{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:F5JS22K6JBF2MFH3B7YDR4VOMK","short_pith_number":"pith:F5JS22K6","canonical_record":{"source":{"id":"2205.11921","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T09:29:02Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"dda7901eece7e92bc8bfae603b2f5d1c1d2b518dab2acd92bdf1d6f2477d87ee","abstract_canon_sha256":"4677530c541c2c22ee24fb6d1ebeb2b71ed5b3dc9022fe83eec2ca259b7b48d8"},"schema_version":"1.0"},"canonical_sha256":"2f532d695e484ba614fb0ff038f2ae6289f9c523e5d46ca628c2e660aacfddd2","source":{"kind":"arxiv","id":"2205.11921","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11921","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11921v2","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11921","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"F5JS22K6JBF2","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"F5JS22K6JBF2MFH3","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"F5JS22K6","created_at":"2026-07-05T07:44:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:F5JS22K6JBF2MFH3B7YDR4VOMK","target":"record","payload":{"canonical_record":{"source":{"id":"2205.11921","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T09:29:02Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"dda7901eece7e92bc8bfae603b2f5d1c1d2b518dab2acd92bdf1d6f2477d87ee","abstract_canon_sha256":"4677530c541c2c22ee24fb6d1ebeb2b71ed5b3dc9022fe83eec2ca259b7b48d8"},"schema_version":"1.0"},"canonical_sha256":"2f532d695e484ba614fb0ff038f2ae6289f9c523e5d46ca628c2e660aacfddd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:51.292232Z","signature_b64":"q3Ip/afw4EaiGfPzcjPIwN+G70rqlZU2HiU0lYwLyLlHIjXmEuuApdDsd9WE1lr60coqq30EzuqEentslmr8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f532d695e484ba614fb0ff038f2ae6289f9c523e5d46ca628c2e660aacfddd2","last_reissued_at":"2026-07-05T07:44:51.291686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:51.291686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.11921","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":"2026-07-05T07:44:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"okPRasBjslHiHnqEnOC7pZSoVmFWbEctWooNVE73RyVwzkJLkKIJpXfDLzBlDx898oO26u/2B0sWmtlPunrfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T08:01:16.002896Z"},"content_sha256":"9e36e26c435b718fd261651552500bb970558df3ae0c74e4402ebf2a0fd19187","schema_version":"1.0","event_id":"sha256:9e36e26c435b718fd261651552500bb970558df3ae0c74e4402ebf2a0fd19187"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:F5JS22K6JBF2MFH3B7YDR4VOMK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compression-aware Training of Neural Networks using Frank-Wolfe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Christoph Spiegel, Max Zimmer, Sebastian Pokutta","submitted_at":"2022-05-24T09:29:02Z","abstract_excerpt":"Many existing Neural Network pruning approaches rely on either retraining or inducing a strong bias in order to converge to a sparse solution throughout training. A third paradigm, 'compression-aware' training, aims to obtain state-of-the-art dense models that are robust to a wide range of compression ratios using a single dense training run while also avoiding retraining. We propose a framework centered around a versatile family of norm constraints and the Stochastic Frank-Wolfe (SFW) algorithm that encourage convergence to well-performing solutions while inducing robustness towards convoluti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11921","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/2205.11921/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":"2026-07-05T07:44:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qykx+lg0Xnxy+Tgsb5DuG4Getg6tq27E0WwfjUBUWK1l6/Tb6EpnZQ7ZUmO19OQBZ7+bko9CzYX4SGD8nly2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T08:01:16.003276Z"},"content_sha256":"849ff89f3e46db0f5505a86c0f325dad1ee5e26f3a107fae5306eb51442ca10b","schema_version":"1.0","event_id":"sha256:849ff89f3e46db0f5505a86c0f325dad1ee5e26f3a107fae5306eb51442ca10b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5JS22K6JBF2MFH3B7YDR4VOMK/bundle.json","state_url":"https://pith.science/pith/F5JS22K6JBF2MFH3B7YDR4VOMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5JS22K6JBF2MFH3B7YDR4VOMK/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":"2026-07-11T08:01:16Z","links":{"resolver":"https://pith.science/pith/F5JS22K6JBF2MFH3B7YDR4VOMK","bundle":"https://pith.science/pith/F5JS22K6JBF2MFH3B7YDR4VOMK/bundle.json","state":"https://pith.science/pith/F5JS22K6JBF2MFH3B7YDR4VOMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5JS22K6JBF2MFH3B7YDR4VOMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:F5JS22K6JBF2MFH3B7YDR4VOMK","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":"4677530c541c2c22ee24fb6d1ebeb2b71ed5b3dc9022fe83eec2ca259b7b48d8","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T09:29:02Z","title_canon_sha256":"dda7901eece7e92bc8bfae603b2f5d1c1d2b518dab2acd92bdf1d6f2477d87ee"},"schema_version":"1.0","source":{"id":"2205.11921","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11921","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11921v2","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11921","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"F5JS22K6JBF2","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"F5JS22K6JBF2MFH3","created_at":"2026-07-05T07:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"F5JS22K6","created_at":"2026-07-05T07:44:51Z"}],"graph_snapshots":[{"event_id":"sha256:849ff89f3e46db0f5505a86c0f325dad1ee5e26f3a107fae5306eb51442ca10b","target":"graph","created_at":"2026-07-05T07:44:51Z","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/2205.11921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many existing Neural Network pruning approaches rely on either retraining or inducing a strong bias in order to converge to a sparse solution throughout training. A third paradigm, 'compression-aware' training, aims to obtain state-of-the-art dense models that are robust to a wide range of compression ratios using a single dense training run while also avoiding retraining. We propose a framework centered around a versatile family of norm constraints and the Stochastic Frank-Wolfe (SFW) algorithm that encourage convergence to well-performing solutions while inducing robustness towards convoluti","authors_text":"Christoph Spiegel, Max Zimmer, Sebastian Pokutta","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T09:29:02Z","title":"Compression-aware Training of Neural Networks using Frank-Wolfe"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11921","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":"sha256:9e36e26c435b718fd261651552500bb970558df3ae0c74e4402ebf2a0fd19187","target":"record","created_at":"2026-07-05T07:44:51Z","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":"4677530c541c2c22ee24fb6d1ebeb2b71ed5b3dc9022fe83eec2ca259b7b48d8","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-24T09:29:02Z","title_canon_sha256":"dda7901eece7e92bc8bfae603b2f5d1c1d2b518dab2acd92bdf1d6f2477d87ee"},"schema_version":"1.0","source":{"id":"2205.11921","kind":"arxiv","version":2}},"canonical_sha256":"2f532d695e484ba614fb0ff038f2ae6289f9c523e5d46ca628c2e660aacfddd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f532d695e484ba614fb0ff038f2ae6289f9c523e5d46ca628c2e660aacfddd2","first_computed_at":"2026-07-05T07:44:51.291686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:51.291686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q3Ip/afw4EaiGfPzcjPIwN+G70rqlZU2HiU0lYwLyLlHIjXmEuuApdDsd9WE1lr60coqq30EzuqEentslmr8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:51.292232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11921","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e36e26c435b718fd261651552500bb970558df3ae0c74e4402ebf2a0fd19187","sha256:849ff89f3e46db0f5505a86c0f325dad1ee5e26f3a107fae5306eb51442ca10b"],"state_sha256":"1443be9913e78a9617800c402c51fb9e1af9ceee3a2e528ead51f252d0767bdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sbzE9pKQp+egH8H/0vq6JXkeEGjFGl1HH4ogsEcCx4fvzkRhPhQGdBkuTYNr/kZp3aeYbmR79k3AI3L+HR8TDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T08:01:16.005948Z","bundle_sha256":"7f838ef9a0e1b6bccc8761bb0ff1e388674040d8b3e530893da6a9c58c1849b8"}}