{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FNKPD3Q7ADWKNALECBAV3Z2IL4","short_pith_number":"pith:FNKPD3Q7","canonical_record":{"source":{"id":"2501.09522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T13:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"e09fe506940edbfc0c27f7c591d42fc9b91d4822fdefe4e94ade9f7727931d6f","abstract_canon_sha256":"586e1474b083552775c5ed075cb3aadacb940545d7900b88ced8d97503114b3f"},"schema_version":"1.0"},"canonical_sha256":"2b54f1ee1f00eca6816410415de7485f06b08fa4e1a0f19fd36f6cd464db82b5","source":{"kind":"arxiv","id":"2501.09522","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09522","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09522v1","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09522","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"FNKPD3Q7ADWK","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"pith_short_16","alias_value":"FNKPD3Q7ADWKNALE","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"pith_short_8","alias_value":"FNKPD3Q7","created_at":"2026-07-05T10:01:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FNKPD3Q7ADWKNALECBAV3Z2IL4","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T13:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"e09fe506940edbfc0c27f7c591d42fc9b91d4822fdefe4e94ade9f7727931d6f","abstract_canon_sha256":"586e1474b083552775c5ed075cb3aadacb940545d7900b88ced8d97503114b3f"},"schema_version":"1.0"},"canonical_sha256":"2b54f1ee1f00eca6816410415de7485f06b08fa4e1a0f19fd36f6cd464db82b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:48.131223Z","signature_b64":"m4TR5EBRpEoVFgJLfn5BnYH0sGuMrZPYjBttrsQVAzzCPASzaSHa9UJrvxeUMzulmq2fhWHzmHwLlUnODh9qBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b54f1ee1f00eca6816410415de7485f06b08fa4e1a0f19fd36f6cd464db82b5","last_reissued_at":"2026-07-05T10:01:48.130747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:48.130747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09522","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":"2026-07-05T10:01:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LaUn1LCk8etl0bSdqa2nc9LO3pPjJF5nmVsuF0np9gFl0+56gxamveEkMVMeYr7MFUbbKA1Bsp4sFc6mrAwZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:38:49.646993Z"},"content_sha256":"834874914678289799702c9321072e588e162ced6e5da77d5dffece8260f6aef","schema_version":"1.0","event_id":"sha256:834874914678289799702c9321072e588e162ced6e5da77d5dffece8260f6aef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FNKPD3Q7ADWKNALECBAV3Z2IL4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anke Tang, Bo Du, Dacheng Tao, Enneng Yang, Han Hu, Li Shen, Yong Luo","submitted_at":"2025-01-16T13:17:24Z","abstract_excerpt":"Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains. Current model merging techniques focus on merging all available models simultaneously, with weight interpolation-based methods being the predominant approaches. However, these conventional approaches are not well-suited for scenarios where models become available sequentially, and they often suffer from high memory requirements and potential interference between tasks. In this study, we propose a training-free projec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09522","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/2501.09522/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":"2026-07-05T10:01:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QHazH5v66YDnwNUElpebcpOi+jC5B2Q9IgaYMm9MuPgQ73Led0rvGezsEqhqvaCvlBTXC5er/MqQBPHKNr/7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:38:49.647519Z"},"content_sha256":"62a7033ffa207975c912a96da21fab0356647bf9ab14708e93b1eec949fb3ef1","schema_version":"1.0","event_id":"sha256:62a7033ffa207975c912a96da21fab0356647bf9ab14708e93b1eec949fb3ef1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FNKPD3Q7ADWKNALECBAV3Z2IL4/bundle.json","state_url":"https://pith.science/pith/FNKPD3Q7ADWKNALECBAV3Z2IL4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FNKPD3Q7ADWKNALECBAV3Z2IL4/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":"2026-08-08T07:38:49Z","links":{"resolver":"https://pith.science/pith/FNKPD3Q7ADWKNALECBAV3Z2IL4","bundle":"https://pith.science/pith/FNKPD3Q7ADWKNALECBAV3Z2IL4/bundle.json","state":"https://pith.science/pith/FNKPD3Q7ADWKNALECBAV3Z2IL4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FNKPD3Q7ADWKNALECBAV3Z2IL4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FNKPD3Q7ADWKNALECBAV3Z2IL4","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":"586e1474b083552775c5ed075cb3aadacb940545d7900b88ced8d97503114b3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T13:17:24Z","title_canon_sha256":"e09fe506940edbfc0c27f7c591d42fc9b91d4822fdefe4e94ade9f7727931d6f"},"schema_version":"1.0","source":{"id":"2501.09522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09522","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09522v1","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09522","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"pith_short_12","alias_value":"FNKPD3Q7ADWK","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"pith_short_16","alias_value":"FNKPD3Q7ADWKNALE","created_at":"2026-07-05T10:01:48Z"},{"alias_kind":"pith_short_8","alias_value":"FNKPD3Q7","created_at":"2026-07-05T10:01:48Z"}],"graph_snapshots":[{"event_id":"sha256:62a7033ffa207975c912a96da21fab0356647bf9ab14708e93b1eec949fb3ef1","target":"graph","created_at":"2026-07-05T10:01:48Z","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/2501.09522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains. Current model merging techniques focus on merging all available models simultaneously, with weight interpolation-based methods being the predominant approaches. However, these conventional approaches are not well-suited for scenarios where models become available sequentially, and they often suffer from high memory requirements and potential interference between tasks. In this study, we propose a training-free projec","authors_text":"Anke Tang, Bo Du, Dacheng Tao, Enneng Yang, Han Hu, Li Shen, Yong Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T13:17:24Z","title":"Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09522","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":"sha256:834874914678289799702c9321072e588e162ced6e5da77d5dffece8260f6aef","target":"record","created_at":"2026-07-05T10:01:48Z","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":"586e1474b083552775c5ed075cb3aadacb940545d7900b88ced8d97503114b3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T13:17:24Z","title_canon_sha256":"e09fe506940edbfc0c27f7c591d42fc9b91d4822fdefe4e94ade9f7727931d6f"},"schema_version":"1.0","source":{"id":"2501.09522","kind":"arxiv","version":1}},"canonical_sha256":"2b54f1ee1f00eca6816410415de7485f06b08fa4e1a0f19fd36f6cd464db82b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b54f1ee1f00eca6816410415de7485f06b08fa4e1a0f19fd36f6cd464db82b5","first_computed_at":"2026-07-05T10:01:48.130747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:48.130747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m4TR5EBRpEoVFgJLfn5BnYH0sGuMrZPYjBttrsQVAzzCPASzaSHa9UJrvxeUMzulmq2fhWHzmHwLlUnODh9qBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:48.131223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:834874914678289799702c9321072e588e162ced6e5da77d5dffece8260f6aef","sha256:62a7033ffa207975c912a96da21fab0356647bf9ab14708e93b1eec949fb3ef1"],"state_sha256":"c5380b0186a2ea5bd3863d4de375b12fa26fbe1a75fd6bc1b0d3ba698ca4022c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KS7dCX7O85PArJm5fFth/+2B8AqO1kJKsIGpd1E9UxitnvgLAAA3Tef6agJg7K+WqMs4e+DFflaXNX+r26HhCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:38:49.651906Z","bundle_sha256":"ebffaafb0b7068a09295552926f971fdb8b812e4c13875a8ef398a8a8e6b5d67"}}