{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JTKM6TOGZQNNGLYPWEPHLNXCKO","short_pith_number":"pith:JTKM6TOG","canonical_record":{"source":{"id":"2502.02496","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:12:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"db08034f869d2b559b295977951443c5ec954095d2f0424ef151386b3f258386","abstract_canon_sha256":"0aa61212864fcd0bec293f9a082c72425be5f5e74433202c1386b9cafea8de7b"},"schema_version":"1.0"},"canonical_sha256":"4cd4cf4dc6cc1ad32f0fb11e75b6e25395ed614b862005a124f1ee55eb616957","source":{"kind":"arxiv","id":"2502.02496","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02496","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02496v2","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02496","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"JTKM6TOGZQNN","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"JTKM6TOGZQNNGLYP","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"JTKM6TOG","created_at":"2026-07-05T10:10:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JTKM6TOGZQNNGLYPWEPHLNXCKO","target":"record","payload":{"canonical_record":{"source":{"id":"2502.02496","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:12:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"db08034f869d2b559b295977951443c5ec954095d2f0424ef151386b3f258386","abstract_canon_sha256":"0aa61212864fcd0bec293f9a082c72425be5f5e74433202c1386b9cafea8de7b"},"schema_version":"1.0"},"canonical_sha256":"4cd4cf4dc6cc1ad32f0fb11e75b6e25395ed614b862005a124f1ee55eb616957","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:49.180829Z","signature_b64":"6s5dbunrTpS1vJA9q7O3SdtD8cdOo3sfIBn8hKDNQB2KG07bTAkKc5YVYBY6RtZhva6Xz1XtC6XUiYdAVOjUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cd4cf4dc6cc1ad32f0fb11e75b6e25395ed614b862005a124f1ee55eb616957","last_reissued_at":"2026-07-05T10:10:49.180365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:49.180365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.02496","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":"2026-07-05T10:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xPOH9U8iKULRfAyOpk6e9WeIFj/Qey5CRACYeWn/dP0rQIq17QYUgdhCilRqqLAO3VPjqy3KviASTTBp85y2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:03:05.439512Z"},"content_sha256":"37f0a8781ec2bbc04ad61fdde01099aaa4b71a2cd83b6d0d6e15a69d95062ec7","schema_version":"1.0","event_id":"sha256:37f0a8781ec2bbc04ad61fdde01099aaa4b71a2cd83b6d0d6e15a69d95062ec7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JTKM6TOGZQNNGLYPWEPHLNXCKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernd Bischl, Chris Kolb, David R\\\"ugamer, Tobias Weber","submitted_at":"2025-02-04T17:12:56Z","abstract_excerpt":"Sparse regularization techniques are well-established in machine learning, yet their application in neural networks remains challenging due to the non-differentiability of penalties like the $L_1$ norm, which is incompatible with stochastic gradient descent. A promising alternative is shallow weight factorization, where weights are decomposed into two factors, allowing for smooth optimization of $L_1$-penalized neural networks by adding differentiable $L_2$ regularization to the factors. In this work, we introduce deep weight factorization, extending previous shallow approaches to more than tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02496","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/2502.02496/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":"2026-07-05T10:10:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KWRQ3tPvtJcMW3g0gPXF7k+/5y+GTjBohLhfDQ2AfDuzod7DMI+nM+x2ZiBuihnOdDthimai6/35JO2nZX+ADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:03:05.440216Z"},"content_sha256":"c6c4d815d5435f1f7352ed0933400e70af1f02a11ed15c5cc792b07eec7d700d","schema_version":"1.0","event_id":"sha256:c6c4d815d5435f1f7352ed0933400e70af1f02a11ed15c5cc792b07eec7d700d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTKM6TOGZQNNGLYPWEPHLNXCKO/bundle.json","state_url":"https://pith.science/pith/JTKM6TOGZQNNGLYPWEPHLNXCKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTKM6TOGZQNNGLYPWEPHLNXCKO/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":"2026-08-10T08:03:05Z","links":{"resolver":"https://pith.science/pith/JTKM6TOGZQNNGLYPWEPHLNXCKO","bundle":"https://pith.science/pith/JTKM6TOGZQNNGLYPWEPHLNXCKO/bundle.json","state":"https://pith.science/pith/JTKM6TOGZQNNGLYPWEPHLNXCKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTKM6TOGZQNNGLYPWEPHLNXCKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JTKM6TOGZQNNGLYPWEPHLNXCKO","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":"0aa61212864fcd0bec293f9a082c72425be5f5e74433202c1386b9cafea8de7b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:12:56Z","title_canon_sha256":"db08034f869d2b559b295977951443c5ec954095d2f0424ef151386b3f258386"},"schema_version":"1.0","source":{"id":"2502.02496","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02496","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02496v2","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02496","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"pith_short_12","alias_value":"JTKM6TOGZQNN","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"pith_short_16","alias_value":"JTKM6TOGZQNNGLYP","created_at":"2026-07-05T10:10:49Z"},{"alias_kind":"pith_short_8","alias_value":"JTKM6TOG","created_at":"2026-07-05T10:10:49Z"}],"graph_snapshots":[{"event_id":"sha256:c6c4d815d5435f1f7352ed0933400e70af1f02a11ed15c5cc792b07eec7d700d","target":"graph","created_at":"2026-07-05T10:10:49Z","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/2502.02496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse regularization techniques are well-established in machine learning, yet their application in neural networks remains challenging due to the non-differentiability of penalties like the $L_1$ norm, which is incompatible with stochastic gradient descent. A promising alternative is shallow weight factorization, where weights are decomposed into two factors, allowing for smooth optimization of $L_1$-penalized neural networks by adding differentiable $L_2$ regularization to the factors. In this work, we introduce deep weight factorization, extending previous shallow approaches to more than tw","authors_text":"Bernd Bischl, Chris Kolb, David R\\\"ugamer, Tobias Weber","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:12:56Z","title":"Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02496","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":"sha256:37f0a8781ec2bbc04ad61fdde01099aaa4b71a2cd83b6d0d6e15a69d95062ec7","target":"record","created_at":"2026-07-05T10:10:49Z","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":"0aa61212864fcd0bec293f9a082c72425be5f5e74433202c1386b9cafea8de7b","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:12:56Z","title_canon_sha256":"db08034f869d2b559b295977951443c5ec954095d2f0424ef151386b3f258386"},"schema_version":"1.0","source":{"id":"2502.02496","kind":"arxiv","version":2}},"canonical_sha256":"4cd4cf4dc6cc1ad32f0fb11e75b6e25395ed614b862005a124f1ee55eb616957","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cd4cf4dc6cc1ad32f0fb11e75b6e25395ed614b862005a124f1ee55eb616957","first_computed_at":"2026-07-05T10:10:49.180365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:49.180365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6s5dbunrTpS1vJA9q7O3SdtD8cdOo3sfIBn8hKDNQB2KG07bTAkKc5YVYBY6RtZhva6Xz1XtC6XUiYdAVOjUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:49.180829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02496","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37f0a8781ec2bbc04ad61fdde01099aaa4b71a2cd83b6d0d6e15a69d95062ec7","sha256:c6c4d815d5435f1f7352ed0933400e70af1f02a11ed15c5cc792b07eec7d700d"],"state_sha256":"4a307dc4f89162cf42612caa22bc89b6a007da998bf91a9858dd3050f1847cc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"psawfplh77Kv+eskm7K+HpMHGk75sGJuoWt9lv1ta3ZiIYje34HWF1AobKyjRDlbouus7RtcaNC2DwWLSxOXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:03:05.447162Z","bundle_sha256":"689b25eb3016be615d7eda6e52a88439b24d61a6963a67fd81e65c49a4e8a3fc"}}