{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5XMUBKD3LTWJP7AWMN6SZM6SPM","short_pith_number":"pith:5XMUBKD3","canonical_record":{"source":{"id":"2310.04361","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T16:34:51Z","cross_cats_sorted":[],"title_canon_sha256":"575a30a5386b6cf7231601c1bf432174dd62669319b08d81251fdd2cf9601f55","abstract_canon_sha256":"703763ffd6b25328f9a1ae142da281999862982897357dfab3cad98996734ff6"},"schema_version":"1.0"},"canonical_sha256":"edd940a87b5cec97fc16637d2cb3d27b335107bc1f58f55f327e65476c252eca","source":{"kind":"arxiv","id":"2310.04361","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04361","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04361v4","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04361","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"5XMUBKD3LTWJ","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"5XMUBKD3LTWJP7AW","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"5XMUBKD3","created_at":"2026-07-05T09:34:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5XMUBKD3LTWJP7AWMN6SZM6SPM","target":"record","payload":{"canonical_record":{"source":{"id":"2310.04361","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T16:34:51Z","cross_cats_sorted":[],"title_canon_sha256":"575a30a5386b6cf7231601c1bf432174dd62669319b08d81251fdd2cf9601f55","abstract_canon_sha256":"703763ffd6b25328f9a1ae142da281999862982897357dfab3cad98996734ff6"},"schema_version":"1.0"},"canonical_sha256":"edd940a87b5cec97fc16637d2cb3d27b335107bc1f58f55f327e65476c252eca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:09.953730Z","signature_b64":"plcKENVSd4PLY+UdvxiMyJHC2VUk0DaLUvsw/tnNz8EKpC5DAslXNwKmXhPhzsY0kn5Pzq+r5no0s60nkkWnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edd940a87b5cec97fc16637d2cb3d27b335107bc1f58f55f327e65476c252eca","last_reissued_at":"2026-07-05T09:34:09.953197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:09.953197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.04361","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vIjZWfXFVhgxbJWcGWuZgPoVQj24DUlfNz1A7lef3eM4Q0xfWEd/8ToTrBXZgWfEUzYfeJGT0ILk+k6l/xWNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:27:32.275637Z"},"content_sha256":"558e25366976e454b05e132845443d06b254224177b4d6491390f574c0ad599e","schema_version":"1.0","event_id":"sha256:558e25366976e454b05e132845443d06b254224177b4d6491390f574c0ad599e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5XMUBKD3LTWJP7AWMN6SZM6SPM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bartosz W\\'ojcik, Filip Szatkowski, Miko{\\l}aj Pi\\'orczy\\'nski, Simone Scardapane","submitted_at":"2023-10-06T16:34:51Z","abstract_excerpt":"Transformer models can face practical limitations due to their high computational requirements. At the same time, such models exhibit significant activation sparsity, which can be leveraged to reduce the inference cost by converting parts of the network into equivalent Mixture-of-Experts (MoE) layers. Despite the crucial role played by activation sparsity, its impact on this process remains unexplored. We demonstrate that the efficiency of the conversion can be significantly enhanced by a proper regularization of the activation sparsity of the base model. Moreover, motivated by the high varian"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04361","kind":"arxiv","version":4},"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/2310.04361/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":"2026-07-05T09:34:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GWEzB6BZO36wLgTvD+thIlZO1bOcEjijfHqmXkSJoXytMnB7IoBq0gCkJsiwGSxKD97CxxQfnm81PM+LHX72Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:27:32.276172Z"},"content_sha256":"ed9588e64b0542cce32d575a1e31d1fee168880ca19073849516633c3a76e634","schema_version":"1.0","event_id":"sha256:ed9588e64b0542cce32d575a1e31d1fee168880ca19073849516633c3a76e634"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XMUBKD3LTWJP7AWMN6SZM6SPM/bundle.json","state_url":"https://pith.science/pith/5XMUBKD3LTWJP7AWMN6SZM6SPM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XMUBKD3LTWJP7AWMN6SZM6SPM/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":"2026-08-11T14:27:32Z","links":{"resolver":"https://pith.science/pith/5XMUBKD3LTWJP7AWMN6SZM6SPM","bundle":"https://pith.science/pith/5XMUBKD3LTWJP7AWMN6SZM6SPM/bundle.json","state":"https://pith.science/pith/5XMUBKD3LTWJP7AWMN6SZM6SPM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XMUBKD3LTWJP7AWMN6SZM6SPM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5XMUBKD3LTWJP7AWMN6SZM6SPM","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":"703763ffd6b25328f9a1ae142da281999862982897357dfab3cad98996734ff6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T16:34:51Z","title_canon_sha256":"575a30a5386b6cf7231601c1bf432174dd62669319b08d81251fdd2cf9601f55"},"schema_version":"1.0","source":{"id":"2310.04361","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04361","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04361v4","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04361","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"pith_short_12","alias_value":"5XMUBKD3LTWJ","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"pith_short_16","alias_value":"5XMUBKD3LTWJP7AW","created_at":"2026-07-05T09:34:09Z"},{"alias_kind":"pith_short_8","alias_value":"5XMUBKD3","created_at":"2026-07-05T09:34:09Z"}],"graph_snapshots":[{"event_id":"sha256:ed9588e64b0542cce32d575a1e31d1fee168880ca19073849516633c3a76e634","target":"graph","created_at":"2026-07-05T09:34:09Z","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/2310.04361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer models can face practical limitations due to their high computational requirements. At the same time, such models exhibit significant activation sparsity, which can be leveraged to reduce the inference cost by converting parts of the network into equivalent Mixture-of-Experts (MoE) layers. Despite the crucial role played by activation sparsity, its impact on this process remains unexplored. We demonstrate that the efficiency of the conversion can be significantly enhanced by a proper regularization of the activation sparsity of the base model. Moreover, motivated by the high varian","authors_text":"Bartosz W\\'ojcik, Filip Szatkowski, Miko{\\l}aj Pi\\'orczy\\'nski, Simone Scardapane","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T16:34:51Z","title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.04361","kind":"arxiv","version":4},"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":"sha256:558e25366976e454b05e132845443d06b254224177b4d6491390f574c0ad599e","target":"record","created_at":"2026-07-05T09:34:09Z","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":"703763ffd6b25328f9a1ae142da281999862982897357dfab3cad98996734ff6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-06T16:34:51Z","title_canon_sha256":"575a30a5386b6cf7231601c1bf432174dd62669319b08d81251fdd2cf9601f55"},"schema_version":"1.0","source":{"id":"2310.04361","kind":"arxiv","version":4}},"canonical_sha256":"edd940a87b5cec97fc16637d2cb3d27b335107bc1f58f55f327e65476c252eca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edd940a87b5cec97fc16637d2cb3d27b335107bc1f58f55f327e65476c252eca","first_computed_at":"2026-07-05T09:34:09.953197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:09.953197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"plcKENVSd4PLY+UdvxiMyJHC2VUk0DaLUvsw/tnNz8EKpC5DAslXNwKmXhPhzsY0kn5Pzq+r5no0s60nkkWnCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:09.953730Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04361","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:558e25366976e454b05e132845443d06b254224177b4d6491390f574c0ad599e","sha256:ed9588e64b0542cce32d575a1e31d1fee168880ca19073849516633c3a76e634"],"state_sha256":"786362488df478d66fb69ea154b688b2f239b7c4ea11d38e10bcc6b734e73f38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZGyhUjcslfkYXyZ8zOXGQF7qpeZGeAg8FqQUs45tBImiwNxJGnucAn8k3hAuJyn1n+0pEw24qUFfXs/b/M1YAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:27:32.280666Z","bundle_sha256":"a4de3342d8f0a6452c4a920e025b20159ede01d76745f966e47ad2d1901ce3b4"}}