{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PPKBVNQOWHBFG4NNDPZ5JDOGCA","short_pith_number":"pith:PPKBVNQO","canonical_record":{"source":{"id":"2411.05500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T12:02:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b5095da3dbf619d27c84da8a962ea1a03ad708589811fd75b7d6c0c449ae9fe4","abstract_canon_sha256":"927b38f84672fe3a737ebdacab7ca10d930138e54d391e447cd9194e686e1836"},"schema_version":"1.0"},"canonical_sha256":"7bd41ab60eb1c25371ad1bf3d48dc6100277cc2e45d4e7a927d41f4fb36359af","source":{"kind":"arxiv","id":"2411.05500","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05500","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05500v1","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05500","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"pith_short_12","alias_value":"PPKBVNQOWHBF","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"pith_short_16","alias_value":"PPKBVNQOWHBFG4NN","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"pith_short_8","alias_value":"PPKBVNQO","created_at":"2026-07-05T09:33:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PPKBVNQOWHBFG4NNDPZ5JDOGCA","target":"record","payload":{"canonical_record":{"source":{"id":"2411.05500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T12:02:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b5095da3dbf619d27c84da8a962ea1a03ad708589811fd75b7d6c0c449ae9fe4","abstract_canon_sha256":"927b38f84672fe3a737ebdacab7ca10d930138e54d391e447cd9194e686e1836"},"schema_version":"1.0"},"canonical_sha256":"7bd41ab60eb1c25371ad1bf3d48dc6100277cc2e45d4e7a927d41f4fb36359af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:02.107139Z","signature_b64":"OBZQIEfrffRKw3Ta71LLcgxOuM5tlTSWKc1C4H3BCbqD430Eua21saVuJ+YlRDOlWTdy3v2jq5KgemHv5TfnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bd41ab60eb1c25371ad1bf3d48dc6100277cc2e45d4e7a927d41f4fb36359af","last_reissued_at":"2026-07-05T09:33:02.106623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:02.106623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.05500","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":"2026-07-05T09:33:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1XXhbMS3DYqb+xAXMBmVEpV1nOyAXjUkdbITFRlYVKi3t5nzRebTCHHGi6mdPtpAVtww60HcwK44f57UTxxMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T11:53:23.083436Z"},"content_sha256":"3957ce20fb1948c240440998b13ce39243d826708ff3478345fb8a5ca3dcd693","schema_version":"1.0","event_id":"sha256:3957ce20fb1948c240440998b13ce39243d826708ff3478345fb8a5ca3dcd693"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PPKBVNQOWHBFG4NNDPZ5JDOGCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FGGP: Fixed-Rate Gradient-First Gradual Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Can Deniz Bezek, Lingkai Zhu, Orcun Goksel","submitted_at":"2024-11-08T12:02:25Z","abstract_excerpt":"In recent years, the increasing size of deep learning models and their growing demand for computational resources have drawn significant attention to the practice of pruning neural networks, while aiming to preserve their accuracy. In unstructured gradual pruning, which sparsifies a network by gradually removing individual network parameters until a targeted network sparsity is reached, recent works show that both gradient and weight magnitudes should be considered. In this work, we show that such mechanism, e.g., the order of prioritization and selection criteria, is essential. We introduce a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05500","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/2411.05500/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":"2026-07-05T09:33:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DOXMVFYePmslgmTY7DjP02iymqjrzfNQxlDp8jVrAlypJT6sXmCaaBI5TjlJb0uAbxun3R59engRhUOd62JeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T11:53:23.083814Z"},"content_sha256":"9570d5805c118f760a3fbe6775cc0c4d6f5dcd5c9c17ac8398600ae7159a2314","schema_version":"1.0","event_id":"sha256:9570d5805c118f760a3fbe6775cc0c4d6f5dcd5c9c17ac8398600ae7159a2314"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPKBVNQOWHBFG4NNDPZ5JDOGCA/bundle.json","state_url":"https://pith.science/pith/PPKBVNQOWHBFG4NNDPZ5JDOGCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPKBVNQOWHBFG4NNDPZ5JDOGCA/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":"2026-07-12T11:53:23Z","links":{"resolver":"https://pith.science/pith/PPKBVNQOWHBFG4NNDPZ5JDOGCA","bundle":"https://pith.science/pith/PPKBVNQOWHBFG4NNDPZ5JDOGCA/bundle.json","state":"https://pith.science/pith/PPKBVNQOWHBFG4NNDPZ5JDOGCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPKBVNQOWHBFG4NNDPZ5JDOGCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PPKBVNQOWHBFG4NNDPZ5JDOGCA","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":"927b38f84672fe3a737ebdacab7ca10d930138e54d391e447cd9194e686e1836","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T12:02:25Z","title_canon_sha256":"b5095da3dbf619d27c84da8a962ea1a03ad708589811fd75b7d6c0c449ae9fe4"},"schema_version":"1.0","source":{"id":"2411.05500","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05500","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05500v1","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05500","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"pith_short_12","alias_value":"PPKBVNQOWHBF","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"pith_short_16","alias_value":"PPKBVNQOWHBFG4NN","created_at":"2026-07-05T09:33:02Z"},{"alias_kind":"pith_short_8","alias_value":"PPKBVNQO","created_at":"2026-07-05T09:33:02Z"}],"graph_snapshots":[{"event_id":"sha256:9570d5805c118f760a3fbe6775cc0c4d6f5dcd5c9c17ac8398600ae7159a2314","target":"graph","created_at":"2026-07-05T09:33:02Z","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/2411.05500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, the increasing size of deep learning models and their growing demand for computational resources have drawn significant attention to the practice of pruning neural networks, while aiming to preserve their accuracy. In unstructured gradual pruning, which sparsifies a network by gradually removing individual network parameters until a targeted network sparsity is reached, recent works show that both gradient and weight magnitudes should be considered. In this work, we show that such mechanism, e.g., the order of prioritization and selection criteria, is essential. We introduce a","authors_text":"Can Deniz Bezek, Lingkai Zhu, Orcun Goksel","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T12:02:25Z","title":"FGGP: Fixed-Rate Gradient-First Gradual Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05500","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":"sha256:3957ce20fb1948c240440998b13ce39243d826708ff3478345fb8a5ca3dcd693","target":"record","created_at":"2026-07-05T09:33:02Z","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":"927b38f84672fe3a737ebdacab7ca10d930138e54d391e447cd9194e686e1836","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T12:02:25Z","title_canon_sha256":"b5095da3dbf619d27c84da8a962ea1a03ad708589811fd75b7d6c0c449ae9fe4"},"schema_version":"1.0","source":{"id":"2411.05500","kind":"arxiv","version":1}},"canonical_sha256":"7bd41ab60eb1c25371ad1bf3d48dc6100277cc2e45d4e7a927d41f4fb36359af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bd41ab60eb1c25371ad1bf3d48dc6100277cc2e45d4e7a927d41f4fb36359af","first_computed_at":"2026-07-05T09:33:02.106623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:02.106623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OBZQIEfrffRKw3Ta71LLcgxOuM5tlTSWKc1C4H3BCbqD430Eua21saVuJ+YlRDOlWTdy3v2jq5KgemHv5TfnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:02.107139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05500","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3957ce20fb1948c240440998b13ce39243d826708ff3478345fb8a5ca3dcd693","sha256:9570d5805c118f760a3fbe6775cc0c4d6f5dcd5c9c17ac8398600ae7159a2314"],"state_sha256":"f8be211024bed5945a1e698d52c2733bdeb1cb9700f56ec5fd6b488363d13f0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kVssgsx3SRzkTM//NoVvkyTOyf/IEAVT+fAotmEECOwtOdtmbDrrx2K8u8OkfMJOAGsdugLvc75HmMZP0YkBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T11:53:23.086234Z","bundle_sha256":"a83fcfbfe0f0458c0a2202a64c9b62862ae0ca2d6eedbadb1949f34d72aa9ed8"}}