{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WI56GZTLLTRVEEHEL4ECOM43NK","short_pith_number":"pith:WI56GZTL","canonical_record":{"source":{"id":"2509.14230","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-17T17:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"72c797d3cd16c348d5407e88aa035f33b4c6110766ba72b75593029fb8fcc39b","abstract_canon_sha256":"9ee92e8621f44c685751c871b23863e21a7d9c856494a5b9584d19f143f70eaf"},"schema_version":"1.0"},"canonical_sha256":"b23be3666b5ce35210e45f0827339b6a88ed6894749a688332b40d1964d3a58a","source":{"kind":"arxiv","id":"2509.14230","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.14230","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.14230v2","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.14230","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"WI56GZTLLTRV","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"WI56GZTLLTRVEEHE","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"WI56GZTL","created_at":"2026-07-21T01:20:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WI56GZTLLTRVEEHEL4ECOM43NK","target":"record","payload":{"canonical_record":{"source":{"id":"2509.14230","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-17T17:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"72c797d3cd16c348d5407e88aa035f33b4c6110766ba72b75593029fb8fcc39b","abstract_canon_sha256":"9ee92e8621f44c685751c871b23863e21a7d9c856494a5b9584d19f143f70eaf"},"schema_version":"1.0"},"canonical_sha256":"b23be3666b5ce35210e45f0827339b6a88ed6894749a688332b40d1964d3a58a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:37.145274Z","signature_b64":"V/L1zfEwgZjAEjYoe5FwwF9SSPO4LYHeLvuue+jWp5Cbd6TQAdzv8wefUBjk7QF1wB5yti2ixtRpty8JE+doCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b23be3666b5ce35210e45f0827339b6a88ed6894749a688332b40d1964d3a58a","last_reissued_at":"2026-07-21T01:20:37.144251Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:37.144251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.14230","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":"2026-07-21T01:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z52oIQY/0uTITDXvU0/aOCQCx1MJJLCIffMtantFCPpQASUrVtbheKMi3BnqZyLmt5Nh5y4wT985LX4PJUsECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:08:28.503440Z"},"content_sha256":"82df87c853ed59ce7445585ea13dcb63b6b28a3fa550da7cabd57e2dc893c5d6","schema_version":"1.0","event_id":"sha256:82df87c853ed59ce7445585ea13dcb63b6b28a3fa550da7cabd57e2dc893c5d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WI56GZTLLTRVEEHEL4ECOM43NK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NIRVANA: Structured Pruning Reimagined for Large Language Model Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingrui He, Mengting Ai, Sirui Chen, Tianxin Wei","submitted_at":"2025-09-17T17:59:00Z","abstract_excerpt":"While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance degradation and demand computationally retraining to recover capabilities. To overcome these barriers, we present NIRVANA, a novel, hardware-aware structured pruning framework designed to preserve both zero-shot performance and the optimization landscape for downstream fine-tuning. Departing from traditional loss-based heuristics, our approach evaluates structural importance through a first-order function-space salie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.14230","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/2509.14230/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":"2026-07-21T01:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pilqquFdiyPphSPG9bO+NWq94z3eJ4fS8eb9wp2j1tfTYrFWnMstVqCvK3dMzTB4VVEi/AOsCiZjwmW+z2QTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:08:28.503932Z"},"content_sha256":"5caca5b65d3afb77c4686cf133ebb35b84d70dfdec9c5fbcbb1fac191ae5c69e","schema_version":"1.0","event_id":"sha256:5caca5b65d3afb77c4686cf133ebb35b84d70dfdec9c5fbcbb1fac191ae5c69e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WI56GZTLLTRVEEHEL4ECOM43NK/bundle.json","state_url":"https://pith.science/pith/WI56GZTLLTRVEEHEL4ECOM43NK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WI56GZTLLTRVEEHEL4ECOM43NK/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":"2026-08-04T05:08:28Z","links":{"resolver":"https://pith.science/pith/WI56GZTLLTRVEEHEL4ECOM43NK","bundle":"https://pith.science/pith/WI56GZTLLTRVEEHEL4ECOM43NK/bundle.json","state":"https://pith.science/pith/WI56GZTLLTRVEEHEL4ECOM43NK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WI56GZTLLTRVEEHEL4ECOM43NK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WI56GZTLLTRVEEHEL4ECOM43NK","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":"9ee92e8621f44c685751c871b23863e21a7d9c856494a5b9584d19f143f70eaf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-17T17:59:00Z","title_canon_sha256":"72c797d3cd16c348d5407e88aa035f33b4c6110766ba72b75593029fb8fcc39b"},"schema_version":"1.0","source":{"id":"2509.14230","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.14230","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2509.14230v2","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.14230","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"WI56GZTLLTRV","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"WI56GZTLLTRVEEHE","created_at":"2026-07-21T01:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"WI56GZTL","created_at":"2026-07-21T01:20:37Z"}],"graph_snapshots":[{"event_id":"sha256:5caca5b65d3afb77c4686cf133ebb35b84d70dfdec9c5fbcbb1fac191ae5c69e","target":"graph","created_at":"2026-07-21T01:20:37Z","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/2509.14230/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance degradation and demand computationally retraining to recover capabilities. To overcome these barriers, we present NIRVANA, a novel, hardware-aware structured pruning framework designed to preserve both zero-shot performance and the optimization landscape for downstream fine-tuning. Departing from traditional loss-based heuristics, our approach evaluates structural importance through a first-order function-space salie","authors_text":"Jingrui He, Mengting Ai, Sirui Chen, Tianxin Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-17T17:59:00Z","title":"NIRVANA: Structured Pruning Reimagined for Large Language Model Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.14230","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":"sha256:82df87c853ed59ce7445585ea13dcb63b6b28a3fa550da7cabd57e2dc893c5d6","target":"record","created_at":"2026-07-21T01:20:37Z","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":"9ee92e8621f44c685751c871b23863e21a7d9c856494a5b9584d19f143f70eaf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-17T17:59:00Z","title_canon_sha256":"72c797d3cd16c348d5407e88aa035f33b4c6110766ba72b75593029fb8fcc39b"},"schema_version":"1.0","source":{"id":"2509.14230","kind":"arxiv","version":2}},"canonical_sha256":"b23be3666b5ce35210e45f0827339b6a88ed6894749a688332b40d1964d3a58a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b23be3666b5ce35210e45f0827339b6a88ed6894749a688332b40d1964d3a58a","first_computed_at":"2026-07-21T01:20:37.144251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:20:37.144251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V/L1zfEwgZjAEjYoe5FwwF9SSPO4LYHeLvuue+jWp5Cbd6TQAdzv8wefUBjk7QF1wB5yti2ixtRpty8JE+doCw==","signature_status":"signed_v1","signed_at":"2026-07-21T01:20:37.145274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.14230","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82df87c853ed59ce7445585ea13dcb63b6b28a3fa550da7cabd57e2dc893c5d6","sha256:5caca5b65d3afb77c4686cf133ebb35b84d70dfdec9c5fbcbb1fac191ae5c69e"],"state_sha256":"7cf8356b0534a962cf912782f10f00d835d8730d6d433634afbf0c06fb9570b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IxpK9E0sD7JPMikNsRsLkueNZDnAW7cHmbLq2VNCbf6vhqd8J9Xyv53FYGp4Hpiic0aVv16jq7KCKOYkpwyaBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:08:28.508739Z","bundle_sha256":"681fdf96fd6c00567c18352851e5382cf1eddf7bd169e9dc20562e02e9929c3a"}}