{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IEOJCCD7KLBMWWKPAQA5LOMR7T","short_pith_number":"pith:IEOJCCD7","canonical_record":{"source":{"id":"2401.06426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-12T07:43:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aca1dbbd5269e86c9f0cfe2bf7853daaa2d05a74ad9fa7d79d33107c21b196c3","abstract_canon_sha256":"05d732719ff4eb7db3922e5a5f53400ed0e7dbd04206154101a7cb92b5f8880f"},"schema_version":"1.0"},"canonical_sha256":"411c91087f52c2cb594f0401d5b991fcf8f34aa86e0054cb0137bd58976be4e9","source":{"kind":"arxiv","id":"2401.06426","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06426","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06426v1","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06426","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"IEOJCCD7KLBM","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"IEOJCCD7KLBMWWKP","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"IEOJCCD7","created_at":"2026-07-05T07:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IEOJCCD7KLBMWWKPAQA5LOMR7T","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-12T07:43:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aca1dbbd5269e86c9f0cfe2bf7853daaa2d05a74ad9fa7d79d33107c21b196c3","abstract_canon_sha256":"05d732719ff4eb7db3922e5a5f53400ed0e7dbd04206154101a7cb92b5f8880f"},"schema_version":"1.0"},"canonical_sha256":"411c91087f52c2cb594f0401d5b991fcf8f34aa86e0054cb0137bd58976be4e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:50.474441Z","signature_b64":"gtXu41zRE/2g+dlGjW1b9YtZMI22uIIfPmt9fDZb2fyj5Ouw1NrzLDQtVOYrwHQ+NOQf0n/I3Iv/C/bYTpt+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"411c91087f52c2cb594f0401d5b991fcf8f34aa86e0054cb0137bd58976be4e9","last_reissued_at":"2026-07-05T07:32:50.474075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:50.474075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06426","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":"2026-07-05T07:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QfWlYZo+r5HujSB2bCjSKiMvSh/zhTBuGsk8eJZhCOG/pJ8TisMTKiRjyhuI5RyovRG5j6YWIN70X1r+0r3PAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:19:24.983704Z"},"content_sha256":"be356273e6b1893cdc4f26cf84f47966a1acacb2b211e95160d32216db328d38","schema_version":"1.0","event_id":"sha256:be356273e6b1893cdc4f26cf84f47966a1acacb2b211e95160d32216db328d38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IEOJCCD7KLBMWWKPAQA5LOMR7T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ashish Sirasao, Dehua Tang, Dong Li, Fan Jiang, Ji Liu, Jinzhang Peng, Li Zhang, Lu Tian, Mingjie Lu, Xiaocheng Zeng, Yuanxian Huang, Yu Wang","submitted_at":"2024-01-12T07:43:48Z","abstract_excerpt":"Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain efficient modules, such as popular inverted residual blocks. Prior depth pruning methods by reducing network depths are not suitable for pruning some efficient models due to the existence of some normalization layers. Moreover, finetuning subnet by directly removing activation layers would corrupt the original model weights, hindering the pruned model from achieving high performance. To address these issues, we propose a novel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06426","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/2401.06426/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":"2026-07-05T07:32:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EH5g7K/TYBn7OCsTaRUEfYDDYyVbU/4dXOBgVaifIlOKkjaqwxJ7pn71/mn/8deRN8rPVqlM/th0vNcogdxWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T23:19:24.984215Z"},"content_sha256":"d2cfa99ba6b3166370669fb23775b0e49b26f7be73e290e9bd71f70ac4a7bd07","schema_version":"1.0","event_id":"sha256:d2cfa99ba6b3166370669fb23775b0e49b26f7be73e290e9bd71f70ac4a7bd07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEOJCCD7KLBMWWKPAQA5LOMR7T/bundle.json","state_url":"https://pith.science/pith/IEOJCCD7KLBMWWKPAQA5LOMR7T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEOJCCD7KLBMWWKPAQA5LOMR7T/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":"2026-08-15T23:19:24Z","links":{"resolver":"https://pith.science/pith/IEOJCCD7KLBMWWKPAQA5LOMR7T","bundle":"https://pith.science/pith/IEOJCCD7KLBMWWKPAQA5LOMR7T/bundle.json","state":"https://pith.science/pith/IEOJCCD7KLBMWWKPAQA5LOMR7T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEOJCCD7KLBMWWKPAQA5LOMR7T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IEOJCCD7KLBMWWKPAQA5LOMR7T","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":"05d732719ff4eb7db3922e5a5f53400ed0e7dbd04206154101a7cb92b5f8880f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-12T07:43:48Z","title_canon_sha256":"aca1dbbd5269e86c9f0cfe2bf7853daaa2d05a74ad9fa7d79d33107c21b196c3"},"schema_version":"1.0","source":{"id":"2401.06426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06426","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06426v1","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06426","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"pith_short_12","alias_value":"IEOJCCD7KLBM","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"IEOJCCD7KLBMWWKP","created_at":"2026-07-05T07:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"IEOJCCD7","created_at":"2026-07-05T07:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:d2cfa99ba6b3166370669fb23775b0e49b26f7be73e290e9bd71f70ac4a7bd07","target":"graph","created_at":"2026-07-05T07:32:50Z","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/2401.06426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional channel-wise pruning methods by reducing network channels struggle to effectively prune efficient CNN models with depth-wise convolutional layers and certain efficient modules, such as popular inverted residual blocks. Prior depth pruning methods by reducing network depths are not suitable for pruning some efficient models due to the existence of some normalization layers. Moreover, finetuning subnet by directly removing activation layers would corrupt the original model weights, hindering the pruned model from achieving high performance. To address these issues, we propose a novel","authors_text":"Ashish Sirasao, Dehua Tang, Dong Li, Fan Jiang, Ji Liu, Jinzhang Peng, Li Zhang, Lu Tian, Mingjie Lu, Xiaocheng Zeng, Yuanxian Huang, Yu Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-12T07:43:48Z","title":"UPDP: A Unified Progressive Depth Pruner for CNN and Vision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06426","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:be356273e6b1893cdc4f26cf84f47966a1acacb2b211e95160d32216db328d38","target":"record","created_at":"2026-07-05T07:32:50Z","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":"05d732719ff4eb7db3922e5a5f53400ed0e7dbd04206154101a7cb92b5f8880f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-12T07:43:48Z","title_canon_sha256":"aca1dbbd5269e86c9f0cfe2bf7853daaa2d05a74ad9fa7d79d33107c21b196c3"},"schema_version":"1.0","source":{"id":"2401.06426","kind":"arxiv","version":1}},"canonical_sha256":"411c91087f52c2cb594f0401d5b991fcf8f34aa86e0054cb0137bd58976be4e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"411c91087f52c2cb594f0401d5b991fcf8f34aa86e0054cb0137bd58976be4e9","first_computed_at":"2026-07-05T07:32:50.474075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:50.474075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gtXu41zRE/2g+dlGjW1b9YtZMI22uIIfPmt9fDZb2fyj5Ouw1NrzLDQtVOYrwHQ+NOQf0n/I3Iv/C/bYTpt+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:50.474441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be356273e6b1893cdc4f26cf84f47966a1acacb2b211e95160d32216db328d38","sha256:d2cfa99ba6b3166370669fb23775b0e49b26f7be73e290e9bd71f70ac4a7bd07"],"state_sha256":"4edd80390b621a9ddd5530079d5cf19383f02607c0e076f9deed1338550240fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AneuC8lR7uUcAMicK/NyQj8Zopjw+BLIghE/Q+EkjhARkV7Kj7gos6YiHP9E+0KO+Sieu79VD/0VmdikvuZKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T23:19:24.987725Z","bundle_sha256":"c42339ae25389f4026d54f23f7e36df2d0ab26d64859d37fb68a44664684d3ec"}}