{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CESHLE64IOJTBNEFGWFIXDIJ2X","short_pith_number":"pith:CESHLE64","canonical_record":{"source":{"id":"2411.16901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T20:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"23f70c860ed4d4a38923adec139692a2eefde9e4f1ab2098ca16cd684c3caa9f","abstract_canon_sha256":"5b05840cf9d6067099ea09faaec417d83ff8ff3b79078537993a2e30b4aa1fdd"},"schema_version":"1.0"},"canonical_sha256":"11247593dc439330b485358a8b8d09d5c02df9a61387a15ec14a7806b51a7246","source":{"kind":"arxiv","id":"2411.16901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16901","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16901v1","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16901","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"CESHLE64IOJT","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"CESHLE64IOJTBNEF","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"CESHLE64","created_at":"2026-07-05T10:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CESHLE64IOJTBNEFGWFIXDIJ2X","target":"record","payload":{"canonical_record":{"source":{"id":"2411.16901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T20:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"23f70c860ed4d4a38923adec139692a2eefde9e4f1ab2098ca16cd684c3caa9f","abstract_canon_sha256":"5b05840cf9d6067099ea09faaec417d83ff8ff3b79078537993a2e30b4aa1fdd"},"schema_version":"1.0"},"canonical_sha256":"11247593dc439330b485358a8b8d09d5c02df9a61387a15ec14a7806b51a7246","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:27.052869Z","signature_b64":"ovhB12B2KFnNsF1axNLgjfik6nahBiT7fePpyHFUETCEtavWWj3EDnphqEFXjqDdR8qKpg17QHIdiVySq0rdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11247593dc439330b485358a8b8d09d5c02df9a61387a15ec14a7806b51a7246","last_reissued_at":"2026-07-05T10:29:27.052272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:27.052272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.16901","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":"2026-07-05T10:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VBL2hTrmuJlzwhVL07hViKzphVT5VtSxFMt8HsFTY+92KOEnhZ/tCPt0Nl8fEKl1yEso0hyRMM6NtulDBUVrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:43:00.073536Z"},"content_sha256":"65eb4d42ea0c6386d391d0a5cdb2fa85c18ca39eb826bf99cdd22a1c7aae4e53","schema_version":"1.0","event_id":"sha256:65eb4d42ea0c6386d391d0a5cdb2fa85c18ca39eb826bf99cdd22a1c7aae4e53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CESHLE64IOJTBNEFGWFIXDIJ2X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Convolutional Neural Networks Structured Pruning via Gravity Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdesselam Ferdi","submitted_at":"2024-11-25T20:10:10Z","abstract_excerpt":"Structured pruning is a widely employed strategy for accelerating deep convolutional neural networks (DCNNs). However, existing methods often necessitate modifications to the original architectures, involve complex implementations, and require lengthy fine-tuning stages. To address these challenges, we propose a novel physics-inspired approach that integrates the concept of gravity into the training stage of DCNNs. In this approach, the gravity is directly proportional to the product of the masses of the convolution filter and the attracting filter, and inversely proportional to the square of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16901","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/2411.16901/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":"2026-07-05T10:29:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7X+LE+0m28md7vWDYVh4EvbBzNJTu+ym2zxKH6QmdVR2u7jpXf1lh8trRICXG+GABJC5IFpo5thdlIvwSqTpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:43:00.074079Z"},"content_sha256":"7ba7ae74a0704456183bd226b983b512425d085216c1806e20168b15ac83b3bb","schema_version":"1.0","event_id":"sha256:7ba7ae74a0704456183bd226b983b512425d085216c1806e20168b15ac83b3bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CESHLE64IOJTBNEFGWFIXDIJ2X/bundle.json","state_url":"https://pith.science/pith/CESHLE64IOJTBNEFGWFIXDIJ2X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CESHLE64IOJTBNEFGWFIXDIJ2X/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":"2026-08-13T02:43:00Z","links":{"resolver":"https://pith.science/pith/CESHLE64IOJTBNEFGWFIXDIJ2X","bundle":"https://pith.science/pith/CESHLE64IOJTBNEFGWFIXDIJ2X/bundle.json","state":"https://pith.science/pith/CESHLE64IOJTBNEFGWFIXDIJ2X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CESHLE64IOJTBNEFGWFIXDIJ2X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CESHLE64IOJTBNEFGWFIXDIJ2X","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":"5b05840cf9d6067099ea09faaec417d83ff8ff3b79078537993a2e30b4aa1fdd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T20:10:10Z","title_canon_sha256":"23f70c860ed4d4a38923adec139692a2eefde9e4f1ab2098ca16cd684c3caa9f"},"schema_version":"1.0","source":{"id":"2411.16901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16901","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16901v1","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16901","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"pith_short_12","alias_value":"CESHLE64IOJT","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"CESHLE64IOJTBNEF","created_at":"2026-07-05T10:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"CESHLE64","created_at":"2026-07-05T10:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:7ba7ae74a0704456183bd226b983b512425d085216c1806e20168b15ac83b3bb","target":"graph","created_at":"2026-07-05T10:29:27Z","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/2411.16901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Structured pruning is a widely employed strategy for accelerating deep convolutional neural networks (DCNNs). However, existing methods often necessitate modifications to the original architectures, involve complex implementations, and require lengthy fine-tuning stages. To address these challenges, we propose a novel physics-inspired approach that integrates the concept of gravity into the training stage of DCNNs. In this approach, the gravity is directly proportional to the product of the masses of the convolution filter and the attracting filter, and inversely proportional to the square of ","authors_text":"Abdesselam Ferdi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T20:10:10Z","title":"Deep Convolutional Neural Networks Structured Pruning via Gravity Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16901","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":"sha256:65eb4d42ea0c6386d391d0a5cdb2fa85c18ca39eb826bf99cdd22a1c7aae4e53","target":"record","created_at":"2026-07-05T10:29:27Z","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":"5b05840cf9d6067099ea09faaec417d83ff8ff3b79078537993a2e30b4aa1fdd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T20:10:10Z","title_canon_sha256":"23f70c860ed4d4a38923adec139692a2eefde9e4f1ab2098ca16cd684c3caa9f"},"schema_version":"1.0","source":{"id":"2411.16901","kind":"arxiv","version":1}},"canonical_sha256":"11247593dc439330b485358a8b8d09d5c02df9a61387a15ec14a7806b51a7246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11247593dc439330b485358a8b8d09d5c02df9a61387a15ec14a7806b51a7246","first_computed_at":"2026-07-05T10:29:27.052272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:27.052272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ovhB12B2KFnNsF1axNLgjfik6nahBiT7fePpyHFUETCEtavWWj3EDnphqEFXjqDdR8qKpg17QHIdiVySq0rdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:27.052869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65eb4d42ea0c6386d391d0a5cdb2fa85c18ca39eb826bf99cdd22a1c7aae4e53","sha256:7ba7ae74a0704456183bd226b983b512425d085216c1806e20168b15ac83b3bb"],"state_sha256":"cbe85461c0a6fc8c2c59eb55357bdee9c7bfeaa2c1ae2ae287d3c6403ee336a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5Mi/8KpwY2L2A388GnLB/ytJQHtBWng9e2sTSyBYJbWWktzcNxr6FKPodO11OCBkwBcuPQvFXbW4DSEI1CKBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T02:43:00.079841Z","bundle_sha256":"b7b549334acb8f2b387f473312a4c4fdeb3daab7c21c375a46a7b78db1fcea31"}}