{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZFAUWYSOATBH6OVTG7HTYZZUXM","short_pith_number":"pith:ZFAUWYSO","canonical_record":{"source":{"id":"2605.18331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T12:48:41Z","cross_cats_sorted":[],"title_canon_sha256":"b67ffd4d9f5297306d27e67200fdf8df7ee8d8f18f2c21462993a2fe5fd149fc","abstract_canon_sha256":"1f9bd2e6482c56c397bcc65f357eea60fb1ec833e64cd4aca6aaa8d068bc0a3d"},"schema_version":"1.0"},"canonical_sha256":"c9414b624e04c27f3ab337cf3c6734bb180128ee6b507bd781edaf3f60448ba6","source":{"kind":"arxiv","id":"2605.18331","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18331","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18331v1","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18331","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"ZFAUWYSOATBH","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZFAUWYSOATBH6OVT","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZFAUWYSO","created_at":"2026-05-20T00:05:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZFAUWYSOATBH6OVTG7HTYZZUXM","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T12:48:41Z","cross_cats_sorted":[],"title_canon_sha256":"b67ffd4d9f5297306d27e67200fdf8df7ee8d8f18f2c21462993a2fe5fd149fc","abstract_canon_sha256":"1f9bd2e6482c56c397bcc65f357eea60fb1ec833e64cd4aca6aaa8d068bc0a3d"},"schema_version":"1.0"},"canonical_sha256":"c9414b624e04c27f3ab337cf3c6734bb180128ee6b507bd781edaf3f60448ba6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:55.592849Z","signature_b64":"GSCXLtnJ3JpR8EqprMq5i/YybhRVDGGUD70DNUkot88OeJN8Nr9qfmoCTvM0r6gpczU7IFesoLToYwN5LknfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9414b624e04c27f3ab337cf3c6734bb180128ee6b507bd781edaf3f60448ba6","last_reissued_at":"2026-05-20T00:05:55.592220Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:55.592220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18331","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":"2026-05-20T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nM7muvGu+1KNT1Tia2MRlsZEEYI2RWjQt/6fyQIjEjExIHAjEQ9n54JZNa6BIS0JcESogPoTy20ek8+YTQIHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T06:23:15.227977Z"},"content_sha256":"c4e2594c465800be0a915710d00bb987a25d2a3a994291e7ca6a8022220b3257","schema_version":"1.0","event_id":"sha256:c4e2594c465800be0a915710d00bb987a25d2a3a994291e7ca6a8022220b3257"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZFAUWYSOATBH6OVTG7HTYZZUXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prune, Update and Trim: Robust Structured Pruning for Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Diego Coello de Portugal Mecke, Lars Schmidth-Thieme, Tom Hanika","submitted_at":"2026-05-18T12:48:41Z","abstract_excerpt":"Large Language Models (LLMs) have experienced significant growth and development in recent years. However, performing inference on LLMs remains costly, especially for long-context inference or in resource-constrained devices. This motivates the development of new post-training pruning (PTP) methods. These methods reduce LLMs' requirements by removing a substantial part of the model's parameters. The discarded weights are selected depending on their impact on the models performance. Current PTP methods prune the models by removing the less informative hidden nodes from the FFN layers, and the l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18331","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/2605.18331/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.175692Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.845072Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"38648810cf23f648bd947e06b36adfa06f5dd82fca9413ac2c50269e28d8fc91"},"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":"2026-05-20T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nEnGSzLcbLEI5vpT/g4mgTQsX3w/u35dG5uPo7pZKY5WYniJSlNf8mCFceh+n9RciQRM2rlvFahmzpjPOjdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T06:23:15.228738Z"},"content_sha256":"a450fae5b9affc9965ebb500f5d0ab58f2b025876943a03536cbaf91a427d965","schema_version":"1.0","event_id":"sha256:a450fae5b9affc9965ebb500f5d0ab58f2b025876943a03536cbaf91a427d965"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZFAUWYSOATBH6OVTG7HTYZZUXM/bundle.json","state_url":"https://pith.science/pith/ZFAUWYSOATBH6OVTG7HTYZZUXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZFAUWYSOATBH6OVTG7HTYZZUXM/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":"2026-05-24T06:23:15Z","links":{"resolver":"https://pith.science/pith/ZFAUWYSOATBH6OVTG7HTYZZUXM","bundle":"https://pith.science/pith/ZFAUWYSOATBH6OVTG7HTYZZUXM/bundle.json","state":"https://pith.science/pith/ZFAUWYSOATBH6OVTG7HTYZZUXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZFAUWYSOATBH6OVTG7HTYZZUXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZFAUWYSOATBH6OVTG7HTYZZUXM","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":"1f9bd2e6482c56c397bcc65f357eea60fb1ec833e64cd4aca6aaa8d068bc0a3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T12:48:41Z","title_canon_sha256":"b67ffd4d9f5297306d27e67200fdf8df7ee8d8f18f2c21462993a2fe5fd149fc"},"schema_version":"1.0","source":{"id":"2605.18331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18331","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18331v1","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18331","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"ZFAUWYSOATBH","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZFAUWYSOATBH6OVT","created_at":"2026-05-20T00:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZFAUWYSO","created_at":"2026-05-20T00:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:a450fae5b9affc9965ebb500f5d0ab58f2b025876943a03536cbaf91a427d965","target":"graph","created_at":"2026-05-20T00:05:55Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.175692Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.845072Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18331/integrity.json","findings":[],"snapshot_sha256":"38648810cf23f648bd947e06b36adfa06f5dd82fca9413ac2c50269e28d8fc91","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have experienced significant growth and development in recent years. However, performing inference on LLMs remains costly, especially for long-context inference or in resource-constrained devices. This motivates the development of new post-training pruning (PTP) methods. These methods reduce LLMs' requirements by removing a substantial part of the model's parameters. The discarded weights are selected depending on their impact on the models performance. Current PTP methods prune the models by removing the less informative hidden nodes from the FFN layers, and the l","authors_text":"Diego Coello de Portugal Mecke, Lars Schmidth-Thieme, Tom Hanika","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T12:48:41Z","title":"Prune, Update and Trim: Robust Structured Pruning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18331","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:c4e2594c465800be0a915710d00bb987a25d2a3a994291e7ca6a8022220b3257","target":"record","created_at":"2026-05-20T00:05:55Z","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":"1f9bd2e6482c56c397bcc65f357eea60fb1ec833e64cd4aca6aaa8d068bc0a3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T12:48:41Z","title_canon_sha256":"b67ffd4d9f5297306d27e67200fdf8df7ee8d8f18f2c21462993a2fe5fd149fc"},"schema_version":"1.0","source":{"id":"2605.18331","kind":"arxiv","version":1}},"canonical_sha256":"c9414b624e04c27f3ab337cf3c6734bb180128ee6b507bd781edaf3f60448ba6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9414b624e04c27f3ab337cf3c6734bb180128ee6b507bd781edaf3f60448ba6","first_computed_at":"2026-05-20T00:05:55.592220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:55.592220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GSCXLtnJ3JpR8EqprMq5i/YybhRVDGGUD70DNUkot88OeJN8Nr9qfmoCTvM0r6gpczU7IFesoLToYwN5LknfAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:55.592849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4e2594c465800be0a915710d00bb987a25d2a3a994291e7ca6a8022220b3257","sha256:a450fae5b9affc9965ebb500f5d0ab58f2b025876943a03536cbaf91a427d965"],"state_sha256":"745c6cd1c48950ed5e35f9ac218c6b30d4bc101201bc1c01e9a2937da6763357"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8eddjKDwE0WYFFSjY9Tdkw9G/B948bs4n6bNvFOg7AL0XP6UPsARizupEi2VvgVlwpsJ5BMA2rwHe8qFm3kBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T06:23:15.232520Z","bundle_sha256":"9324bdbc0b6f8fac9d372a58a9d3f75c28d666c47b5a6164d7d94fbb5a219c2b"}}