a20b5211c17fea180dc520784f3fc6ad842e5ef6347e67d81be5e"},"schema_version":"1.0","source":{"id":"2407.20584","kind":"arxiv","version":3}},"canonical_sha256":"d899b0739b0a12ad079dd571f1321cbabebd34bcfc1d65de93494fe116a639de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d899b0739b0a12ad079dd571f1321cbabebd34bcfc1d65de93494fe116a639de","first_computed_at":"2026-07-05T09:50:50.548275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:50.548275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5a718QZLYV+oChPHlyQ42BeVK9DA2ub5LMAU3zMZx3nqHZAe6wDLOOsRByn03R24Q9/vtnQ+KAimziHgoWNvCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:50.548895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20584","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97a2f73bfd496756c3c511c3a975d556cc3958cb241cdd4f667b6158e68555d1","sha256:aeef0b13a6cc0ce93ee86090248c7325f2bc971920be301ff6aaea73200072dc"],"state_sha256":"281bfe621f1e527d4fb84eea21b4dc3804a52f6d00d63bd284b842a099165896"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HygluoQSBabpnlXADEKnB5J7mZ3HWsXiIKmG3zpB/L5ry09TwNTRba6eWLq+ebSHXKybqFVbtcI+cOXMDh1yDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:36:06.938165Z","bundle_sha256":"77f61c627c2f27013cf035c13d9063418b3eccb642a349800d22d4c688ea395b"}}