{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KPSQZZ7AZNPN6BCKHFCJA4AOI7","short_pith_number":"pith:KPSQZZ7A","canonical_record":{"source":{"id":"2503.06184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-08T12:00:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c48568f63c41d92714e70b510f3b61dab600fe8763ff8ca54ad90a391041dad1","abstract_canon_sha256":"39b0c4c58b44e3a0239105aad807ab3b52da74b833932ade8277cd255de1cabd"},"schema_version":"1.0"},"canonical_sha256":"53e50ce7e0cb5edf044a394490700e47e3dfd105226ae56fe900bf0db86de044","source":{"kind":"arxiv","id":"2503.06184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06184","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06184v1","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06184","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"pith_short_12","alias_value":"KPSQZZ7AZNPN","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"KPSQZZ7AZNPN6BCK","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"KPSQZZ7A","created_at":"2026-07-05T10:26:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KPSQZZ7AZNPN6BCKHFCJA4AOI7","target":"record","payload":{"canonical_record":{"source":{"id":"2503.06184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-08T12:00:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c48568f63c41d92714e70b510f3b61dab600fe8763ff8ca54ad90a391041dad1","abstract_canon_sha256":"39b0c4c58b44e3a0239105aad807ab3b52da74b833932ade8277cd255de1cabd"},"schema_version":"1.0"},"canonical_sha256":"53e50ce7e0cb5edf044a394490700e47e3dfd105226ae56fe900bf0db86de044","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:56.151896Z","signature_b64":"BY5TaszPyPnts3sKSlWrf9uSk7oFXBzqWew0dKdBTt+eSI1BNg0KZgTqZdbhSCoWF3DIkcTbjUggJlprKHzHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e50ce7e0cb5edf044a394490700e47e3dfd105226ae56fe900bf0db86de044","last_reissued_at":"2026-07-05T10:26:56.151395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:56.151395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.06184","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":"2026-07-05T10:26:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FL9OiGxoKG7z28Tv4KWhpKrgfGdba2wNdzb+AFiZGnPidyoMPfFHSghDZZNX6KdqT4wAzMfghREjwBGXsFy+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:14:33.838646Z"},"content_sha256":"8540b7aacf7088df5e39f09cd3d2a6086b6eaca7e6e684404ffd59307c686c8b","schema_version":"1.0","event_id":"sha256:8540b7aacf7088df5e39f09cd3d2a6086b6eaca7e6e684404ffd59307c686c8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KPSQZZ7AZNPN6BCKHFCJA4AOI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-aware Adaptive Structured Pruning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jin Wang, Jun Kong, Xinge Ma, Xuejie Zhang","submitted_at":"2025-03-08T12:00:21Z","abstract_excerpt":"Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectively reduce the resource demands for deployment by removing redundant model parameters. However, the randomly selected calibration data and fixed single importance estimation metrics in existing structured pruning methods lead to degraded performance of pruned models. This study introduces AdaPruner, a sample-aware adaptive structured pruning framework for LLMs, aiming to optimize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06184","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/2503.06184/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":"2026-07-05T10:26:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Epjl5eKWcEC/OpFaehC+XH5XJnPG8eDuGHEFLCLyWiF+5KGnAfuG9AliyFLd8F6C1ajZyPF5ZlHcWp4+j94KCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:14:33.839386Z"},"content_sha256":"3765bae8803b2b234c12fa8253727dc5935478bc12370f7f6f7c118de67bb16e","schema_version":"1.0","event_id":"sha256:3765bae8803b2b234c12fa8253727dc5935478bc12370f7f6f7c118de67bb16e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPSQZZ7AZNPN6BCKHFCJA4AOI7/bundle.json","state_url":"https://pith.science/pith/KPSQZZ7AZNPN6BCKHFCJA4AOI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPSQZZ7AZNPN6BCKHFCJA4AOI7/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":"2026-08-17T22:14:33Z","links":{"resolver":"https://pith.science/pith/KPSQZZ7AZNPN6BCKHFCJA4AOI7","bundle":"https://pith.science/pith/KPSQZZ7AZNPN6BCKHFCJA4AOI7/bundle.json","state":"https://pith.science/pith/KPSQZZ7AZNPN6BCKHFCJA4AOI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPSQZZ7AZNPN6BCKHFCJA4AOI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KPSQZZ7AZNPN6BCKHFCJA4AOI7","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":"39b0c4c58b44e3a0239105aad807ab3b52da74b833932ade8277cd255de1cabd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-08T12:00:21Z","title_canon_sha256":"c48568f63c41d92714e70b510f3b61dab600fe8763ff8ca54ad90a391041dad1"},"schema_version":"1.0","source":{"id":"2503.06184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06184","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06184v1","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06184","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"pith_short_12","alias_value":"KPSQZZ7AZNPN","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"pith_short_16","alias_value":"KPSQZZ7AZNPN6BCK","created_at":"2026-07-05T10:26:56Z"},{"alias_kind":"pith_short_8","alias_value":"KPSQZZ7A","created_at":"2026-07-05T10:26:56Z"}],"graph_snapshots":[{"event_id":"sha256:3765bae8803b2b234c12fa8253727dc5935478bc12370f7f6f7c118de67bb16e","target":"graph","created_at":"2026-07-05T10:26:56Z","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/2503.06184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectively reduce the resource demands for deployment by removing redundant model parameters. However, the randomly selected calibration data and fixed single importance estimation metrics in existing structured pruning methods lead to degraded performance of pruned models. This study introduces AdaPruner, a sample-aware adaptive structured pruning framework for LLMs, aiming to optimize","authors_text":"Jin Wang, Jun Kong, Xinge Ma, Xuejie Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-08T12:00:21Z","title":"Sample-aware Adaptive Structured Pruning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06184","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":"sha256:8540b7aacf7088df5e39f09cd3d2a6086b6eaca7e6e684404ffd59307c686c8b","target":"record","created_at":"2026-07-05T10:26:56Z","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":"39b0c4c58b44e3a0239105aad807ab3b52da74b833932ade8277cd255de1cabd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-08T12:00:21Z","title_canon_sha256":"c48568f63c41d92714e70b510f3b61dab600fe8763ff8ca54ad90a391041dad1"},"schema_version":"1.0","source":{"id":"2503.06184","kind":"arxiv","version":1}},"canonical_sha256":"53e50ce7e0cb5edf044a394490700e47e3dfd105226ae56fe900bf0db86de044","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53e50ce7e0cb5edf044a394490700e47e3dfd105226ae56fe900bf0db86de044","first_computed_at":"2026-07-05T10:26:56.151395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:56.151395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BY5TaszPyPnts3sKSlWrf9uSk7oFXBzqWew0dKdBTt+eSI1BNg0KZgTqZdbhSCoWF3DIkcTbjUggJlprKHzHCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:56.151896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.06184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8540b7aacf7088df5e39f09cd3d2a6086b6eaca7e6e684404ffd59307c686c8b","sha256:3765bae8803b2b234c12fa8253727dc5935478bc12370f7f6f7c118de67bb16e"],"state_sha256":"e672afe7959f86023177e980499e5f924ec2b558173e9d9100f1e20e35e8dfb3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KettChc2YuQeU0/ARG4Js/56fi0xQ9+kYjg7A+0ewVikerQ/EGrXkZEIaQU0KV38hHOsFkaDwfEJcMuYb1KfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:14:33.850512Z","bundle_sha256":"0196094e915c96955ff2728c4e661b5c169e2136bc38792a5ee0ef29a8527902"}}