{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UGO33OA3KPRNFRPRNKST6IXPQ7","short_pith_number":"pith:UGO33OA3","schema_version":"1.0","canonical_sha256":"a19dbdb81b53e2d2c5f16aa53f22ef87c9ae04680645d456c0566b0077c86795","source":{"kind":"arxiv","id":"2502.10743","version":2},"attestation_state":"computed","paper":{"title":"1bit-Merging: Dynamic Quantized Merging for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowei He, Han Wu, Linqi Song, Mingxuan Yuan, Shuqi Liu, Xiongwei Han, Yuxuan Yao, Zehua Liu","submitted_at":"2025-02-15T09:47:50Z","abstract_excerpt":"Recent advances in large language models have led to specialized models excelling in specific domains, creating a need for efficient model merging techniques. While traditional merging approaches combine parameters into a single static model, they often compromise task-specific performance. However, task-specific routing methods maintain accuracy but introduce substantial storage overhead. We present \\texttt{1bit}-Merging, a novel framework that integrates task-specific routing with 1-bit quantized task vectors to balance performance and storage efficiency. Our approach leverages the observati"},"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":"2502.10743","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-15T09:47:50Z","cross_cats_sorted":[],"title_canon_sha256":"997fc1d5b62b27d56bb929cb7d52678977b8f0ed0e305edeb087fc2ee342425b","abstract_canon_sha256":"6659e5497b3e3e8eadf530d663b7e9138e78178f651af03c95f1bb75f4096ae1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:16.493437Z","signature_b64":"vn1MC/bKNAiAsBZvIYXasyFG0HhH18z2rlr7SjQ3GDlOkjC9ZVh+PENCh9Hs5Yv8yGldnn22RTtQpiwTYsrJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a19dbdb81b53e2d2c5f16aa53f22ef87c9ae04680645d456c0566b0077c86795","last_reissued_at":"2026-07-05T11:08:16.492886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:16.492886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"1bit-Merging: Dynamic Quantized Merging for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowei He, Han Wu, Linqi Song, Mingxuan Yuan, Shuqi Liu, Xiongwei Han, Yuxuan Yao, Zehua Liu","submitted_at":"2025-02-15T09:47:50Z","abstract_excerpt":"Recent advances in large language models have led to specialized models excelling in specific domains, creating a need for efficient model merging techniques. While traditional merging approaches combine parameters into a single static model, they often compromise task-specific performance. However, task-specific routing methods maintain accuracy but introduce substantial storage overhead. We present \\texttt{1bit}-Merging, a novel framework that integrates task-specific routing with 1-bit quantized task vectors to balance performance and storage efficiency. Our approach leverages the observati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10743","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/2502.10743/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":"2502.10743","created_at":"2026-07-05T11:08:16.492964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10743v2","created_at":"2026-07-05T11:08:16.492964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10743","created_at":"2026-07-05T11:08:16.492964+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGO33OA3KPRN","created_at":"2026-07-05T11:08:16.492964+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGO33OA3KPRNFRPR","created_at":"2026-07-05T11:08:16.492964+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGO33OA3","created_at":"2026-07-05T11:08:16.492964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08124","citing_title":"Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7","json":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7.json","graph_json":"https://pith.science/api/pith-number/UGO33OA3KPRNFRPRNKST6IXPQ7/graph.json","events_json":"https://pith.science/api/pith-number/UGO33OA3KPRNFRPRNKST6IXPQ7/events.json","paper":"https://pith.science/paper/UGO33OA3"},"agent_actions":{"view_html":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7","download_json":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7.json","view_paper":"https://pith.science/paper/UGO33OA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10743&json=true","fetch_graph":"https://pith.science/api/pith-number/UGO33OA3KPRNFRPRNKST6IXPQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/UGO33OA3KPRNFRPRNKST6IXPQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7/action/storage_attestation","attest_author":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7/action/author_attestation","sign_citation":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7/action/citation_signature","submit_replication":"https://pith.science/pith/UGO33OA3KPRNFRPRNKST6IXPQ7/action/replication_record"}},"created_at":"2026-07-05T11:08:16.492964+00:00","updated_at":"2026-07-05T11:08:16.492964+00:00"}