{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:26T4J6Y3XI4FGFRHQRQCUOBVLJ","short_pith_number":"pith:26T4J6Y3","canonical_record":{"source":{"id":"2308.02060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T21:49:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"adbaf9b02c3ba4aea9f4cf991382f5c563365fa210028ffaa6d09a829aa33e3d","abstract_canon_sha256":"efb4fbbdc1333a067b5a20620967c48ee4079c7b4c6fa4d19b406b8346464281"},"schema_version":"1.0"},"canonical_sha256":"d7a7c4fb1bba3853162784602a38355a7452fb31d98485b05d6f0ebdaba0b429","source":{"kind":"arxiv","id":"2308.02060","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02060","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02060v2","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02060","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"pith_short_12","alias_value":"26T4J6Y3XI4F","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"pith_short_16","alias_value":"26T4J6Y3XI4FGFRH","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"pith_short_8","alias_value":"26T4J6Y3","created_at":"2026-07-05T06:48:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:26T4J6Y3XI4FGFRHQRQCUOBVLJ","target":"record","payload":{"canonical_record":{"source":{"id":"2308.02060","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T21:49:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"adbaf9b02c3ba4aea9f4cf991382f5c563365fa210028ffaa6d09a829aa33e3d","abstract_canon_sha256":"efb4fbbdc1333a067b5a20620967c48ee4079c7b4c6fa4d19b406b8346464281"},"schema_version":"1.0"},"canonical_sha256":"d7a7c4fb1bba3853162784602a38355a7452fb31d98485b05d6f0ebdaba0b429","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:50.746695Z","signature_b64":"zHdQVtpcV8PkrSA9R/tui71qcRQs3P3OFn8ZshPWjtrkyF2jxizQATqopqfhYOJ2HcLxTp2NCvRhWq1UjY8NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7a7c4fb1bba3853162784602a38355a7452fb31d98485b05d6f0ebdaba0b429","last_reissued_at":"2026-07-05T06:48:50.746151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:50.746151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.02060","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":"2026-07-05T06:48:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCRX3sE9lmfHsLBpWaC2YmAmn3ZSDHQkffGt2SSqtsSQGeQUS1/DzILq+NVZIiJyQPuaN2LVuuc4SkaYnG8QCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:06:48.318290Z"},"content_sha256":"9358c97e5079b32b96cdaecad56b02d7f3f022dcd2b9f112166d0093245b4ccb","schema_version":"1.0","event_id":"sha256:9358c97e5079b32b96cdaecad56b02d7f3f022dcd2b9f112166d0093245b4ccb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:26T4J6Y3XI4FGFRHQRQCUOBVLJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexandra Peste, Dan Alistarh, Denis Kuznedelev, Eldar Kurtic, Elias Frantar, Eugenia Iofinova","submitted_at":"2023-08-03T21:49:14Z","abstract_excerpt":"Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the community. Yet, much less is known about the interaction between sparsity and the standard stochastic optimization techniques used for training sparse networks, and most existing work uses standard dense schedules and hyperparameters for training sparse networks. In this work, we examine the impact of high sparsity on model training using the standard computer visi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02060","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/2308.02060/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":"2026-07-05T06:48:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"16KggjpJiUJrlyf/xH7hopzAtQ6uepMAciv0umdP+BELyQG4K27f3uTPZmPyfkEox8BnKhLE9az999JuGI4+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T01:06:48.345173Z"},"content_sha256":"ef14cd8dfd61bb7cf4a25638f3f3af20e26bec35119873ac4747bac58b91a9ec","schema_version":"1.0","event_id":"sha256:ef14cd8dfd61bb7cf4a25638f3f3af20e26bec35119873ac4747bac58b91a9ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26T4J6Y3XI4FGFRHQRQCUOBVLJ/bundle.json","state_url":"https://pith.science/pith/26T4J6Y3XI4FGFRHQRQCUOBVLJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26T4J6Y3XI4FGFRHQRQCUOBVLJ/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":"2026-08-05T01:06:48Z","links":{"resolver":"https://pith.science/pith/26T4J6Y3XI4FGFRHQRQCUOBVLJ","bundle":"https://pith.science/pith/26T4J6Y3XI4FGFRHQRQCUOBVLJ/bundle.json","state":"https://pith.science/pith/26T4J6Y3XI4FGFRHQRQCUOBVLJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26T4J6Y3XI4FGFRHQRQCUOBVLJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:26T4J6Y3XI4FGFRHQRQCUOBVLJ","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":"efb4fbbdc1333a067b5a20620967c48ee4079c7b4c6fa4d19b406b8346464281","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T21:49:14Z","title_canon_sha256":"adbaf9b02c3ba4aea9f4cf991382f5c563365fa210028ffaa6d09a829aa33e3d"},"schema_version":"1.0","source":{"id":"2308.02060","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.02060","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"arxiv_version","alias_value":"2308.02060v2","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02060","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"pith_short_12","alias_value":"26T4J6Y3XI4F","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"pith_short_16","alias_value":"26T4J6Y3XI4FGFRH","created_at":"2026-07-05T06:48:50Z"},{"alias_kind":"pith_short_8","alias_value":"26T4J6Y3","created_at":"2026-07-05T06:48:50Z"}],"graph_snapshots":[{"event_id":"sha256:ef14cd8dfd61bb7cf4a25638f3f3af20e26bec35119873ac4747bac58b91a9ec","target":"graph","created_at":"2026-07-05T06:48:50Z","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/2308.02060/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the community. Yet, much less is known about the interaction between sparsity and the standard stochastic optimization techniques used for training sparse networks, and most existing work uses standard dense schedules and hyperparameters for training sparse networks. In this work, we examine the impact of high sparsity on model training using the standard computer visi","authors_text":"Alexandra Peste, Dan Alistarh, Denis Kuznedelev, Eldar Kurtic, Elias Frantar, Eugenia Iofinova","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T21:49:14Z","title":"Accurate Neural Network Pruning Requires Rethinking Sparse Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02060","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":"sha256:9358c97e5079b32b96cdaecad56b02d7f3f022dcd2b9f112166d0093245b4ccb","target":"record","created_at":"2026-07-05T06:48:50Z","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":"efb4fbbdc1333a067b5a20620967c48ee4079c7b4c6fa4d19b406b8346464281","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-03T21:49:14Z","title_canon_sha256":"adbaf9b02c3ba4aea9f4cf991382f5c563365fa210028ffaa6d09a829aa33e3d"},"schema_version":"1.0","source":{"id":"2308.02060","kind":"arxiv","version":2}},"canonical_sha256":"d7a7c4fb1bba3853162784602a38355a7452fb31d98485b05d6f0ebdaba0b429","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7a7c4fb1bba3853162784602a38355a7452fb31d98485b05d6f0ebdaba0b429","first_computed_at":"2026-07-05T06:48:50.746151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:50.746151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zHdQVtpcV8PkrSA9R/tui71qcRQs3P3OFn8ZshPWjtrkyF2jxizQATqopqfhYOJ2HcLxTp2NCvRhWq1UjY8NBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:50.746695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.02060","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9358c97e5079b32b96cdaecad56b02d7f3f022dcd2b9f112166d0093245b4ccb","sha256:ef14cd8dfd61bb7cf4a25638f3f3af20e26bec35119873ac4747bac58b91a9ec"],"state_sha256":"e92e3d53c64d168ee8062334c4d33d3538a2f6ef77996cae89ffe24c393fb661"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/h80YclPNNEMXXRB9pk+D6JTSRKokyKzxEUexxUV5yWbnzrYjvRecfIzZHY8XOMk9VUXk7oPolb0TUo7PM8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T01:06:48.416353Z","bundle_sha256":"25b8f8eb4ca290815ddea20dc19a14d3b0acaed285a861d4fffdf03c143d3ce8"}}