{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MHLRICJCYBWGUMBYU26PIXO4JI","short_pith_number":"pith:MHLRICJC","canonical_record":{"source":{"id":"2606.18627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T02:48:35Z","cross_cats_sorted":[],"title_canon_sha256":"062d32ce05b52070fb0fe8e802e242f0c692ea07a0b0006828903e937cc69499","abstract_canon_sha256":"7f87da7eae7c313ec2ea6b70f1ec3520068d157d7f838ad2fb8916d7b0e7b957"},"schema_version":"1.0"},"canonical_sha256":"61d7140922c06c6a3038a6bcf45ddc4a3eb18917f0125c1d7f0ec9b6da4754cf","source":{"kind":"arxiv","id":"2606.18627","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18627","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18627v1","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18627","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"MHLRICJCYBWG","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"MHLRICJCYBWGUMBY","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"MHLRICJC","created_at":"2026-06-19T16:11:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MHLRICJCYBWGUMBYU26PIXO4JI","target":"record","payload":{"canonical_record":{"source":{"id":"2606.18627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T02:48:35Z","cross_cats_sorted":[],"title_canon_sha256":"062d32ce05b52070fb0fe8e802e242f0c692ea07a0b0006828903e937cc69499","abstract_canon_sha256":"7f87da7eae7c313ec2ea6b70f1ec3520068d157d7f838ad2fb8916d7b0e7b957"},"schema_version":"1.0"},"canonical_sha256":"61d7140922c06c6a3038a6bcf45ddc4a3eb18917f0125c1d7f0ec9b6da4754cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:42.870470Z","signature_b64":"AOTLyrpL237zX5skS4GRQGkz3+UckDu+68FWEfLjDpjOmGnenVpfQUMJ7KmVyJitLNx474fPo7Fs7TCfqQ1pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d7140922c06c6a3038a6bcf45ddc4a3eb18917f0125c1d7f0ec9b6da4754cf","last_reissued_at":"2026-06-19T16:11:42.870051Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:42.870051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.18627","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":"2026-06-19T16:11:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sk9ok1WR37lftgDaBeF9TJtiDfDHOl7y3IyyOY3bptlz67ThKe+fTUq4KPQ1GzF2LAJJWOjV1JthyYJM1NO2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T23:18:07.218398Z"},"content_sha256":"72a7f7f8def7b9355ec47b67b80791904cc662974b4440976f44f9b8c2e449fe","schema_version":"1.0","event_id":"sha256:72a7f7f8def7b9355ec47b67b80791904cc662974b4440976f44f9b8c2e449fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MHLRICJCYBWGUMBYU26PIXO4JI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PACT: Preserving Anchored Cores in Task-vectors for Model Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chunyan Miao, Hao Wang, Ningyuan Shi, Peilin Zhao, Zhipeng Zhou","submitted_at":"2026-06-17T02:48:35Z","abstract_excerpt":"Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most existing model merging approaches follow the Task Arithmetic paradigm, which decomposes fine-tuned weights into pre-trained parameters and task vectors, and performs merging exclusively in the task-vector space. The effectiveness of this paradigm implicitly relies on the assumption that task-specific knowledge is encoded solely within task vectors. We argue that this assumption generally does not hold due to the intrins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18627","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/2606.18627/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":"2026-06-19T16:11:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/knCl6kQu3nTLsqgaiF/h/m4k4QWwtoWaOWMKZoHDKR3ayNQ/Fr1Am8rSUEIoIiqXrouLa2f09C5OMOcij9Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T23:18:07.218773Z"},"content_sha256":"80843a115447ce5ebc4d15e75c1c729255d0354fca5be16bfb8ceabb5cdc5f8e","schema_version":"1.0","event_id":"sha256:80843a115447ce5ebc4d15e75c1c729255d0354fca5be16bfb8ceabb5cdc5f8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MHLRICJCYBWGUMBYU26PIXO4JI/bundle.json","state_url":"https://pith.science/pith/MHLRICJCYBWGUMBYU26PIXO4JI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MHLRICJCYBWGUMBYU26PIXO4JI/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":"2026-06-27T23:18:07Z","links":{"resolver":"https://pith.science/pith/MHLRICJCYBWGUMBYU26PIXO4JI","bundle":"https://pith.science/pith/MHLRICJCYBWGUMBYU26PIXO4JI/bundle.json","state":"https://pith.science/pith/MHLRICJCYBWGUMBYU26PIXO4JI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MHLRICJCYBWGUMBYU26PIXO4JI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MHLRICJCYBWGUMBYU26PIXO4JI","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":"7f87da7eae7c313ec2ea6b70f1ec3520068d157d7f838ad2fb8916d7b0e7b957","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T02:48:35Z","title_canon_sha256":"062d32ce05b52070fb0fe8e802e242f0c692ea07a0b0006828903e937cc69499"},"schema_version":"1.0","source":{"id":"2606.18627","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18627","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18627v1","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18627","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"MHLRICJCYBWG","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"MHLRICJCYBWGUMBY","created_at":"2026-06-19T16:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"MHLRICJC","created_at":"2026-06-19T16:11:42Z"}],"graph_snapshots":[{"event_id":"sha256:80843a115447ce5ebc4d15e75c1c729255d0354fca5be16bfb8ceabb5cdc5f8e","target":"graph","created_at":"2026-06-19T16:11:42Z","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/2606.18627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model. Most existing model merging approaches follow the Task Arithmetic paradigm, which decomposes fine-tuned weights into pre-trained parameters and task vectors, and performs merging exclusively in the task-vector space. The effectiveness of this paradigm implicitly relies on the assumption that task-specific knowledge is encoded solely within task vectors. We argue that this assumption generally does not hold due to the intrins","authors_text":"Chunyan Miao, Hao Wang, Ningyuan Shi, Peilin Zhao, Zhipeng Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T02:48:35Z","title":"PACT: Preserving Anchored Cores in Task-vectors for Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18627","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":"sha256:72a7f7f8def7b9355ec47b67b80791904cc662974b4440976f44f9b8c2e449fe","target":"record","created_at":"2026-06-19T16:11:42Z","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":"7f87da7eae7c313ec2ea6b70f1ec3520068d157d7f838ad2fb8916d7b0e7b957","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T02:48:35Z","title_canon_sha256":"062d32ce05b52070fb0fe8e802e242f0c692ea07a0b0006828903e937cc69499"},"schema_version":"1.0","source":{"id":"2606.18627","kind":"arxiv","version":1}},"canonical_sha256":"61d7140922c06c6a3038a6bcf45ddc4a3eb18917f0125c1d7f0ec9b6da4754cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61d7140922c06c6a3038a6bcf45ddc4a3eb18917f0125c1d7f0ec9b6da4754cf","first_computed_at":"2026-06-19T16:11:42.870051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:42.870051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AOTLyrpL237zX5skS4GRQGkz3+UckDu+68FWEfLjDpjOmGnenVpfQUMJ7KmVyJitLNx474fPo7Fs7TCfqQ1pAg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:42.870470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18627","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72a7f7f8def7b9355ec47b67b80791904cc662974b4440976f44f9b8c2e449fe","sha256:80843a115447ce5ebc4d15e75c1c729255d0354fca5be16bfb8ceabb5cdc5f8e"],"state_sha256":"62afdce5e698c2df56763402317e59aa35a0a625b29251a2024b8f6372a376b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AUhR9RD1GVTv5fcVivjuk/YZN2XscyO3verrUPbbIHBuYwykCp01VIGh+dQ8hv0Cu2tMqOcfRFXylHVZLFK6AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T23:18:07.220706Z","bundle_sha256":"bc00ad8ef19bf12c1f29fe7b84c9f44e39b600ec2250ea795e6e76f70664ed7e"}}