{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:67AHLDEPTTEJZOOQH3WLBG63JB","short_pith_number":"pith:67AHLDEP","schema_version":"1.0","canonical_sha256":"f7c0758c8f9cc89cb9d03eecb09bdb48792b874481649178904ddd99a4c972ab","source":{"kind":"arxiv","id":"2606.22589","version":1},"attestation_state":"computed","paper":{"title":"Training-free Task Classification for Multi-Task Model Merging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinwook Jung, Jungyong Son, Sungyong Baik","submitted_at":"2026-06-21T16:51:29Z","abstract_excerpt":"Ever since the advent of foundation models and the pre-training-finetuning paradigm, there have been numerous efforts to merge multiple task-specific experts into a single multi-task model. Prior work largely focuses on finding a single merged model, but it often underperforms individual experts due to parameter interference. To resolve this, dynamic model merging employs routing to activate task-relevant parameters per input. However, existing routers typically require either additional training with abundant labeled datasets or assume the access to task IDs of each input at inference time. I"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.22589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T16:51:29Z","cross_cats_sorted":[],"title_canon_sha256":"ec8dc1bad98b6938ef7c3dd6bd5540a80e228d37789d6ff3c9c5d17ffef9e76a","abstract_canon_sha256":"176789a92b6d1dc471f90011d30b0ddb6a65ee0d8b18f0393b5d33af22248910"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:42.292397Z","signature_b64":"65uoRX6adN4cLGfr5zhAVqKMNxJlWi2Yxq8aEAscUFxpctOJqvUG4hwdqL326Rodo9GGDRHEn3CY+/kWTICDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7c0758c8f9cc89cb9d03eecb09bdb48792b874481649178904ddd99a4c972ab","last_reissued_at":"2026-06-23T02:13:42.292044Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:42.292044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-free Task Classification for Multi-Task Model Merging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinwook Jung, Jungyong Son, Sungyong Baik","submitted_at":"2026-06-21T16:51:29Z","abstract_excerpt":"Ever since the advent of foundation models and the pre-training-finetuning paradigm, there have been numerous efforts to merge multiple task-specific experts into a single multi-task model. Prior work largely focuses on finding a single merged model, but it often underperforms individual experts due to parameter interference. To resolve this, dynamic model merging employs routing to activate task-relevant parameters per input. However, existing routers typically require either additional training with abundant labeled datasets or assume the access to task IDs of each input at inference time. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22589","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/2606.22589/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.22589","created_at":"2026-06-23T02:13:42.292089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22589v1","created_at":"2026-06-23T02:13:42.292089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22589","created_at":"2026-06-23T02:13:42.292089+00:00"},{"alias_kind":"pith_short_12","alias_value":"67AHLDEPTTEJ","created_at":"2026-06-23T02:13:42.292089+00:00"},{"alias_kind":"pith_short_16","alias_value":"67AHLDEPTTEJZOOQ","created_at":"2026-06-23T02:13:42.292089+00:00"},{"alias_kind":"pith_short_8","alias_value":"67AHLDEP","created_at":"2026-06-23T02:13:42.292089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB","json":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB.json","graph_json":"https://pith.science/api/pith-number/67AHLDEPTTEJZOOQH3WLBG63JB/graph.json","events_json":"https://pith.science/api/pith-number/67AHLDEPTTEJZOOQH3WLBG63JB/events.json","paper":"https://pith.science/paper/67AHLDEP"},"agent_actions":{"view_html":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB","download_json":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB.json","view_paper":"https://pith.science/paper/67AHLDEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22589&json=true","fetch_graph":"https://pith.science/api/pith-number/67AHLDEPTTEJZOOQH3WLBG63JB/graph.json","fetch_events":"https://pith.science/api/pith-number/67AHLDEPTTEJZOOQH3WLBG63JB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB/action/storage_attestation","attest_author":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB/action/author_attestation","sign_citation":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB/action/citation_signature","submit_replication":"https://pith.science/pith/67AHLDEPTTEJZOOQH3WLBG63JB/action/replication_record"}},"created_at":"2026-06-23T02:13:42.292089+00:00","updated_at":"2026-06-23T02:13:42.292089+00:00"}