{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YI5Z7QZ37EFJ6OTN6XU4QYZVDD","short_pith_number":"pith:YI5Z7QZ3","canonical_record":{"source":{"id":"2506.12876","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T15:02:59Z","cross_cats_sorted":[],"title_canon_sha256":"d31951f3908684b9ea320dcb1d17bff60021e3f14c4a112c5e2d40902c4fba7b","abstract_canon_sha256":"e8ff8554316c96586a262f28c7b2a10b86d1ed87b1855586b8902e29ce540013"},"schema_version":"1.0"},"canonical_sha256":"c23b9fc33bf90a9f3a6df5e9c8633518cf2009ae22205d22395e32faef7f4700","source":{"kind":"arxiv","id":"2506.12876","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12876","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12876v2","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12876","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"YI5Z7QZ37EFJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YI5Z7QZ37EFJ6OTN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YI5Z7QZ3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YI5Z7QZ37EFJ6OTN6XU4QYZVDD","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12876","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T15:02:59Z","cross_cats_sorted":[],"title_canon_sha256":"d31951f3908684b9ea320dcb1d17bff60021e3f14c4a112c5e2d40902c4fba7b","abstract_canon_sha256":"e8ff8554316c96586a262f28c7b2a10b86d1ed87b1855586b8902e29ce540013"},"schema_version":"1.0"},"canonical_sha256":"c23b9fc33bf90a9f3a6df5e9c8633518cf2009ae22205d22395e32faef7f4700","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:35.438038Z","signature_b64":"7VKw2WGCDp6hDR++4TjvcxWFAtjzn62d0d+aHL6e2FW3Aasr3uhYFA7roaBkg/8bVThbmMzt3MeEi4Y76e+tBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c23b9fc33bf90a9f3a6df5e9c8633518cf2009ae22205d22395e32faef7f4700","last_reissued_at":"2026-05-18T03:09:35.437385Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:35.437385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12876","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":"2026-05-18T03:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5sp7O5EXP7or1oU2VHJmNytqAQ1SXkcdN3nUjPVzR2dcNYyTQzrflHjfNJqqHG05BUUA/M1y0K+onFP6ma/fAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T21:05:40.539634Z"},"content_sha256":"b0acaa9f9c15423b00a0519881c7dcac53823c51eee556add4149dee37f3d381","schema_version":"1.0","event_id":"sha256:b0acaa9f9c15423b00a0519881c7dcac53823c51eee556add4149dee37f3d381"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YI5Z7QZ37EFJ6OTN6XU4QYZVDD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Li Shen, Qixin Zhang, Xikun Zhang, Yan Sun, Zhiyuan Yu","submitted_at":"2025-06-15T15:02:59Z","abstract_excerpt":"The rapid scaling of large language models~(LLMs) has made inference efficiency a primary bottleneck in the practical deployment. To address this, semi-structured sparsity offers a promising solution by strategically retaining $N$ elements out of every $M$ weights, thereby enabling hardware-friendly acceleration and reduced memory. However, existing (N:M)-compatible approaches typically fall into two categories: rule-based layerwise greedy search, which suffers from considerable errors, and gradient-driven combinatorial learning, which incurs prohibitive training costs. To tackle these challen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12876","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":""},"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":"2026-05-18T03:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gb8SUbl5b8LhowU7R7DA1y3e3BQRt3g3icg1eNXdbmAZYKC/AkoJ73altK5xswEY4Mldg8/cgqEmig5yOWqXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T21:05:40.540383Z"},"content_sha256":"e20003b8662166211fa6bd3ebb9da3c0e557f19edbca16eb394b879adf2621ad","schema_version":"1.0","event_id":"sha256:e20003b8662166211fa6bd3ebb9da3c0e557f19edbca16eb394b879adf2621ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YI5Z7QZ37EFJ6OTN6XU4QYZVDD/bundle.json","state_url":"https://pith.science/pith/YI5Z7QZ37EFJ6OTN6XU4QYZVDD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YI5Z7QZ37EFJ6OTN6XU4QYZVDD/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":"2026-06-08T21:05:40Z","links":{"resolver":"https://pith.science/pith/YI5Z7QZ37EFJ6OTN6XU4QYZVDD","bundle":"https://pith.science/pith/YI5Z7QZ37EFJ6OTN6XU4QYZVDD/bundle.json","state":"https://pith.science/pith/YI5Z7QZ37EFJ6OTN6XU4QYZVDD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YI5Z7QZ37EFJ6OTN6XU4QYZVDD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YI5Z7QZ37EFJ6OTN6XU4QYZVDD","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":"e8ff8554316c96586a262f28c7b2a10b86d1ed87b1855586b8902e29ce540013","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T15:02:59Z","title_canon_sha256":"d31951f3908684b9ea320dcb1d17bff60021e3f14c4a112c5e2d40902c4fba7b"},"schema_version":"1.0","source":{"id":"2506.12876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12876","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12876v2","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12876","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"YI5Z7QZ37EFJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YI5Z7QZ37EFJ6OTN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YI5Z7QZ3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e20003b8662166211fa6bd3ebb9da3c0e557f19edbca16eb394b879adf2621ad","target":"graph","created_at":"2026-05-18T03:09:35Z","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"},"paper":{"abstract_excerpt":"The rapid scaling of large language models~(LLMs) has made inference efficiency a primary bottleneck in the practical deployment. To address this, semi-structured sparsity offers a promising solution by strategically retaining $N$ elements out of every $M$ weights, thereby enabling hardware-friendly acceleration and reduced memory. However, existing (N:M)-compatible approaches typically fall into two categories: rule-based layerwise greedy search, which suffers from considerable errors, and gradient-driven combinatorial learning, which incurs prohibitive training costs. To tackle these challen","authors_text":"Dacheng Tao, Li Shen, Qixin Zhang, Xikun Zhang, Yan Sun, Zhiyuan Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T15:02:59Z","title":"MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12876","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:b0acaa9f9c15423b00a0519881c7dcac53823c51eee556add4149dee37f3d381","target":"record","created_at":"2026-05-18T03:09:35Z","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":"e8ff8554316c96586a262f28c7b2a10b86d1ed87b1855586b8902e29ce540013","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T15:02:59Z","title_canon_sha256":"d31951f3908684b9ea320dcb1d17bff60021e3f14c4a112c5e2d40902c4fba7b"},"schema_version":"1.0","source":{"id":"2506.12876","kind":"arxiv","version":2}},"canonical_sha256":"c23b9fc33bf90a9f3a6df5e9c8633518cf2009ae22205d22395e32faef7f4700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c23b9fc33bf90a9f3a6df5e9c8633518cf2009ae22205d22395e32faef7f4700","first_computed_at":"2026-05-18T03:09:35.437385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:35.437385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7VKw2WGCDp6hDR++4TjvcxWFAtjzn62d0d+aHL6e2FW3Aasr3uhYFA7roaBkg/8bVThbmMzt3MeEi4Y76e+tBg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:35.438038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0acaa9f9c15423b00a0519881c7dcac53823c51eee556add4149dee37f3d381","sha256:e20003b8662166211fa6bd3ebb9da3c0e557f19edbca16eb394b879adf2621ad"],"state_sha256":"7c0965896de96b9617af6b7c6efacd75607ec9ae7c46356676e17324ac91ce96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W5zH4Qyoye2PEI+C/0mg4pKemkzmNCVNLsPvMhc5q+rIVMY7fDrMy0c48n7DgEUvZKvQ3WPeaTca90BzOcXgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T21:05:40.544889Z","bundle_sha256":"05427aa6d33370b757d65db1990f7374222252a736d2d1d4d22382706d6830fa"}}