{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R2I7VGXBVOU7EVLNQ6BIWZ5YYQ","short_pith_number":"pith:R2I7VGXB","canonical_record":{"source":{"id":"2505.24469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T11:13:48Z","cross_cats_sorted":[],"title_canon_sha256":"44e3ca2b61b3ab246e3238459bc69af9b882d3819973656f6f018eb34c466412","abstract_canon_sha256":"712fff9b3d3111959916543cc7e29e64f0c87aec14463a1c8dd01d379cfddf16"},"schema_version":"1.0"},"canonical_sha256":"8e91fa9ae1aba9f2556d87828b67b8c43ae9066767d19194ca2934c1c98bf1be","source":{"kind":"arxiv","id":"2505.24469","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24469","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24469v1","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24469","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"R2I7VGXBVOU7","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"R2I7VGXBVOU7EVLN","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"R2I7VGXB","created_at":"2026-07-05T11:12:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R2I7VGXBVOU7EVLNQ6BIWZ5YYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T11:13:48Z","cross_cats_sorted":[],"title_canon_sha256":"44e3ca2b61b3ab246e3238459bc69af9b882d3819973656f6f018eb34c466412","abstract_canon_sha256":"712fff9b3d3111959916543cc7e29e64f0c87aec14463a1c8dd01d379cfddf16"},"schema_version":"1.0"},"canonical_sha256":"8e91fa9ae1aba9f2556d87828b67b8c43ae9066767d19194ca2934c1c98bf1be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:50.342215Z","signature_b64":"GTRpSXMkmU48LCrm7KjMqe6HV3EgnFcqBc9JrMy7rm06qVfZ6/QwyYgE700bkLVxwVJvk0ANbL5jqE+ztj0uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e91fa9ae1aba9f2556d87828b67b8c43ae9066767d19194ca2934c1c98bf1be","last_reissued_at":"2026-07-05T11:12:50.341706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:50.341706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24469","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m02h13yREHyE3mOUwccC3JfCPaePmcCPF0wFhu2Ye2IAF6sIzK/F9NyMOOZxuloqUshZhE63zrifxboh6kS+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:00:12.642944Z"},"content_sha256":"4fbbae773807f8b74f43f3c073045d795c251a335daca33f229ebd95c7f8b5d9","schema_version":"1.0","event_id":"sha256:4fbbae773807f8b74f43f3c073045d795c251a335daca33f229ebd95c7f8b5d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R2I7VGXBVOU7EVLNQ6BIWZ5YYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Smooth Model Compression without Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ander Biguri, Carola-Bibiane Sch\\\"onlieb, Christina Runkel, Jovita Lukasik, Michael Moeller, Natacha Kuete Meli","submitted_at":"2025-05-30T11:13:48Z","abstract_excerpt":"Compressing and pruning large machine learning models has become a critical step towards their deployment in real-world applications. Standard pruning and compression techniques are typically designed without taking the structure of the network's weights into account, limiting their effectiveness. We explore the impact of smooth regularization on neural network training and model compression. By applying nuclear norm, first- and second-order derivative penalties of the weights during training, we encourage structured smoothness while preserving predictive performance on par with non-smooth mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24469","kind":"arxiv","version":1},"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/2505.24469/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":"2026-07-05T11:12:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xxDWFqC9D2a4ih/cxIgsoeJdeQuZkrG43FjJgtCkFwoNcvOtePBn9Ujd28/6hFoR/KPDRhqGUnkksk14X1/gDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:00:12.643886Z"},"content_sha256":"79b463bf6caff0bd54fdc1944cd0e441d8722ac8ad8039b8295b67d53f15e625","schema_version":"1.0","event_id":"sha256:79b463bf6caff0bd54fdc1944cd0e441d8722ac8ad8039b8295b67d53f15e625"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2I7VGXBVOU7EVLNQ6BIWZ5YYQ/bundle.json","state_url":"https://pith.science/pith/R2I7VGXBVOU7EVLNQ6BIWZ5YYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2I7VGXBVOU7EVLNQ6BIWZ5YYQ/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":"2026-08-08T14:00:12Z","links":{"resolver":"https://pith.science/pith/R2I7VGXBVOU7EVLNQ6BIWZ5YYQ","bundle":"https://pith.science/pith/R2I7VGXBVOU7EVLNQ6BIWZ5YYQ/bundle.json","state":"https://pith.science/pith/R2I7VGXBVOU7EVLNQ6BIWZ5YYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2I7VGXBVOU7EVLNQ6BIWZ5YYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R2I7VGXBVOU7EVLNQ6BIWZ5YYQ","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":"712fff9b3d3111959916543cc7e29e64f0c87aec14463a1c8dd01d379cfddf16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T11:13:48Z","title_canon_sha256":"44e3ca2b61b3ab246e3238459bc69af9b882d3819973656f6f018eb34c466412"},"schema_version":"1.0","source":{"id":"2505.24469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24469","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24469v1","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24469","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_12","alias_value":"R2I7VGXBVOU7","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_16","alias_value":"R2I7VGXBVOU7EVLN","created_at":"2026-07-05T11:12:50Z"},{"alias_kind":"pith_short_8","alias_value":"R2I7VGXB","created_at":"2026-07-05T11:12:50Z"}],"graph_snapshots":[{"event_id":"sha256:79b463bf6caff0bd54fdc1944cd0e441d8722ac8ad8039b8295b67d53f15e625","target":"graph","created_at":"2026-07-05T11:12:50Z","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/2505.24469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compressing and pruning large machine learning models has become a critical step towards their deployment in real-world applications. Standard pruning and compression techniques are typically designed without taking the structure of the network's weights into account, limiting their effectiveness. We explore the impact of smooth regularization on neural network training and model compression. By applying nuclear norm, first- and second-order derivative penalties of the weights during training, we encourage structured smoothness while preserving predictive performance on par with non-smooth mod","authors_text":"Ander Biguri, Carola-Bibiane Sch\\\"onlieb, Christina Runkel, Jovita Lukasik, Michael Moeller, Natacha Kuete Meli","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T11:13:48Z","title":"Smooth Model Compression without Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24469","kind":"arxiv","version":1},"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":"sha256:4fbbae773807f8b74f43f3c073045d795c251a335daca33f229ebd95c7f8b5d9","target":"record","created_at":"2026-07-05T11:12:50Z","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":"712fff9b3d3111959916543cc7e29e64f0c87aec14463a1c8dd01d379cfddf16","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T11:13:48Z","title_canon_sha256":"44e3ca2b61b3ab246e3238459bc69af9b882d3819973656f6f018eb34c466412"},"schema_version":"1.0","source":{"id":"2505.24469","kind":"arxiv","version":1}},"canonical_sha256":"8e91fa9ae1aba9f2556d87828b67b8c43ae9066767d19194ca2934c1c98bf1be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e91fa9ae1aba9f2556d87828b67b8c43ae9066767d19194ca2934c1c98bf1be","first_computed_at":"2026-07-05T11:12:50.341706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:50.341706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GTRpSXMkmU48LCrm7KjMqe6HV3EgnFcqBc9JrMy7rm06qVfZ6/QwyYgE700bkLVxwVJvk0ANbL5jqE+ztj0uDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:50.342215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fbbae773807f8b74f43f3c073045d795c251a335daca33f229ebd95c7f8b5d9","sha256:79b463bf6caff0bd54fdc1944cd0e441d8722ac8ad8039b8295b67d53f15e625"],"state_sha256":"e0d2f7b0aae223806b51b853b65bbbd70e08a1f27676060850d9eab781dd5c0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G7fInBcUo2UkWY2R+2uW4YE50i7q2X7RpuEoHcvmZibsKOoNrNpPf4A/yh3XxL1mRuD+XBvLr97dlNXf4RKACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:00:12.650676Z","bundle_sha256":"37a8ee4a318ba03ad23541a18cbc258378936beeface02b4d18e95072ba0dabe"}}