{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZY2P6XKUWBCR4NQ5SVEJM7SEFV","short_pith_number":"pith:ZY2P6XKU","canonical_record":{"source":{"id":"2206.06563","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T02:34:07Z","cross_cats_sorted":["math.AT"],"title_canon_sha256":"aa600f0f06c19ad5a6810e5a7567dd2b00189d315696d6b631875fd720062c3e","abstract_canon_sha256":"ca74d95831e3b42acfbab844ea493e16914d2b4c974badf1db5c805e25f6eb19"},"schema_version":"1.0"},"canonical_sha256":"ce34ff5d54b0451e361d9548967e442d44ba42fc52d74dd2623e9b24f534596d","source":{"kind":"arxiv","id":"2206.06563","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.06563","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"arxiv_version","alias_value":"2206.06563v2","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06563","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZY2P6XKUWBCR","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZY2P6XKUWBCR4NQ5","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZY2P6XKU","created_at":"2026-07-05T04:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZY2P6XKUWBCR4NQ5SVEJM7SEFV","target":"record","payload":{"canonical_record":{"source":{"id":"2206.06563","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T02:34:07Z","cross_cats_sorted":["math.AT"],"title_canon_sha256":"aa600f0f06c19ad5a6810e5a7567dd2b00189d315696d6b631875fd720062c3e","abstract_canon_sha256":"ca74d95831e3b42acfbab844ea493e16914d2b4c974badf1db5c805e25f6eb19"},"schema_version":"1.0"},"canonical_sha256":"ce34ff5d54b0451e361d9548967e442d44ba42fc52d74dd2623e9b24f534596d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:28.554410Z","signature_b64":"1SO5dNtDDQeX8xpD6uHTZrAjUWX1ACwDOcA6uF/1THPj+jmno0XHlDvT+Zdj6f6Uu/kvhJvkK5nokxMul2RVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce34ff5d54b0451e361d9548967e442d44ba42fc52d74dd2623e9b24f534596d","last_reissued_at":"2026-07-05T04:32:28.553952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:28.553952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.06563","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":"2026-07-05T04:32:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5UaGKH0JTBU2XXLoUzogKtpC5eDyzF0eA1C5ag7tVVk6sW/dkyVPt8nQT+I5X2tv+YBdlCDP6jU1OIBhkuPYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:06:52.889712Z"},"content_sha256":"c71dc31957c624bc983748f195eec1e593399df48cf7904cde2f84c636cf6abc","schema_version":"1.0","event_id":"sha256:c71dc31957c624bc983748f195eec1e593399df48cf7904cde2f84c636cf6abc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZY2P6XKUWBCR4NQ5SVEJM7SEFV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zeroth-Order Topological Insights into Iterative Magnitude Pruning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.AT"],"primary_cat":"cs.LG","authors_text":"Aishwarya Balwani, Jakob Krzyston","submitted_at":"2022-06-14T02:34:07Z","abstract_excerpt":"Modern-day neural networks are famously large, yet also highly redundant and compressible; there exist numerous pruning strategies in the deep learning literature that yield over 90% sparser sub-networks of fully-trained, dense architectures while still maintaining their original accuracies. Amongst these many methods though -- thanks to its conceptual simplicity, ease of implementation, and efficacy -- Iterative Magnitude Pruning (IMP) dominates in practice and is the de facto baseline to beat in the pruning community. However, theoretical explanations as to why a simplistic method such as IM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06563","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/2206.06563/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":"2026-07-05T04:32:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSZn4WlibIjGgE7HJgi7qqnaH9xnrX3baPSoKQrBUjfENTVD9W0ZEd6y4RBWmAyhwOX0mpWLDXSCd8iY/9h6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:06:52.890364Z"},"content_sha256":"9bd24bed7b30559284568a2791b6f886f970638749af900c7ae7b5615d2f1fb5","schema_version":"1.0","event_id":"sha256:9bd24bed7b30559284568a2791b6f886f970638749af900c7ae7b5615d2f1fb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZY2P6XKUWBCR4NQ5SVEJM7SEFV/bundle.json","state_url":"https://pith.science/pith/ZY2P6XKUWBCR4NQ5SVEJM7SEFV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZY2P6XKUWBCR4NQ5SVEJM7SEFV/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":"2026-08-04T06:06:52Z","links":{"resolver":"https://pith.science/pith/ZY2P6XKUWBCR4NQ5SVEJM7SEFV","bundle":"https://pith.science/pith/ZY2P6XKUWBCR4NQ5SVEJM7SEFV/bundle.json","state":"https://pith.science/pith/ZY2P6XKUWBCR4NQ5SVEJM7SEFV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZY2P6XKUWBCR4NQ5SVEJM7SEFV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZY2P6XKUWBCR4NQ5SVEJM7SEFV","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":"ca74d95831e3b42acfbab844ea493e16914d2b4c974badf1db5c805e25f6eb19","cross_cats_sorted":["math.AT"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T02:34:07Z","title_canon_sha256":"aa600f0f06c19ad5a6810e5a7567dd2b00189d315696d6b631875fd720062c3e"},"schema_version":"1.0","source":{"id":"2206.06563","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.06563","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"arxiv_version","alias_value":"2206.06563v2","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06563","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZY2P6XKUWBCR","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"ZY2P6XKUWBCR4NQ5","created_at":"2026-07-05T04:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"ZY2P6XKU","created_at":"2026-07-05T04:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:9bd24bed7b30559284568a2791b6f886f970638749af900c7ae7b5615d2f1fb5","target":"graph","created_at":"2026-07-05T04:32:28Z","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/2206.06563/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern-day neural networks are famously large, yet also highly redundant and compressible; there exist numerous pruning strategies in the deep learning literature that yield over 90% sparser sub-networks of fully-trained, dense architectures while still maintaining their original accuracies. Amongst these many methods though -- thanks to its conceptual simplicity, ease of implementation, and efficacy -- Iterative Magnitude Pruning (IMP) dominates in practice and is the de facto baseline to beat in the pruning community. However, theoretical explanations as to why a simplistic method such as IM","authors_text":"Aishwarya Balwani, Jakob Krzyston","cross_cats":["math.AT"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T02:34:07Z","title":"Zeroth-Order Topological Insights into Iterative Magnitude Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06563","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:c71dc31957c624bc983748f195eec1e593399df48cf7904cde2f84c636cf6abc","target":"record","created_at":"2026-07-05T04:32:28Z","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":"ca74d95831e3b42acfbab844ea493e16914d2b4c974badf1db5c805e25f6eb19","cross_cats_sorted":["math.AT"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-14T02:34:07Z","title_canon_sha256":"aa600f0f06c19ad5a6810e5a7567dd2b00189d315696d6b631875fd720062c3e"},"schema_version":"1.0","source":{"id":"2206.06563","kind":"arxiv","version":2}},"canonical_sha256":"ce34ff5d54b0451e361d9548967e442d44ba42fc52d74dd2623e9b24f534596d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce34ff5d54b0451e361d9548967e442d44ba42fc52d74dd2623e9b24f534596d","first_computed_at":"2026-07-05T04:32:28.553952Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:28.553952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1SO5dNtDDQeX8xpD6uHTZrAjUWX1ACwDOcA6uF/1THPj+jmno0XHlDvT+Zdj6f6Uu/kvhJvkK5nokxMul2RVBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:28.554410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.06563","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c71dc31957c624bc983748f195eec1e593399df48cf7904cde2f84c636cf6abc","sha256:9bd24bed7b30559284568a2791b6f886f970638749af900c7ae7b5615d2f1fb5"],"state_sha256":"cf1f4b96a5794588105f7ba36eda056c96230b8e7cbf4f7ccf32be0e9107ae2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EoN5w0MXMEljcreliEG/kidh0c51OAp8MaW1Ef80PfeEJCUWCXD0Bs9AA8RZrmpER6Lo6xo8HufeTtcp41SeBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:06:52.895403Z","bundle_sha256":"d07429591da901025f1eb7444078fd159a2f10ca98fe10973aea9a20569b7bd3"}}