{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NGJ7XE6AFRHOADZJJ3FTSKBU52","short_pith_number":"pith:NGJ7XE6A","canonical_record":{"source":{"id":"2408.12568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T17:35:18Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"b3cdf1e1fed8fefd3c35293073bab2cc0340fbb2848c1e52beb612f07678bd7b","abstract_canon_sha256":"109faf766855c5a4b70eed813e108b02b273bc32b2b26b664ddaebd5863203b5"},"schema_version":"1.0"},"canonical_sha256":"6993fb93c02c4ee00f294ecb392834eebf25d20ebf8c12199c95429a6df8b126","source":{"kind":"arxiv","id":"2408.12568","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12568","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12568v2","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12568","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_12","alias_value":"NGJ7XE6AFRHO","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_16","alias_value":"NGJ7XE6AFRHOADZJ","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_8","alias_value":"NGJ7XE6A","created_at":"2026-07-05T09:24:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NGJ7XE6AFRHOADZJJ3FTSKBU52","target":"record","payload":{"canonical_record":{"source":{"id":"2408.12568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T17:35:18Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"b3cdf1e1fed8fefd3c35293073bab2cc0340fbb2848c1e52beb612f07678bd7b","abstract_canon_sha256":"109faf766855c5a4b70eed813e108b02b273bc32b2b26b664ddaebd5863203b5"},"schema_version":"1.0"},"canonical_sha256":"6993fb93c02c4ee00f294ecb392834eebf25d20ebf8c12199c95429a6df8b126","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:37.920375Z","signature_b64":"2sigjwiy+eNT7ajZXi2JpFYUALVwTS+efPqfwRuzTh2vNrwwoqzxRfFL0ffRVDWOxQDpPA4BAl11b9P6misWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6993fb93c02c4ee00f294ecb392834eebf25d20ebf8c12199c95429a6df8b126","last_reissued_at":"2026-07-05T09:24:37.919865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:37.919865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.12568","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":"2026-07-05T09:24:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XgTy/xir4FgUESqLiGThsIR/XkulP81q/pfQH4tmAWmiB9UAbmfhE46cpSE8edTpLBugpKWIXnIKozjjsCeUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T15:34:01.846196Z"},"content_sha256":"a417daa7c80011c6ca5d51364ba8bb7f63db2216d7684507788d128b965aead8","schema_version":"1.0","event_id":"sha256:a417daa7c80011c6ca5d51364ba8bb7f63db2216d7684507788d128b965aead8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NGJ7XE6AFRHOADZJJ3FTSKBU52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Maximilian Dreyer, Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Sebastian Lapuschkin, Thomas Wiegand, Wojciech Samek","submitted_at":"2024-08-22T17:35:18Z","abstract_excerpt":"To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary components of these often over-parameterized networks. Previous work has shown that attribution methods from the field of eXplainable AI serve as effective means to extract and prune the least relevant network components in a few-shot fashion. We extend the current state by proposing to explicitly optimize hyperparameters of attribution methods for the task "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12568","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/2408.12568/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":"2026-07-05T09:24:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"koslGudklf4frbZUbjwOEky/U+HUzUcfRfLN6TCSr41IhipoY+O1nZMaYkgkL3c86iWat2ggol3EouVCDwAsAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T15:34:01.846597Z"},"content_sha256":"8e5ec0ec6512a480cda4876167b7d7aad3e845cdd5b9e45fa3758379f45197f7","schema_version":"1.0","event_id":"sha256:8e5ec0ec6512a480cda4876167b7d7aad3e845cdd5b9e45fa3758379f45197f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NGJ7XE6AFRHOADZJJ3FTSKBU52/bundle.json","state_url":"https://pith.science/pith/NGJ7XE6AFRHOADZJJ3FTSKBU52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NGJ7XE6AFRHOADZJJ3FTSKBU52/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":"2026-07-13T15:34:01Z","links":{"resolver":"https://pith.science/pith/NGJ7XE6AFRHOADZJJ3FTSKBU52","bundle":"https://pith.science/pith/NGJ7XE6AFRHOADZJJ3FTSKBU52/bundle.json","state":"https://pith.science/pith/NGJ7XE6AFRHOADZJJ3FTSKBU52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NGJ7XE6AFRHOADZJJ3FTSKBU52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NGJ7XE6AFRHOADZJJ3FTSKBU52","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":"109faf766855c5a4b70eed813e108b02b273bc32b2b26b664ddaebd5863203b5","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T17:35:18Z","title_canon_sha256":"b3cdf1e1fed8fefd3c35293073bab2cc0340fbb2848c1e52beb612f07678bd7b"},"schema_version":"1.0","source":{"id":"2408.12568","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12568","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12568v2","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12568","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_12","alias_value":"NGJ7XE6AFRHO","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_16","alias_value":"NGJ7XE6AFRHOADZJ","created_at":"2026-07-05T09:24:37Z"},{"alias_kind":"pith_short_8","alias_value":"NGJ7XE6A","created_at":"2026-07-05T09:24:37Z"}],"graph_snapshots":[{"event_id":"sha256:8e5ec0ec6512a480cda4876167b7d7aad3e845cdd5b9e45fa3758379f45197f7","target":"graph","created_at":"2026-07-05T09:24:37Z","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/2408.12568/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary components of these often over-parameterized networks. Previous work has shown that attribution methods from the field of eXplainable AI serve as effective means to extract and prune the least relevant network components in a few-shot fashion. We extend the current state by proposing to explicitly optimize hyperparameters of attribution methods for the task ","authors_text":"Maximilian Dreyer, Reduan Achtibat, Sayed Mohammad Vakilzadeh Hatefi, Sebastian Lapuschkin, Thomas Wiegand, Wojciech Samek","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T17:35:18Z","title":"Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12568","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:a417daa7c80011c6ca5d51364ba8bb7f63db2216d7684507788d128b965aead8","target":"record","created_at":"2026-07-05T09:24:37Z","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":"109faf766855c5a4b70eed813e108b02b273bc32b2b26b664ddaebd5863203b5","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T17:35:18Z","title_canon_sha256":"b3cdf1e1fed8fefd3c35293073bab2cc0340fbb2848c1e52beb612f07678bd7b"},"schema_version":"1.0","source":{"id":"2408.12568","kind":"arxiv","version":2}},"canonical_sha256":"6993fb93c02c4ee00f294ecb392834eebf25d20ebf8c12199c95429a6df8b126","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6993fb93c02c4ee00f294ecb392834eebf25d20ebf8c12199c95429a6df8b126","first_computed_at":"2026-07-05T09:24:37.919865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:37.919865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2sigjwiy+eNT7ajZXi2JpFYUALVwTS+efPqfwRuzTh2vNrwwoqzxRfFL0ffRVDWOxQDpPA4BAl11b9P6misWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:37.920375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12568","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a417daa7c80011c6ca5d51364ba8bb7f63db2216d7684507788d128b965aead8","sha256:8e5ec0ec6512a480cda4876167b7d7aad3e845cdd5b9e45fa3758379f45197f7"],"state_sha256":"81e18be3f61cffd2b622349e6161923c5cf9835072d0c8339cb232c5014ea16b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xGzgUEGOy1kWr/1hTLNe8vMJ8o8Fuuo8McxFOeZNfxB8s97zAYcZCc2tPaC3ygBw3I6wsBXCqQkeIa4HFpZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T15:34:01.848803Z","bundle_sha256":"ace79be0adda8e25dfddd3cb44ad68dc0011eba8ddb8d24bdee51881df28269b"}}