{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6DYAXO3ODFG2WNF2GNDWACUDOH","short_pith_number":"pith:6DYAXO3O","canonical_record":{"source":{"id":"2305.02299","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-03T17:48:55Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"02c64728fc3f25da4810a47517c745fe4fad1f7a9e02cf666a8c4ccf55701cf1","abstract_canon_sha256":"2c6012093d36aaa06cc673dfbfddfd67f49844a928d9e050d80ab42459ef44d3"},"schema_version":"1.0"},"canonical_sha256":"f0f00bbb6e194dab34ba3347600a8371c018496d3fa065b78187f14513e3e308","source":{"kind":"arxiv","id":"2305.02299","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02299","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02299v4","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02299","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"pith_short_12","alias_value":"6DYAXO3ODFG2","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"pith_short_16","alias_value":"6DYAXO3ODFG2WNF2","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"pith_short_8","alias_value":"6DYAXO3O","created_at":"2026-07-05T07:47:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6DYAXO3ODFG2WNF2GNDWACUDOH","target":"record","payload":{"canonical_record":{"source":{"id":"2305.02299","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-03T17:48:55Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"02c64728fc3f25da4810a47517c745fe4fad1f7a9e02cf666a8c4ccf55701cf1","abstract_canon_sha256":"2c6012093d36aaa06cc673dfbfddfd67f49844a928d9e050d80ab42459ef44d3"},"schema_version":"1.0"},"canonical_sha256":"f0f00bbb6e194dab34ba3347600a8371c018496d3fa065b78187f14513e3e308","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:56.552459Z","signature_b64":"oZN2ieDJSrqPbCFLQM5pRsakRE8ermV0TWCg3K5ztYcDWBitw2U3ED0FJEcchlOxw9A5qoQTdWpPbO3MeZA/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f00bbb6e194dab34ba3347600a8371c018496d3fa065b78187f14513e3e308","last_reissued_at":"2026-07-05T07:47:56.551824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:56.551824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.02299","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:47:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CE+1eCp1RTJ8OXTP6ueOKyvKiMtXnsnxtB+ECxN8sYBImeypOjnvI83ATrJgsPEK78ZIs2Ajk8RdEE4llaHzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:42:19.721750Z"},"content_sha256":"538bb6e4039de7aba449aafb05cb3638dd15cfd068038c90105f9c9a1d78c767","schema_version":"1.0","event_id":"sha256:538bb6e4039de7aba449aafb05cb3638dd15cfd068038c90105f9c9a1d78c767"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6DYAXO3ODFG2WNF2GNDWACUDOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Sparse Training with Structured Sparsity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Anna Golubeva, Mihai Nica, Mike Lasby, Utku Evci, Yani Ioannou","submitted_at":"2023-05-03T17:48:55Z","abstract_excerpt":"Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training, matching the generalization of dense models while enabling sparse training and inference. Although the resulting models are highly sparse and theoretically less computationally expensive, achieving speedups with unstructured sparsity on real-world hardware is challenging. In this work, we propose a sparse-to-sparse DST method, Structured RigL (SRigL), to learn a variant of fine-grained structured N:M sparsity by imposing a constant fan-in constraint. Using our empirical analysis of existin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02299","kind":"arxiv","version":4},"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/2305.02299/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":"2026-07-05T07:47:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LusgD8wbQhAg99txkKnGReV9rFVibPUbOwdMSaMg9Bxx5AvAxEGnsiwDcAZXD8PS3wVkeY15nKE3P1JLK42CCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:42:19.722235Z"},"content_sha256":"f1bec4452a3e5f3d0d17ff087d9fc2da667c78b39b01b032ecbdf04667457b4b","schema_version":"1.0","event_id":"sha256:f1bec4452a3e5f3d0d17ff087d9fc2da667c78b39b01b032ecbdf04667457b4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6DYAXO3ODFG2WNF2GNDWACUDOH/bundle.json","state_url":"https://pith.science/pith/6DYAXO3ODFG2WNF2GNDWACUDOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6DYAXO3ODFG2WNF2GNDWACUDOH/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":"2026-08-08T03:42:19Z","links":{"resolver":"https://pith.science/pith/6DYAXO3ODFG2WNF2GNDWACUDOH","bundle":"https://pith.science/pith/6DYAXO3ODFG2WNF2GNDWACUDOH/bundle.json","state":"https://pith.science/pith/6DYAXO3ODFG2WNF2GNDWACUDOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6DYAXO3ODFG2WNF2GNDWACUDOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6DYAXO3ODFG2WNF2GNDWACUDOH","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":"2c6012093d36aaa06cc673dfbfddfd67f49844a928d9e050d80ab42459ef44d3","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-03T17:48:55Z","title_canon_sha256":"02c64728fc3f25da4810a47517c745fe4fad1f7a9e02cf666a8c4ccf55701cf1"},"schema_version":"1.0","source":{"id":"2305.02299","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02299","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02299v4","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02299","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"pith_short_12","alias_value":"6DYAXO3ODFG2","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"pith_short_16","alias_value":"6DYAXO3ODFG2WNF2","created_at":"2026-07-05T07:47:56Z"},{"alias_kind":"pith_short_8","alias_value":"6DYAXO3O","created_at":"2026-07-05T07:47:56Z"}],"graph_snapshots":[{"event_id":"sha256:f1bec4452a3e5f3d0d17ff087d9fc2da667c78b39b01b032ecbdf04667457b4b","target":"graph","created_at":"2026-07-05T07:47:56Z","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/2305.02299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training, matching the generalization of dense models while enabling sparse training and inference. Although the resulting models are highly sparse and theoretically less computationally expensive, achieving speedups with unstructured sparsity on real-world hardware is challenging. In this work, we propose a sparse-to-sparse DST method, Structured RigL (SRigL), to learn a variant of fine-grained structured N:M sparsity by imposing a constant fan-in constraint. Using our empirical analysis of existin","authors_text":"Anna Golubeva, Mihai Nica, Mike Lasby, Utku Evci, Yani Ioannou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-03T17:48:55Z","title":"Dynamic Sparse Training with Structured Sparsity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02299","kind":"arxiv","version":4},"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":"sha256:538bb6e4039de7aba449aafb05cb3638dd15cfd068038c90105f9c9a1d78c767","target":"record","created_at":"2026-07-05T07:47:56Z","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":"2c6012093d36aaa06cc673dfbfddfd67f49844a928d9e050d80ab42459ef44d3","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-03T17:48:55Z","title_canon_sha256":"02c64728fc3f25da4810a47517c745fe4fad1f7a9e02cf666a8c4ccf55701cf1"},"schema_version":"1.0","source":{"id":"2305.02299","kind":"arxiv","version":4}},"canonical_sha256":"f0f00bbb6e194dab34ba3347600a8371c018496d3fa065b78187f14513e3e308","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0f00bbb6e194dab34ba3347600a8371c018496d3fa065b78187f14513e3e308","first_computed_at":"2026-07-05T07:47:56.551824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:56.551824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oZN2ieDJSrqPbCFLQM5pRsakRE8ermV0TWCg3K5ztYcDWBitw2U3ED0FJEcchlOxw9A5qoQTdWpPbO3MeZA/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:56.552459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.02299","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:538bb6e4039de7aba449aafb05cb3638dd15cfd068038c90105f9c9a1d78c767","sha256:f1bec4452a3e5f3d0d17ff087d9fc2da667c78b39b01b032ecbdf04667457b4b"],"state_sha256":"f12706d17240254ab5a1df7c03089d4b8004d9efbdbe7dea7952fb1b79888317"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1OIBqq1d/BwU/j7x14kdpuJ9byuVtgtwkct59wjJfccS+t6wnK5zXiRzH7SlyHD+XhS4/NK4cLJu8MUU1mlMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:42:19.725674Z","bundle_sha256":"858ee69f12b04ab1a5b1f7e2aa402b192bafb5c33b308e938cb097786bbb367a"}}