{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ME7DH7SAZCKUHL4BBMID53OHJC","short_pith_number":"pith:ME7DH7SA","canonical_record":{"source":{"id":"2201.13096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T10:14:31Z","cross_cats_sorted":[],"title_canon_sha256":"19dd966b08ea6e13e953f457831062467237fddba1275fd07408e6e75646911c","abstract_canon_sha256":"adb6dc52829ac3de65a0b7034c79f3c4f73e97667a5e113314782d1b87d4cd93"},"schema_version":"1.0"},"canonical_sha256":"613e33fe40c89543af810b103eedc748875f2f32da8cc31fdba221f6a72a6fe4","source":{"kind":"arxiv","id":"2201.13096","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.13096","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"arxiv_version","alias_value":"2201.13096v2","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13096","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"pith_short_12","alias_value":"ME7DH7SAZCKU","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"pith_short_16","alias_value":"ME7DH7SAZCKUHL4B","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"pith_short_8","alias_value":"ME7DH7SA","created_at":"2026-07-05T04:51:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ME7DH7SAZCKUHL4BBMID53OHJC","target":"record","payload":{"canonical_record":{"source":{"id":"2201.13096","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T10:14:31Z","cross_cats_sorted":[],"title_canon_sha256":"19dd966b08ea6e13e953f457831062467237fddba1275fd07408e6e75646911c","abstract_canon_sha256":"adb6dc52829ac3de65a0b7034c79f3c4f73e97667a5e113314782d1b87d4cd93"},"schema_version":"1.0"},"canonical_sha256":"613e33fe40c89543af810b103eedc748875f2f32da8cc31fdba221f6a72a6fe4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:06.504342Z","signature_b64":"X1mu1QUM4ph2sAz38emPp/iGDgB2K4Zhjx00CAQFcStQ+CpFxkueFYIPJrBnWkYLrBLmYVersXXflwWAQSpxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"613e33fe40c89543af810b103eedc748875f2f32da8cc31fdba221f6a72a6fe4","last_reissued_at":"2026-07-05T04:51:06.503902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:06.503902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.13096","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":"2026-07-05T04:51:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMD9fWz+7ALEPZk/Y/7kzcx9MOZwfUX78QAUJq60Tla1ugA5BKiYibA1HQnf7arwX1nhvv8RbVfxY7gP0WWJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T13:15:33.968787Z"},"content_sha256":"7e9b43df97650e9a5772308f7dfeddabccb23d600dff83473def59f98f6e0bf0","schema_version":"1.0","event_id":"sha256:7e9b43df97650e9a5772308f7dfeddabccb23d600dff83473def59f98f6e0bf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ME7DH7SAZCKUHL4BBMID53OHJC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPDY: Accurate Pruning with Speedup Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dan Alistarh, Elias Frantar","submitted_at":"2022-01-31T10:14:31Z","abstract_excerpt":"The recent focus on the efficiency of deep neural networks (DNNs) has led to significant work on model compression approaches, of which weight pruning is one of the most popular. At the same time, there is rapidly-growing computational support for efficiently executing the unstructured-sparse models obtained via pruning. Yet, most existing pruning methods minimize just the number of remaining weights, i.e. the size of the model, rather than optimizing for inference time. We address this gap by introducing SPDY, a new compression method which automatically determines layer-wise sparsity targets"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13096","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/2201.13096/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":"2026-07-05T04:51:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j/lfCzMq58pi0Ey3mcS/AxTGf2IVu6zmiprwTyx27EMggDHBbWTOZXQP7/MA9UU0dAmYGU8TYVQ4pjofgrsMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T13:15:33.969488Z"},"content_sha256":"50f78a75bd08517abe6c615beae632d59dec4fc7d6b88d0b8c1475640b0233d4","schema_version":"1.0","event_id":"sha256:50f78a75bd08517abe6c615beae632d59dec4fc7d6b88d0b8c1475640b0233d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ME7DH7SAZCKUHL4BBMID53OHJC/bundle.json","state_url":"https://pith.science/pith/ME7DH7SAZCKUHL4BBMID53OHJC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ME7DH7SAZCKUHL4BBMID53OHJC/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":"2026-08-15T13:15:33Z","links":{"resolver":"https://pith.science/pith/ME7DH7SAZCKUHL4BBMID53OHJC","bundle":"https://pith.science/pith/ME7DH7SAZCKUHL4BBMID53OHJC/bundle.json","state":"https://pith.science/pith/ME7DH7SAZCKUHL4BBMID53OHJC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ME7DH7SAZCKUHL4BBMID53OHJC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ME7DH7SAZCKUHL4BBMID53OHJC","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":"adb6dc52829ac3de65a0b7034c79f3c4f73e97667a5e113314782d1b87d4cd93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T10:14:31Z","title_canon_sha256":"19dd966b08ea6e13e953f457831062467237fddba1275fd07408e6e75646911c"},"schema_version":"1.0","source":{"id":"2201.13096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.13096","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"arxiv_version","alias_value":"2201.13096v2","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13096","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"pith_short_12","alias_value":"ME7DH7SAZCKU","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"pith_short_16","alias_value":"ME7DH7SAZCKUHL4B","created_at":"2026-07-05T04:51:06Z"},{"alias_kind":"pith_short_8","alias_value":"ME7DH7SA","created_at":"2026-07-05T04:51:06Z"}],"graph_snapshots":[{"event_id":"sha256:50f78a75bd08517abe6c615beae632d59dec4fc7d6b88d0b8c1475640b0233d4","target":"graph","created_at":"2026-07-05T04:51:06Z","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/2201.13096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent focus on the efficiency of deep neural networks (DNNs) has led to significant work on model compression approaches, of which weight pruning is one of the most popular. At the same time, there is rapidly-growing computational support for efficiently executing the unstructured-sparse models obtained via pruning. Yet, most existing pruning methods minimize just the number of remaining weights, i.e. the size of the model, rather than optimizing for inference time. We address this gap by introducing SPDY, a new compression method which automatically determines layer-wise sparsity targets","authors_text":"Dan Alistarh, Elias Frantar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T10:14:31Z","title":"SPDY: Accurate Pruning with Speedup Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13096","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":"sha256:7e9b43df97650e9a5772308f7dfeddabccb23d600dff83473def59f98f6e0bf0","target":"record","created_at":"2026-07-05T04:51:06Z","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":"adb6dc52829ac3de65a0b7034c79f3c4f73e97667a5e113314782d1b87d4cd93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T10:14:31Z","title_canon_sha256":"19dd966b08ea6e13e953f457831062467237fddba1275fd07408e6e75646911c"},"schema_version":"1.0","source":{"id":"2201.13096","kind":"arxiv","version":2}},"canonical_sha256":"613e33fe40c89543af810b103eedc748875f2f32da8cc31fdba221f6a72a6fe4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"613e33fe40c89543af810b103eedc748875f2f32da8cc31fdba221f6a72a6fe4","first_computed_at":"2026-07-05T04:51:06.503902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:51:06.503902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X1mu1QUM4ph2sAz38emPp/iGDgB2K4Zhjx00CAQFcStQ+CpFxkueFYIPJrBnWkYLrBLmYVersXXflwWAQSpxAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:51:06.504342Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.13096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e9b43df97650e9a5772308f7dfeddabccb23d600dff83473def59f98f6e0bf0","sha256:50f78a75bd08517abe6c615beae632d59dec4fc7d6b88d0b8c1475640b0233d4"],"state_sha256":"8ea85b4414d791e32f0b55595f431daa037d3f1faecaa98c7962f03fd6d429f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V+PJ7ULRV4jWZeM+iCGLXNE+hNfJJR85pDRVZcDNr7wBybsyGki5V0kEP7hgr/evId/vKZ/7tFhGuoTAma9oBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T13:15:33.973214Z","bundle_sha256":"a6f948a404b78f21accb04848c8a21c46f15b4ce865dcd17ddf4ae2d6a871f79"}}