{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RHVEXAKNPXGMCBRQSRY7RMLMEW","short_pith_number":"pith:RHVEXAKN","canonical_record":{"source":{"id":"2503.07605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T17:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"ef3b5203449b3851306dd6e909fd62cec2c0942a95546fb304e6af67318134b0","abstract_canon_sha256":"60802ea380be57ab16d5e420d0e41380b448dd119512d64419f5513132bfc0c6"},"schema_version":"1.0"},"canonical_sha256":"89ea4b814d7dccc106309471f8b16c25b4b00bff4bec3436509c9fd75daa88b4","source":{"kind":"arxiv","id":"2503.07605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07605","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07605v1","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07605","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"pith_short_12","alias_value":"RHVEXAKNPXGM","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"pith_short_16","alias_value":"RHVEXAKNPXGMCBRQ","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"pith_short_8","alias_value":"RHVEXAKN","created_at":"2026-07-05T10:28:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RHVEXAKNPXGMCBRQSRY7RMLMEW","target":"record","payload":{"canonical_record":{"source":{"id":"2503.07605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T17:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"ef3b5203449b3851306dd6e909fd62cec2c0942a95546fb304e6af67318134b0","abstract_canon_sha256":"60802ea380be57ab16d5e420d0e41380b448dd119512d64419f5513132bfc0c6"},"schema_version":"1.0"},"canonical_sha256":"89ea4b814d7dccc106309471f8b16c25b4b00bff4bec3436509c9fd75daa88b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:08.029198Z","signature_b64":"9TS2Bj4IdF8tOjI/X2PAQ9uauA1GCl94HqHh/Vsj5xcIBGGTN3GbuvFXIzrsz9pkXcfaGRID/OMKwEfFkiZiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89ea4b814d7dccc106309471f8b16c25b4b00bff4bec3436509c9fd75daa88b4","last_reissued_at":"2026-07-05T10:28:08.028468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:08.028468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.07605","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":"2026-07-05T10:28:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YxWV+FVVOdSwj1oaFTGjigjmNJ7DwdtEg0o41jkl6eg+nC+7vaO2fGKoeLLvjhbNAzaImpHRF8TvX7Peyd+9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:18:57.325538Z"},"content_sha256":"b048105dc6dc4818f5942ee4659ddae365fba08052592ec30e83a8813c1dcc13","schema_version":"1.0","event_id":"sha256:b048105dc6dc4818f5942ee4659ddae365fba08052592ec30e83a8813c1dcc13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RHVEXAKNPXGMCBRQSRY7RMLMEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Tang, Feiyu Xiong, Hanyu Wang, Huayi Lai, Jiawei Yang, Jihao Zhao, Shichao Song, Simin Niu, Xun Liang, Zhiyu Li","submitted_at":"2025-03-10T17:59:03Z","abstract_excerpt":"Large Language Models have achieved remarkable success across various natural language processing tasks, yet their high computational cost during inference remains a major bottleneck. This paper introduces Sparse Expert Activation Pruning (SEAP), a training-free pruning method that selectively retains task-relevant parameters to reduce inference overhead. Inspired by the clustering patterns of hidden states and activations in LLMs, SEAP identifies task-specific expert activation patterns and prunes the model while preserving task performance and enhancing computational efficiency. Experimental"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07605","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/2503.07605/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":"2026-07-05T10:28:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wfq6xgyxe0/wFdg+7gf+Jd2k4v2kJj9ufHixwh+9xmWkEIaiwSBCZnCi2F4IaJTF7psFX/H4fKzR10ROhVGOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:18:57.325842Z"},"content_sha256":"819c598ded6909c1d8996325f4ed645033da612c5669f1a94b86af880650e7df","schema_version":"1.0","event_id":"sha256:819c598ded6909c1d8996325f4ed645033da612c5669f1a94b86af880650e7df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHVEXAKNPXGMCBRQSRY7RMLMEW/bundle.json","state_url":"https://pith.science/pith/RHVEXAKNPXGMCBRQSRY7RMLMEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHVEXAKNPXGMCBRQSRY7RMLMEW/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":"2026-07-31T14:18:57Z","links":{"resolver":"https://pith.science/pith/RHVEXAKNPXGMCBRQSRY7RMLMEW","bundle":"https://pith.science/pith/RHVEXAKNPXGMCBRQSRY7RMLMEW/bundle.json","state":"https://pith.science/pith/RHVEXAKNPXGMCBRQSRY7RMLMEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHVEXAKNPXGMCBRQSRY7RMLMEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RHVEXAKNPXGMCBRQSRY7RMLMEW","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":"60802ea380be57ab16d5e420d0e41380b448dd119512d64419f5513132bfc0c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T17:59:03Z","title_canon_sha256":"ef3b5203449b3851306dd6e909fd62cec2c0942a95546fb304e6af67318134b0"},"schema_version":"1.0","source":{"id":"2503.07605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07605","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07605v1","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07605","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"pith_short_12","alias_value":"RHVEXAKNPXGM","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"pith_short_16","alias_value":"RHVEXAKNPXGMCBRQ","created_at":"2026-07-05T10:28:08Z"},{"alias_kind":"pith_short_8","alias_value":"RHVEXAKN","created_at":"2026-07-05T10:28:08Z"}],"graph_snapshots":[{"event_id":"sha256:819c598ded6909c1d8996325f4ed645033da612c5669f1a94b86af880650e7df","target":"graph","created_at":"2026-07-05T10:28:08Z","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/2503.07605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models have achieved remarkable success across various natural language processing tasks, yet their high computational cost during inference remains a major bottleneck. This paper introduces Sparse Expert Activation Pruning (SEAP), a training-free pruning method that selectively retains task-relevant parameters to reduce inference overhead. Inspired by the clustering patterns of hidden states and activations in LLMs, SEAP identifies task-specific expert activation patterns and prunes the model while preserving task performance and enhancing computational efficiency. Experimental","authors_text":"Bo Tang, Feiyu Xiong, Hanyu Wang, Huayi Lai, Jiawei Yang, Jihao Zhao, Shichao Song, Simin Niu, Xun Liang, Zhiyu Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T17:59:03Z","title":"SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07605","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:b048105dc6dc4818f5942ee4659ddae365fba08052592ec30e83a8813c1dcc13","target":"record","created_at":"2026-07-05T10:28:08Z","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":"60802ea380be57ab16d5e420d0e41380b448dd119512d64419f5513132bfc0c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T17:59:03Z","title_canon_sha256":"ef3b5203449b3851306dd6e909fd62cec2c0942a95546fb304e6af67318134b0"},"schema_version":"1.0","source":{"id":"2503.07605","kind":"arxiv","version":1}},"canonical_sha256":"89ea4b814d7dccc106309471f8b16c25b4b00bff4bec3436509c9fd75daa88b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89ea4b814d7dccc106309471f8b16c25b4b00bff4bec3436509c9fd75daa88b4","first_computed_at":"2026-07-05T10:28:08.028468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:08.028468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9TS2Bj4IdF8tOjI/X2PAQ9uauA1GCl94HqHh/Vsj5xcIBGGTN3GbuvFXIzrsz9pkXcfaGRID/OMKwEfFkiZiCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:08.029198Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b048105dc6dc4818f5942ee4659ddae365fba08052592ec30e83a8813c1dcc13","sha256:819c598ded6909c1d8996325f4ed645033da612c5669f1a94b86af880650e7df"],"state_sha256":"b4da981d690c89e87889cacb68c5fac9db2197facbf6f96e2cba672dd8e30410"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oG1LowHFe64kLnuTV1SjTiSPM2MGwxGbRRcDVN+tyiW8h+1ahR5An3vAL3cscRTkq8TnMJuH7lUGqsBq39yRCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:18:57.327881Z","bundle_sha256":"9462350c1c031c56302cea22a26bd880d9b8949181631dda64f5b33c75034267"}}