{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DQPAZDPTMHGVQYVID4M2734TQA","short_pith_number":"pith:DQPAZDPT","canonical_record":{"source":{"id":"2508.09471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T04:00:56Z","cross_cats_sorted":[],"title_canon_sha256":"6ed0ac5dae15da9de78371eac13e7f78ceec82fefa3d4c409fa1a6d2381b8d0d","abstract_canon_sha256":"a61f3baec9c9a4d15ce3e4ef0e9940a5ffe6258fcf65305d16f7a5ddc6205630"},"schema_version":"1.0"},"canonical_sha256":"1c1e0c8df361cd5862a81f19afef9380254f396568dba72c68347f6f9e00b4ee","source":{"kind":"arxiv","id":"2508.09471","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09471","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09471v1","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09471","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"pith_short_12","alias_value":"DQPAZDPTMHGV","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"pith_short_16","alias_value":"DQPAZDPTMHGVQYVI","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"pith_short_8","alias_value":"DQPAZDPT","created_at":"2026-07-05T11:53:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DQPAZDPTMHGVQYVID4M2734TQA","target":"record","payload":{"canonical_record":{"source":{"id":"2508.09471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T04:00:56Z","cross_cats_sorted":[],"title_canon_sha256":"6ed0ac5dae15da9de78371eac13e7f78ceec82fefa3d4c409fa1a6d2381b8d0d","abstract_canon_sha256":"a61f3baec9c9a4d15ce3e4ef0e9940a5ffe6258fcf65305d16f7a5ddc6205630"},"schema_version":"1.0"},"canonical_sha256":"1c1e0c8df361cd5862a81f19afef9380254f396568dba72c68347f6f9e00b4ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:15.485333Z","signature_b64":"Dd8Vtqo1hOSSHnrJOtm4EIHBbpLCeI8RC6Xl+DMWugQB7CKP0du7XYHw4wxDs0O/DmtF8i/V+M/fkdmkSa/CCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c1e0c8df361cd5862a81f19afef9380254f396568dba72c68347f6f9e00b4ee","last_reissued_at":"2026-07-05T11:53:15.484821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:15.484821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.09471","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":"2026-07-05T11:53:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NEkQZ6T4WdL39FptrmNuYzz9I1YerBIOt8uSxoGmrClcTcGMszHCwKlRnOtCfZYdT4sYGEY/rpb/OtiT4jO9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:36:15.703852Z"},"content_sha256":"d412038c60d52f8f0faf1a2c3c9b6389e3489a99a95e9349ba362d94ab6ec6ce","schema_version":"1.0","event_id":"sha256:d412038c60d52f8f0faf1a2c3c9b6389e3489a99a95e9349ba362d94ab6ec6ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DQPAZDPTMHGVQYVID4M2734TQA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Omar Bazarbachi, Yanning Shen, Zijun Sun","submitted_at":"2025-08-13T04:00:56Z","abstract_excerpt":"As Large Language Models (LLMs) become more widely adopted and scale up in size, the computational and memory challenges involved in deploying these massive foundation models have grown increasingly severe. This underscores the urgent need to develop more efficient model variants. Faced with this challenge, the present work introduces EGGS-PTP: an Expander-Graph Guided Structured Post-training Pruning method. The proposed approach leverages graph theory to guide the design of N:M structured pruning, effectively reducing model size and computational demands. By incorporating concepts from expan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09471","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/2508.09471/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":"2026-07-05T11:53:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5O9EMF4XekzGl+X2/uDHbpEbkXL7xBy5FYfmyw1XYJxGWTsttINyLgO8ZGNp6/flCaTrI/3gPfe2S/oxfxfAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:36:15.704374Z"},"content_sha256":"2c0f77dafab7302704508d847da3e895788e5e01c3309454469f129e6439498f","schema_version":"1.0","event_id":"sha256:2c0f77dafab7302704508d847da3e895788e5e01c3309454469f129e6439498f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DQPAZDPTMHGVQYVID4M2734TQA/bundle.json","state_url":"https://pith.science/pith/DQPAZDPTMHGVQYVID4M2734TQA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DQPAZDPTMHGVQYVID4M2734TQA/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":"2026-08-08T23:36:15Z","links":{"resolver":"https://pith.science/pith/DQPAZDPTMHGVQYVID4M2734TQA","bundle":"https://pith.science/pith/DQPAZDPTMHGVQYVID4M2734TQA/bundle.json","state":"https://pith.science/pith/DQPAZDPTMHGVQYVID4M2734TQA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DQPAZDPTMHGVQYVID4M2734TQA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DQPAZDPTMHGVQYVID4M2734TQA","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":"a61f3baec9c9a4d15ce3e4ef0e9940a5ffe6258fcf65305d16f7a5ddc6205630","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T04:00:56Z","title_canon_sha256":"6ed0ac5dae15da9de78371eac13e7f78ceec82fefa3d4c409fa1a6d2381b8d0d"},"schema_version":"1.0","source":{"id":"2508.09471","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09471","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09471v1","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09471","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"pith_short_12","alias_value":"DQPAZDPTMHGV","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"pith_short_16","alias_value":"DQPAZDPTMHGVQYVI","created_at":"2026-07-05T11:53:15Z"},{"alias_kind":"pith_short_8","alias_value":"DQPAZDPT","created_at":"2026-07-05T11:53:15Z"}],"graph_snapshots":[{"event_id":"sha256:2c0f77dafab7302704508d847da3e895788e5e01c3309454469f129e6439498f","target":"graph","created_at":"2026-07-05T11:53:15Z","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/2508.09471/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) become more widely adopted and scale up in size, the computational and memory challenges involved in deploying these massive foundation models have grown increasingly severe. This underscores the urgent need to develop more efficient model variants. Faced with this challenge, the present work introduces EGGS-PTP: an Expander-Graph Guided Structured Post-training Pruning method. The proposed approach leverages graph theory to guide the design of N:M structured pruning, effectively reducing model size and computational demands. By incorporating concepts from expan","authors_text":"Omar Bazarbachi, Yanning Shen, Zijun Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T04:00:56Z","title":"EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09471","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:d412038c60d52f8f0faf1a2c3c9b6389e3489a99a95e9349ba362d94ab6ec6ce","target":"record","created_at":"2026-07-05T11:53:15Z","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":"a61f3baec9c9a4d15ce3e4ef0e9940a5ffe6258fcf65305d16f7a5ddc6205630","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T04:00:56Z","title_canon_sha256":"6ed0ac5dae15da9de78371eac13e7f78ceec82fefa3d4c409fa1a6d2381b8d0d"},"schema_version":"1.0","source":{"id":"2508.09471","kind":"arxiv","version":1}},"canonical_sha256":"1c1e0c8df361cd5862a81f19afef9380254f396568dba72c68347f6f9e00b4ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c1e0c8df361cd5862a81f19afef9380254f396568dba72c68347f6f9e00b4ee","first_computed_at":"2026-07-05T11:53:15.484821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:15.484821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dd8Vtqo1hOSSHnrJOtm4EIHBbpLCeI8RC6Xl+DMWugQB7CKP0du7XYHw4wxDs0O/DmtF8i/V+M/fkdmkSa/CCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:15.485333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09471","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d412038c60d52f8f0faf1a2c3c9b6389e3489a99a95e9349ba362d94ab6ec6ce","sha256:2c0f77dafab7302704508d847da3e895788e5e01c3309454469f129e6439498f"],"state_sha256":"6e40d550486195f60fb1abe6a0adb20abf8e65b5f50a8e66b8ab59a4979ef7b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ioZirm40e1pNdxnfkCZhfZcZez4FB6ViH6dGPx6RgE5YYcbGpVEoCfudkfMb9S+hCbiLzRexuaw77gYvg0wCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:36:15.708914Z","bundle_sha256":"962638e618fd17a0a078e0abf11a95eb47d992accfa0a1a6ad5945d0361d5a63"}}