{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CARIZICC65QYB4DQBZUN36SDZV","short_pith_number":"pith:CARIZICC","canonical_record":{"source":{"id":"2505.16148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:46:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a8889fcca71d5f64b4ebbd3a1326171940c736aa6cf4e14e947a053d73361bdd","abstract_canon_sha256":"e5193eeb2e37a5c0225100373ae8f1c39493a48bf3c8ab9df6570145b7e0633c"},"schema_version":"1.0"},"canonical_sha256":"10228ca042f76180f0700e68ddfa43cd4aa65dd50eb536926b99ce597667dcf6","source":{"kind":"arxiv","id":"2505.16148","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16148","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16148v1","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16148","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_12","alias_value":"CARIZICC65QY","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_16","alias_value":"CARIZICC65QYB4DQ","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_8","alias_value":"CARIZICC","created_at":"2026-07-05T11:07:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CARIZICC65QYB4DQBZUN36SDZV","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16148","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:46:08Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a8889fcca71d5f64b4ebbd3a1326171940c736aa6cf4e14e947a053d73361bdd","abstract_canon_sha256":"e5193eeb2e37a5c0225100373ae8f1c39493a48bf3c8ab9df6570145b7e0633c"},"schema_version":"1.0"},"canonical_sha256":"10228ca042f76180f0700e68ddfa43cd4aa65dd50eb536926b99ce597667dcf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:30.691145Z","signature_b64":"I0eqOgsKgmb5o+2EP7R+aLTenrM67Px+AHf+CkNeROvkktfh3tYvWv2C2paiNdBtlkdsQxiCZJm6Pf5c0u53Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10228ca042f76180f0700e68ddfa43cd4aa65dd50eb536926b99ce597667dcf6","last_reissued_at":"2026-07-05T11:07:30.690642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:30.690642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16148","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":"2026-07-05T11:07:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vH4bQQrN9cHrE+C8sFL60i+M0J4ypnnLOIHR6KZw/Sk/NVVRtfBP5jH7+gJY/V3amUR5wKiE3bMpw/p+OdVbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:30:25.533865Z"},"content_sha256":"3783a5b61722f248c5bcfa3a8100318c29e0453a8224441ccb57defade673e0b","schema_version":"1.0","event_id":"sha256:3783a5b61722f248c5bcfa3a8100318c29e0453a8224441ccb57defade673e0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CARIZICC65QYB4DQBZUN36SDZV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NAN: A Training-Free Solution to Coefficient Estimation in Model Merging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Zheng, Chongjie Si, Jingjing Jiang, Kangtao Lv, Wei Shen, Wenbo Su, Xiaokang Yang, Yadao Wang, Yongwei Wang","submitted_at":"2025-05-22T02:46:08Z","abstract_excerpt":"Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existing approaches often rely on heuristics to determine the merging coefficients, limiting their scalability and generality. In this work, we revisit model merging through the lens of least-squares optimization and show that the optimal merging weights should scale with the amount of task-specific information encoded in each model. Based on this insight, we propose NAN, a simple yet effective method that estimates model m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16148","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/2505.16148/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":"2026-07-05T11:07:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BwvJYnGElxJfn1hVGFuvWSp7iApT92x/iylNgCsVqGk63bh4BeTXz5wFUrrNGf1uVDMiLadlr4yOGMpSEwRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:30:25.534370Z"},"content_sha256":"340609abf3ed39e51d359057214c42a2eaddb0d41134102b32537ae9c6b16bdb","schema_version":"1.0","event_id":"sha256:340609abf3ed39e51d359057214c42a2eaddb0d41134102b32537ae9c6b16bdb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CARIZICC65QYB4DQBZUN36SDZV/bundle.json","state_url":"https://pith.science/pith/CARIZICC65QYB4DQBZUN36SDZV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CARIZICC65QYB4DQBZUN36SDZV/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":"2026-08-07T01:30:25Z","links":{"resolver":"https://pith.science/pith/CARIZICC65QYB4DQBZUN36SDZV","bundle":"https://pith.science/pith/CARIZICC65QYB4DQBZUN36SDZV/bundle.json","state":"https://pith.science/pith/CARIZICC65QYB4DQBZUN36SDZV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CARIZICC65QYB4DQBZUN36SDZV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CARIZICC65QYB4DQBZUN36SDZV","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":"e5193eeb2e37a5c0225100373ae8f1c39493a48bf3c8ab9df6570145b7e0633c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:46:08Z","title_canon_sha256":"a8889fcca71d5f64b4ebbd3a1326171940c736aa6cf4e14e947a053d73361bdd"},"schema_version":"1.0","source":{"id":"2505.16148","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16148","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16148v1","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16148","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_12","alias_value":"CARIZICC65QY","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_16","alias_value":"CARIZICC65QYB4DQ","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_8","alias_value":"CARIZICC","created_at":"2026-07-05T11:07:30Z"}],"graph_snapshots":[{"event_id":"sha256:340609abf3ed39e51d359057214c42a2eaddb0d41134102b32537ae9c6b16bdb","target":"graph","created_at":"2026-07-05T11:07:30Z","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/2505.16148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existing approaches often rely on heuristics to determine the merging coefficients, limiting their scalability and generality. In this work, we revisit model merging through the lens of least-squares optimization and show that the optimal merging weights should scale with the amount of task-specific information encoded in each model. Based on this insight, we propose NAN, a simple yet effective method that estimates model m","authors_text":"Bo Zheng, Chongjie Si, Jingjing Jiang, Kangtao Lv, Wei Shen, Wenbo Su, Xiaokang Yang, Yadao Wang, Yongwei Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:46:08Z","title":"NAN: A Training-Free Solution to Coefficient Estimation in Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16148","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":"sha256:3783a5b61722f248c5bcfa3a8100318c29e0453a8224441ccb57defade673e0b","target":"record","created_at":"2026-07-05T11:07:30Z","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":"e5193eeb2e37a5c0225100373ae8f1c39493a48bf3c8ab9df6570145b7e0633c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T02:46:08Z","title_canon_sha256":"a8889fcca71d5f64b4ebbd3a1326171940c736aa6cf4e14e947a053d73361bdd"},"schema_version":"1.0","source":{"id":"2505.16148","kind":"arxiv","version":1}},"canonical_sha256":"10228ca042f76180f0700e68ddfa43cd4aa65dd50eb536926b99ce597667dcf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10228ca042f76180f0700e68ddfa43cd4aa65dd50eb536926b99ce597667dcf6","first_computed_at":"2026-07-05T11:07:30.690642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:30.690642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I0eqOgsKgmb5o+2EP7R+aLTenrM67Px+AHf+CkNeROvkktfh3tYvWv2C2paiNdBtlkdsQxiCZJm6Pf5c0u53Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:30.691145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16148","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3783a5b61722f248c5bcfa3a8100318c29e0453a8224441ccb57defade673e0b","sha256:340609abf3ed39e51d359057214c42a2eaddb0d41134102b32537ae9c6b16bdb"],"state_sha256":"c0b389c411cb0657d1e69db52486477a04ff11d6b73a40c59fcda0eddc249574"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TtQ3ONkVC8OqDu1Ucn3QWx0+AbgNokHuCSOKYkmEV+WZBjdeiyaOY8pwKDWR1Zm+j9Mlw5R59u1Li5ATROTfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:30:25.537799Z","bundle_sha256":"376c1731b8fe696263c13301d15f920877285e4cc2eae1917463ad3bbf9c8c23"}}