{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6GYT74RTHDHL63R3TYBWAMSU3S","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":"e22d8a7a789c28f64c7124c54e8dcf1bb52d56501be0337aff49e9db28577021","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T04:54:01Z","title_canon_sha256":"0cdbcb2c1eb27cd9ba9a3c8a0ead90a07a723d73f01ab6ac87887e104c357584"},"schema_version":"1.0","source":{"id":"2507.03294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03294","created_at":"2026-07-05T11:31:56Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03294v1","created_at":"2026-07-05T11:31:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03294","created_at":"2026-07-05T11:31:56Z"},{"alias_kind":"pith_short_12","alias_value":"6GYT74RTHDHL","created_at":"2026-07-05T11:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"6GYT74RTHDHL63R3","created_at":"2026-07-05T11:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"6GYT74RT","created_at":"2026-07-05T11:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:0f9e3f9c41452ce3df97f7832b0194be936deccc28ac98d3f9197324aecb4538","target":"graph","created_at":"2026-07-05T11:31:56Z","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/2507.03294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The enormous parameter scale of large language models (LLMs) has made model compression a research hotspot, which aims to alleviate computational resource demands during deployment and inference. As a promising direction, low-rank approximation technique has made remarkable achievements. Nevertheless, unfortunately, the vast majority of studies to low-rank approximation compression generally apply uniform compression ratios across all weight matrices, while disregarding their inherently differentiated impacts on the model's performance. Although a few recent work attempts to employ heuristic s","authors_text":"Guangyan Li, Wensheng Zhang, Yongqiang Tang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T04:54:01Z","title":"MGAA: Multi-Granular Adaptive Allocation fof Low-Rank Compression of LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03294","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":"sha256:904906aaeb0058b171d0c366eaa8c2038fc597015299e6722cdee2b05deccc14","target":"record","created_at":"2026-07-05T11:31:56Z","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":"e22d8a7a789c28f64c7124c54e8dcf1bb52d56501be0337aff49e9db28577021","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T04:54:01Z","title_canon_sha256":"0cdbcb2c1eb27cd9ba9a3c8a0ead90a07a723d73f01ab6ac87887e104c357584"},"schema_version":"1.0","source":{"id":"2507.03294","kind":"arxiv","version":1}},"canonical_sha256":"f1b13ff23338cebf6e3b9e03603254dcb1cd44d6ba07cf85f95300c23ab4bb61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1b13ff23338cebf6e3b9e03603254dcb1cd44d6ba07cf85f95300c23ab4bb61","first_computed_at":"2026-07-05T11:31:56.388041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:56.388041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BKX6ocvvRyACRve1usbtjBdEETQ4AQH3i5bE1HLHoDjcKMxPqFr1zLqcN1GKmtIxJPoXS3lzLMI5toq6qzwvCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:56.388541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:904906aaeb0058b171d0c366eaa8c2038fc597015299e6722cdee2b05deccc14","sha256:0f9e3f9c41452ce3df97f7832b0194be936deccc28ac98d3f9197324aecb4538"],"state_sha256":"5e1a8a901bdb75d9ca74a9eab7901daed737b8aa3c2c005bf5f12c60fc494a60"}