{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D4QOTQBOP4FL2F4PLEFAQG2U3R","short_pith_number":"pith:D4QOTQBO","canonical_record":{"source":{"id":"2506.13406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-16T12:19:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e60cd97862de4509f957966c3162ba425e17755a516027c7513d542f0662a189","abstract_canon_sha256":"b68451c2f4a25d18c4ed7fe5256531bde736309b70af13400253ac6761026811"},"schema_version":"1.0"},"canonical_sha256":"1f20e9c02e7f0abd178f590a081b54dc6314a104f28d63c57b57ea6e4ac14891","source":{"kind":"arxiv","id":"2506.13406","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13406","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13406v1","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13406","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"D4QOTQBOP4FL","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"D4QOTQBOP4FL2F4P","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"D4QOTQBO","created_at":"2026-07-05T11:22:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D4QOTQBOP4FL2F4PLEFAQG2U3R","target":"record","payload":{"canonical_record":{"source":{"id":"2506.13406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-16T12:19:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e60cd97862de4509f957966c3162ba425e17755a516027c7513d542f0662a189","abstract_canon_sha256":"b68451c2f4a25d18c4ed7fe5256531bde736309b70af13400253ac6761026811"},"schema_version":"1.0"},"canonical_sha256":"1f20e9c02e7f0abd178f590a081b54dc6314a104f28d63c57b57ea6e4ac14891","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:09.867437Z","signature_b64":"Q6kZpkbPztO2LWhJJp95QlmGsS5h2rFbvmJT5zEXlhAglkvY2nbk6Re/zOJnXzEiin7DZ8lJhHtt+CKAC0N+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f20e9c02e7f0abd178f590a081b54dc6314a104f28d63c57b57ea6e4ac14891","last_reissued_at":"2026-07-05T11:22:09.866987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:09.866987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.13406","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":"2026-07-05T11:22:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSn9+owMay2u4JtE9BW32Cfp1Dg74rXQkvLKCTzg9M0Jnx0pTCb8IJWuBngNJ4fuRg1Tieri0T3mH1SQ55NqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:22:42.056736Z"},"content_sha256":"0ee55c0a5312fbd815d18031d19e5a644902e88e9fd03704aeec6895a0ea05f5","schema_version":"1.0","event_id":"sha256:0ee55c0a5312fbd815d18031d19e5a644902e88e9fd03704aeec6895a0ea05f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D4QOTQBOP4FL2F4PLEFAQG2U3R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CALM: Consensus-Aware Localized Merging for Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Jiang, Changshui Zhang, Feng Liu, Kunda Yan, Min Zhang, Sen Cui, Zikun Qu","submitted_at":"2025-06-16T12:19:45Z","abstract_excerpt":"Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified into global- and local-aware methods. However, global-aware methods inevitably cause parameter interference, while local-aware methods struggle to maintain the effectiveness of task-specific details in the merged model. To address these limitations, we propose a Consensus-Aware Localized Merging (CALM) method which incorporates localized information aligned with global task consen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13406","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/2506.13406/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":"2026-07-05T11:22:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HxbH1tdzpcZYgqnznhXkOcA+Jcs3GkZNNRNByoe0zD+M9g2yxtCLIIC0m/t3zA4eU53LFvT7Cr628oIZulWIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:22:42.057268Z"},"content_sha256":"814b48a0c61bed191b1315d2da7b5fb2d4582a2d19996d78574b229911b8ea60","schema_version":"1.0","event_id":"sha256:814b48a0c61bed191b1315d2da7b5fb2d4582a2d19996d78574b229911b8ea60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4QOTQBOP4FL2F4PLEFAQG2U3R/bundle.json","state_url":"https://pith.science/pith/D4QOTQBOP4FL2F4PLEFAQG2U3R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4QOTQBOP4FL2F4PLEFAQG2U3R/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":"2026-08-05T22:22:42Z","links":{"resolver":"https://pith.science/pith/D4QOTQBOP4FL2F4PLEFAQG2U3R","bundle":"https://pith.science/pith/D4QOTQBOP4FL2F4PLEFAQG2U3R/bundle.json","state":"https://pith.science/pith/D4QOTQBOP4FL2F4PLEFAQG2U3R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4QOTQBOP4FL2F4PLEFAQG2U3R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D4QOTQBOP4FL2F4PLEFAQG2U3R","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":"b68451c2f4a25d18c4ed7fe5256531bde736309b70af13400253ac6761026811","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-16T12:19:45Z","title_canon_sha256":"e60cd97862de4509f957966c3162ba425e17755a516027c7513d542f0662a189"},"schema_version":"1.0","source":{"id":"2506.13406","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13406","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13406v1","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13406","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"D4QOTQBOP4FL","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"D4QOTQBOP4FL2F4P","created_at":"2026-07-05T11:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"D4QOTQBO","created_at":"2026-07-05T11:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:814b48a0c61bed191b1315d2da7b5fb2d4582a2d19996d78574b229911b8ea60","target":"graph","created_at":"2026-07-05T11:22:09Z","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/2506.13406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified into global- and local-aware methods. However, global-aware methods inevitably cause parameter interference, while local-aware methods struggle to maintain the effectiveness of task-specific details in the merged model. To address these limitations, we propose a Consensus-Aware Localized Merging (CALM) method which incorporates localized information aligned with global task consen","authors_text":"Bo Jiang, Changshui Zhang, Feng Liu, Kunda Yan, Min Zhang, Sen Cui, Zikun Qu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-16T12:19:45Z","title":"CALM: Consensus-Aware Localized Merging for Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13406","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":"sha256:0ee55c0a5312fbd815d18031d19e5a644902e88e9fd03704aeec6895a0ea05f5","target":"record","created_at":"2026-07-05T11:22:09Z","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":"b68451c2f4a25d18c4ed7fe5256531bde736309b70af13400253ac6761026811","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-16T12:19:45Z","title_canon_sha256":"e60cd97862de4509f957966c3162ba425e17755a516027c7513d542f0662a189"},"schema_version":"1.0","source":{"id":"2506.13406","kind":"arxiv","version":1}},"canonical_sha256":"1f20e9c02e7f0abd178f590a081b54dc6314a104f28d63c57b57ea6e4ac14891","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f20e9c02e7f0abd178f590a081b54dc6314a104f28d63c57b57ea6e4ac14891","first_computed_at":"2026-07-05T11:22:09.866987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:09.866987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q6kZpkbPztO2LWhJJp95QlmGsS5h2rFbvmJT5zEXlhAglkvY2nbk6Re/zOJnXzEiin7DZ8lJhHtt+CKAC0N+AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:09.867437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13406","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ee55c0a5312fbd815d18031d19e5a644902e88e9fd03704aeec6895a0ea05f5","sha256:814b48a0c61bed191b1315d2da7b5fb2d4582a2d19996d78574b229911b8ea60"],"state_sha256":"07265f6952e4f4f080854e05e9f2a65f78f3fb63b42853a7ec40b5aacb50be9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PFNNDxEcBBGp02c+yZ18XrH1Fy7iaq81J/XelQYjHDX62KQ0VbTwpHWM3wS5k0IQ4YqjUu0MyO8Luz5LmGmtCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:22:42.062120Z","bundle_sha256":"dcf97685737c1d4772f7d799a793233c5aee398d73a5308a23e0f8dd034fa028"}}