{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AATIRCVBRU7GTSVE5DBLLIGWN2","short_pith_number":"pith:AATIRCVB","canonical_record":{"source":{"id":"2411.10272","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-15T15:28:42Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d08b52f968506604fb32cffb7babf972bec908845fdae26f7567493d878ab9c0","abstract_canon_sha256":"c4e690882a1813febf1423e99a58e18d616eb4de66439a5fd709006c44a3d6f4"},"schema_version":"1.0"},"canonical_sha256":"0026888aa18d3e69caa4e8c2b5a0d66e85dc7f27d0b6045d1f4d35af3050fde7","source":{"kind":"arxiv","id":"2411.10272","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10272","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10272v3","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10272","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"pith_short_12","alias_value":"AATIRCVBRU7G","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"pith_short_16","alias_value":"AATIRCVBRU7GTSVE","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"pith_short_8","alias_value":"AATIRCVB","created_at":"2026-07-05T11:09:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AATIRCVBRU7GTSVE5DBLLIGWN2","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10272","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-15T15:28:42Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d08b52f968506604fb32cffb7babf972bec908845fdae26f7567493d878ab9c0","abstract_canon_sha256":"c4e690882a1813febf1423e99a58e18d616eb4de66439a5fd709006c44a3d6f4"},"schema_version":"1.0"},"canonical_sha256":"0026888aa18d3e69caa4e8c2b5a0d66e85dc7f27d0b6045d1f4d35af3050fde7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:43.995927Z","signature_b64":"Q8YZUjWSwCtGPWLsh69fXL+DNhSxNsAwvqhaq7pszxHHRdRKMGAr9hKmRiXdU2TAPUUBnreBl8UZ4hqzDbcqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0026888aa18d3e69caa4e8c2b5a0d66e85dc7f27d0b6045d1f4d35af3050fde7","last_reissued_at":"2026-07-05T11:09:43.995453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:43.995453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10272","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fwk3ho4zVcrw2pLrtL5U+VgC6egLJhslx/MnKSkqasL2UqbEPIyJWB7Q704tm+ddLd71Q6WvlyRvWKSSdLxHDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T13:28:23.009310Z"},"content_sha256":"b1f74c253183b2230b7ce2f2564002163cdeca6cc00b6c6f279202c190a50597","schema_version":"1.0","event_id":"sha256:b1f74c253183b2230b7ce2f2564002163cdeca6cc00b6c6f279202c190a50597"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AATIRCVBRU7GTSVE5DBLLIGWN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"P$^2$ Law: Scaling Law for Post-Training After Model Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cuiping Li, Hong Chen, Jing Zhang, Xiaodong Chen, Xiaokang Zhang, Yanling Wang, Yuxuan Hu","submitted_at":"2024-11-15T15:28:42Z","abstract_excerpt":"Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs). To recover model performance after pruning, post-training is commonly employed to mitigate the resulting performance degradation. While post-training benefits from larger datasets, once the dataset size is already substantial, increasing the training data provides only limited performance gains. To balance post-training cost and model performance, it is necessary to explore the optimal amount of post-training data.Through extensive experiments on the Llama-3 and Qwen-2.5 series"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10272","kind":"arxiv","version":3},"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/2411.10272/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":"2026-07-05T11:09:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QOv9vVyGEqRAuSbE88zE/d8KXgYk/3Gct/5C2/CqUcu2p/rCc3crA4w+EkFrpVnJQbJCG6tqySucuJL3HUgGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T13:28:23.009708Z"},"content_sha256":"3f70f4908e8741f665fb485e384e154c336b37eb084cffda54f555d8487e0bfa","schema_version":"1.0","event_id":"sha256:3f70f4908e8741f665fb485e384e154c336b37eb084cffda54f555d8487e0bfa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AATIRCVBRU7GTSVE5DBLLIGWN2/bundle.json","state_url":"https://pith.science/pith/AATIRCVBRU7GTSVE5DBLLIGWN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AATIRCVBRU7GTSVE5DBLLIGWN2/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":"2026-07-10T13:28:23Z","links":{"resolver":"https://pith.science/pith/AATIRCVBRU7GTSVE5DBLLIGWN2","bundle":"https://pith.science/pith/AATIRCVBRU7GTSVE5DBLLIGWN2/bundle.json","state":"https://pith.science/pith/AATIRCVBRU7GTSVE5DBLLIGWN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AATIRCVBRU7GTSVE5DBLLIGWN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AATIRCVBRU7GTSVE5DBLLIGWN2","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":"c4e690882a1813febf1423e99a58e18d616eb4de66439a5fd709006c44a3d6f4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-15T15:28:42Z","title_canon_sha256":"d08b52f968506604fb32cffb7babf972bec908845fdae26f7567493d878ab9c0"},"schema_version":"1.0","source":{"id":"2411.10272","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10272","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10272v3","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10272","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"pith_short_12","alias_value":"AATIRCVBRU7G","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"pith_short_16","alias_value":"AATIRCVBRU7GTSVE","created_at":"2026-07-05T11:09:43Z"},{"alias_kind":"pith_short_8","alias_value":"AATIRCVB","created_at":"2026-07-05T11:09:43Z"}],"graph_snapshots":[{"event_id":"sha256:3f70f4908e8741f665fb485e384e154c336b37eb084cffda54f555d8487e0bfa","target":"graph","created_at":"2026-07-05T11:09:43Z","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/2411.10272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pruning has become a widely adopted technique for reducing the hardware requirements of large language models (LLMs). To recover model performance after pruning, post-training is commonly employed to mitigate the resulting performance degradation. While post-training benefits from larger datasets, once the dataset size is already substantial, increasing the training data provides only limited performance gains. To balance post-training cost and model performance, it is necessary to explore the optimal amount of post-training data.Through extensive experiments on the Llama-3 and Qwen-2.5 series","authors_text":"Cuiping Li, Hong Chen, Jing Zhang, Xiaodong Chen, Xiaokang Zhang, Yanling Wang, Yuxuan Hu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-15T15:28:42Z","title":"P$^2$ Law: Scaling Law for Post-Training After Model Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10272","kind":"arxiv","version":3},"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:b1f74c253183b2230b7ce2f2564002163cdeca6cc00b6c6f279202c190a50597","target":"record","created_at":"2026-07-05T11:09:43Z","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":"c4e690882a1813febf1423e99a58e18d616eb4de66439a5fd709006c44a3d6f4","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-15T15:28:42Z","title_canon_sha256":"d08b52f968506604fb32cffb7babf972bec908845fdae26f7567493d878ab9c0"},"schema_version":"1.0","source":{"id":"2411.10272","kind":"arxiv","version":3}},"canonical_sha256":"0026888aa18d3e69caa4e8c2b5a0d66e85dc7f27d0b6045d1f4d35af3050fde7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0026888aa18d3e69caa4e8c2b5a0d66e85dc7f27d0b6045d1f4d35af3050fde7","first_computed_at":"2026-07-05T11:09:43.995453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:43.995453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q8YZUjWSwCtGPWLsh69fXL+DNhSxNsAwvqhaq7pszxHHRdRKMGAr9hKmRiXdU2TAPUUBnreBl8UZ4hqzDbcqCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:43.995927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10272","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1f74c253183b2230b7ce2f2564002163cdeca6cc00b6c6f279202c190a50597","sha256:3f70f4908e8741f665fb485e384e154c336b37eb084cffda54f555d8487e0bfa"],"state_sha256":"c49a6d9fd7c5cf53ee2e77bc3aa023339c8051f0157e8b5ac4c596496207a594"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLAAaebSV3Jaum/ganmTuG5H0597HSgWAGk9bQbsTMLCnBR/DjT4s2P2//gTnE3Eb2YalGuiUVLZDjEc1D8JCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T13:28:23.011636Z","bundle_sha256":"83e02821974eb6119a243ad4e198d0ea7784f6e96ecdbe80692161ff26faf221"}}