{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SZT5PNUG2GUH24PVFCXH2DDJNR","short_pith_number":"pith:SZT5PNUG","canonical_record":{"source":{"id":"2404.05089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-07T22:13:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb1aee6de10223fbced50d477256e7a596bce504306184361f8c0f3092631b58","abstract_canon_sha256":"2ff4c4e46f8f72da863f9c466485d8775ddb2c5bfc817179c4562c4d9883e152"},"schema_version":"1.0"},"canonical_sha256":"9667d7b686d1a87d71f528ae7d0c696c5f49e28ca8225c345fdffdeb79f634aa","source":{"kind":"arxiv","id":"2404.05089","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05089","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05089v1","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05089","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"SZT5PNUG2GUH","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"SZT5PNUG2GUH24PV","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"SZT5PNUG","created_at":"2026-07-05T08:05:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SZT5PNUG2GUH24PVFCXH2DDJNR","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-07T22:13:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bb1aee6de10223fbced50d477256e7a596bce504306184361f8c0f3092631b58","abstract_canon_sha256":"2ff4c4e46f8f72da863f9c466485d8775ddb2c5bfc817179c4562c4d9883e152"},"schema_version":"1.0"},"canonical_sha256":"9667d7b686d1a87d71f528ae7d0c696c5f49e28ca8225c345fdffdeb79f634aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:25.980601Z","signature_b64":"q0xbwiP3m70LtA9dhhNrWTLYK59hStG+aFE4Nf+kU9+YRk03WUzolsTvA75O4WAyNL/FITxZYIzi4KKq3fH1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9667d7b686d1a87d71f528ae7d0c696c5f49e28ca8225c345fdffdeb79f634aa","last_reissued_at":"2026-07-05T08:05:25.980111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:25.980111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05089","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":"2026-07-05T08:05:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O3xjasNJ72pz3J7UjSogKML3JvkN4lZ00xzS/ZaLJNvqfdH2YVTXilqA67P1lRw7xRD/4BO5wJ9GwPL0BETfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:55:29.997158Z"},"content_sha256":"15b9b70aa44df52051f004babb84088047114d9e90437208150b615e083c2420","schema_version":"1.0","event_id":"sha256:15b9b70aa44df52051f004babb84088047114d9e90437208150b615e083c2420"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SZT5PNUG2GUH24PVFCXH2DDJNR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexandre Muzio, Alex Sun, Churan He","submitted_at":"2024-04-07T22:13:43Z","abstract_excerpt":"The advancement of deep learning has led to the emergence of Mixture-of-Experts (MoEs) models, known for their dynamic allocation of computational resources based on input. Despite their promise, MoEs face challenges, particularly in terms of memory requirements. To address this, our work introduces SEER-MoE, a novel two-stage framework for reducing both the memory footprint and compute requirements of pre-trained MoE models. The first stage involves pruning the total number of experts using a heavy-hitters counting guidance, while the second stage employs a regularization-based fine-tuning st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05089","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/2404.05089/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":"2026-07-05T08:05:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"47URIoZG4rAL2P4y0LY0fNGz7f7jSe2hYZbg/kMhoXB9d9r/H+xKc1uZwRawbLyK667maHdL7mPVXcSlbkInAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:55:29.997772Z"},"content_sha256":"3f54c317c23d6efe477c54c81ee32b19984fccb614ab14ff1ddfca0c1dff57a7","schema_version":"1.0","event_id":"sha256:3f54c317c23d6efe477c54c81ee32b19984fccb614ab14ff1ddfca0c1dff57a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZT5PNUG2GUH24PVFCXH2DDJNR/bundle.json","state_url":"https://pith.science/pith/SZT5PNUG2GUH24PVFCXH2DDJNR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZT5PNUG2GUH24PVFCXH2DDJNR/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":"2026-08-21T21:55:30Z","links":{"resolver":"https://pith.science/pith/SZT5PNUG2GUH24PVFCXH2DDJNR","bundle":"https://pith.science/pith/SZT5PNUG2GUH24PVFCXH2DDJNR/bundle.json","state":"https://pith.science/pith/SZT5PNUG2GUH24PVFCXH2DDJNR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZT5PNUG2GUH24PVFCXH2DDJNR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SZT5PNUG2GUH24PVFCXH2DDJNR","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":"2ff4c4e46f8f72da863f9c466485d8775ddb2c5bfc817179c4562c4d9883e152","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-07T22:13:43Z","title_canon_sha256":"bb1aee6de10223fbced50d477256e7a596bce504306184361f8c0f3092631b58"},"schema_version":"1.0","source":{"id":"2404.05089","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05089","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05089v1","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05089","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"SZT5PNUG2GUH","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"SZT5PNUG2GUH24PV","created_at":"2026-07-05T08:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"SZT5PNUG","created_at":"2026-07-05T08:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:3f54c317c23d6efe477c54c81ee32b19984fccb614ab14ff1ddfca0c1dff57a7","target":"graph","created_at":"2026-07-05T08:05:25Z","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/2404.05089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of deep learning has led to the emergence of Mixture-of-Experts (MoEs) models, known for their dynamic allocation of computational resources based on input. Despite their promise, MoEs face challenges, particularly in terms of memory requirements. To address this, our work introduces SEER-MoE, a novel two-stage framework for reducing both the memory footprint and compute requirements of pre-trained MoE models. The first stage involves pruning the total number of experts using a heavy-hitters counting guidance, while the second stage employs a regularization-based fine-tuning st","authors_text":"Alexandre Muzio, Alex Sun, Churan He","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-07T22:13:43Z","title":"SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05089","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":"sha256:15b9b70aa44df52051f004babb84088047114d9e90437208150b615e083c2420","target":"record","created_at":"2026-07-05T08:05:25Z","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":"2ff4c4e46f8f72da863f9c466485d8775ddb2c5bfc817179c4562c4d9883e152","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-07T22:13:43Z","title_canon_sha256":"bb1aee6de10223fbced50d477256e7a596bce504306184361f8c0f3092631b58"},"schema_version":"1.0","source":{"id":"2404.05089","kind":"arxiv","version":1}},"canonical_sha256":"9667d7b686d1a87d71f528ae7d0c696c5f49e28ca8225c345fdffdeb79f634aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9667d7b686d1a87d71f528ae7d0c696c5f49e28ca8225c345fdffdeb79f634aa","first_computed_at":"2026-07-05T08:05:25.980111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:25.980111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q0xbwiP3m70LtA9dhhNrWTLYK59hStG+aFE4Nf+kU9+YRk03WUzolsTvA75O4WAyNL/FITxZYIzi4KKq3fH1Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:25.980601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05089","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15b9b70aa44df52051f004babb84088047114d9e90437208150b615e083c2420","sha256:3f54c317c23d6efe477c54c81ee32b19984fccb614ab14ff1ddfca0c1dff57a7"],"state_sha256":"4a1a7ab59fc028da4784a53f47083c47fca7d056c96ee9529196d4f687f76d34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TVcKH7JJWKugdJ/6v3PNEghqZz1lE1jhGVJoXuYC3iCCCUCrC+BOUv+AY8qzn5PkU70ZwITUkjPqQh9PuXRcCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:55:30.003601Z","bundle_sha256":"febef240206b4d5bbf93f6fd824006bea21f085a01900696f97f12d49f15780b"}}