{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LNO2LLQERQA6JEANHQOPHMTQRL","short_pith_number":"pith:LNO2LLQE","canonical_record":{"source":{"id":"2504.19583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-28T08:42:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d4e2de846f9f8bda0ce913f5e90a82077933fe0580f46cf1f5730d0178818036","abstract_canon_sha256":"ee83f5b313dd51a6307edc7395eb403f166ce92dca1b60f61a6ad394a228af8f"},"schema_version":"1.0"},"canonical_sha256":"5b5da5ae048c01e4900d3c1cf3b2708adfa5d3dfa2991e52ad7c3d31c8c15bd9","source":{"kind":"arxiv","id":"2504.19583","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19583","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19583v2","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19583","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"LNO2LLQERQA6","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"LNO2LLQERQA6JEAN","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"LNO2LLQE","created_at":"2026-07-05T11:13:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LNO2LLQERQA6JEANHQOPHMTQRL","target":"record","payload":{"canonical_record":{"source":{"id":"2504.19583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-28T08:42:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d4e2de846f9f8bda0ce913f5e90a82077933fe0580f46cf1f5730d0178818036","abstract_canon_sha256":"ee83f5b313dd51a6307edc7395eb403f166ce92dca1b60f61a6ad394a228af8f"},"schema_version":"1.0"},"canonical_sha256":"5b5da5ae048c01e4900d3c1cf3b2708adfa5d3dfa2991e52ad7c3d31c8c15bd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:24.535368Z","signature_b64":"tcL75kigdJoNi/+i7BaA3aGI+ouoQM5hfR2phF9aUgAdEvQKWNcI7HtOYgipsaMuTEbxSQUaunSDJ3WxX6frAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5da5ae048c01e4900d3c1cf3b2708adfa5d3dfa2991e52ad7c3d31c8c15bd9","last_reissued_at":"2026-07-05T11:13:24.534843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:24.534843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.19583","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":"2026-07-05T11:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a1JrLRhoDVC0RShRgsFLBeUJb59E8C4rovDNw9b35oBbPEv2qxSKvFjS6+Fj5TIDUSkqn/z20wr/0Ejt1ZyxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:50:21.372240Z"},"content_sha256":"e5beb34b05947bce5c0a7fb2b2597e26f3dacb075e142690f1917a5338163645","schema_version":"1.0","event_id":"sha256:e5beb34b05947bce5c0a7fb2b2597e26f3dacb075e142690f1917a5338163645"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LNO2LLQERQA6JEANHQOPHMTQRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Graph-Based Spectral Decomposition for Parameter Coordination in Language Model Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Binrong Zhu, Guiran Liu, Hanlu Zhang, Shuo Wang, Yumeng Ma","submitted_at":"2025-04-28T08:42:35Z","abstract_excerpt":"This paper proposes a parameter collaborative optimization algorithm for large language models, enhanced with graph spectral analysis. The goal is to improve both fine-tuning efficiency and structural awareness during training. In the proposed method, the parameters of a pre-trained language model are treated as nodes in a graph. A weighted graph is constructed, and Laplacian spectral decomposition is applied to enable frequency-domain modeling and structural representation of the parameter space. Based on this structure, a joint loss function is designed. It combines the task loss with a spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19583","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/2504.19583/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":"2026-07-05T11:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mrxEXMTs0cjGJ9n9glwRoB9vkSwecY309nHtYt7K5DVXZt7K/i1s5JI0MbnkEeNKbeae6rEMoBoAZLMMprM5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:50:21.372745Z"},"content_sha256":"e2f4330349ee4e690cf1f6bbb8a73c24cc6b29bb1918eab7ea703e939ffc7239","schema_version":"1.0","event_id":"sha256:e2f4330349ee4e690cf1f6bbb8a73c24cc6b29bb1918eab7ea703e939ffc7239"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LNO2LLQERQA6JEANHQOPHMTQRL/bundle.json","state_url":"https://pith.science/pith/LNO2LLQERQA6JEANHQOPHMTQRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LNO2LLQERQA6JEANHQOPHMTQRL/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":"2026-08-06T04:50:21Z","links":{"resolver":"https://pith.science/pith/LNO2LLQERQA6JEANHQOPHMTQRL","bundle":"https://pith.science/pith/LNO2LLQERQA6JEANHQOPHMTQRL/bundle.json","state":"https://pith.science/pith/LNO2LLQERQA6JEANHQOPHMTQRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LNO2LLQERQA6JEANHQOPHMTQRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LNO2LLQERQA6JEANHQOPHMTQRL","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":"ee83f5b313dd51a6307edc7395eb403f166ce92dca1b60f61a6ad394a228af8f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-28T08:42:35Z","title_canon_sha256":"d4e2de846f9f8bda0ce913f5e90a82077933fe0580f46cf1f5730d0178818036"},"schema_version":"1.0","source":{"id":"2504.19583","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19583","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19583v2","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19583","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"LNO2LLQERQA6","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"LNO2LLQERQA6JEAN","created_at":"2026-07-05T11:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"LNO2LLQE","created_at":"2026-07-05T11:13:24Z"}],"graph_snapshots":[{"event_id":"sha256:e2f4330349ee4e690cf1f6bbb8a73c24cc6b29bb1918eab7ea703e939ffc7239","target":"graph","created_at":"2026-07-05T11:13:24Z","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/2504.19583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a parameter collaborative optimization algorithm for large language models, enhanced with graph spectral analysis. The goal is to improve both fine-tuning efficiency and structural awareness during training. In the proposed method, the parameters of a pre-trained language model are treated as nodes in a graph. A weighted graph is constructed, and Laplacian spectral decomposition is applied to enable frequency-domain modeling and structural representation of the parameter space. Based on this structure, a joint loss function is designed. It combines the task loss with a spec","authors_text":"Binrong Zhu, Guiran Liu, Hanlu Zhang, Shuo Wang, Yumeng Ma","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-28T08:42:35Z","title":"Graph-Based Spectral Decomposition for Parameter Coordination in Language Model Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19583","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:e5beb34b05947bce5c0a7fb2b2597e26f3dacb075e142690f1917a5338163645","target":"record","created_at":"2026-07-05T11:13:24Z","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":"ee83f5b313dd51a6307edc7395eb403f166ce92dca1b60f61a6ad394a228af8f","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-28T08:42:35Z","title_canon_sha256":"d4e2de846f9f8bda0ce913f5e90a82077933fe0580f46cf1f5730d0178818036"},"schema_version":"1.0","source":{"id":"2504.19583","kind":"arxiv","version":2}},"canonical_sha256":"5b5da5ae048c01e4900d3c1cf3b2708adfa5d3dfa2991e52ad7c3d31c8c15bd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b5da5ae048c01e4900d3c1cf3b2708adfa5d3dfa2991e52ad7c3d31c8c15bd9","first_computed_at":"2026-07-05T11:13:24.534843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:24.534843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tcL75kigdJoNi/+i7BaA3aGI+ouoQM5hfR2phF9aUgAdEvQKWNcI7HtOYgipsaMuTEbxSQUaunSDJ3WxX6frAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:24.535368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.19583","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5beb34b05947bce5c0a7fb2b2597e26f3dacb075e142690f1917a5338163645","sha256:e2f4330349ee4e690cf1f6bbb8a73c24cc6b29bb1918eab7ea703e939ffc7239"],"state_sha256":"00ef7c5c78a30978c42f72d87195851752f410ebf56f7af166e62c2702e472ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaLKr9KfGwTpdl6JSSmIjGOGni0EAXsGydoZE/2YQXhaXBYUJhoL3GpGHT8ttECL1CxiPaDhkuaS6GwYKiHnCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:50:21.377818Z","bundle_sha256":"51bc57a260046fc8f966531bbcc31b47a11f4e6ec7cfacc4dcfd3be81ac29301"}}