{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:B3XV2I5MYNG6OTGO3ZQOSKWHHL","short_pith_number":"pith:B3XV2I5M","canonical_record":{"source":{"id":"2607.17593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:22:02Z","cross_cats_sorted":[],"title_canon_sha256":"560e7f280e1722d444a22c34ea1a7b432ab90d8ccbf11bdff985f5e91ae940b6","abstract_canon_sha256":"0b8b781a9ac0ee4c796a4d941440948bc26aab848dd20ec93980da067e4499a2"},"schema_version":"1.0"},"canonical_sha256":"0eef5d23acc34de74ccede60e92ac73ad130196486cc476b8f8c105328627572","source":{"kind":"arxiv","id":"2607.17593","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17593","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17593v1","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17593","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"B3XV2I5MYNG6","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"B3XV2I5MYNG6OTGO","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"B3XV2I5M","created_at":"2026-07-21T01:21:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:B3XV2I5MYNG6OTGO3ZQOSKWHHL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.17593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:22:02Z","cross_cats_sorted":[],"title_canon_sha256":"560e7f280e1722d444a22c34ea1a7b432ab90d8ccbf11bdff985f5e91ae940b6","abstract_canon_sha256":"0b8b781a9ac0ee4c796a4d941440948bc26aab848dd20ec93980da067e4499a2"},"schema_version":"1.0"},"canonical_sha256":"0eef5d23acc34de74ccede60e92ac73ad130196486cc476b8f8c105328627572","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:54.155631Z","signature_b64":"PGTOTC/p2pMSafo8T7EipIcVKw3Pu28V9ipYeBWEs+tYndDxOCc819GWMfk5LUf+ojsS/pwWcpfzDcKgr1qfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eef5d23acc34de74ccede60e92ac73ad130196486cc476b8f8c105328627572","last_reissued_at":"2026-07-21T01:21:54.154760Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:54.154760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.17593","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":"2026-07-21T01:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bobJwUtoZETp2QPe4zsPBmtuZiRNiBlK6w9TDArTjAdUdVCg0ujcrYffOG0y/uL9kHyWrxGiWDa5bJddCyQ9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:03:52.690864Z"},"content_sha256":"0bc3fbaab7731801601993a6e411280e09a517238477147756a532bf5be1a7f1","schema_version":"1.0","event_id":"sha256:0bc3fbaab7731801601993a6e411280e09a517238477147756a532bf5be1a7f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:B3XV2I5MYNG6OTGO3ZQOSKWHHL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyuan Zhang, Kai Jiang, Xuelong Li, Xueru Bai, Zisong Lin","submitted_at":"2026-07-20T06:22:02Z","abstract_excerpt":"Class Incremental Learning (CIL) aims to learn new concepts consistently from a data stream without forgetting. Unlike typical CIL methods which need to learn a model from scratch, pre-trained model (PTM) can easily adapt to a new task with fine-tuning. However, existing PTM-based CIL methods fail to achieve a trade-off between performance and computational expenditure, i.e., they either adopt the same parameter space so that leading catastrophic forgetting, or expand a new branch for each task but adding more computational cost. To this end, we propose MetrIc Learning with Expandable Subspace"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17593","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/2607.17593/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":"2026-07-21T01:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6SkLKyxKT0zKMsBN9A6+CgeAuZ9VyYg9LMJlvRz0nMcKUJC90oQQ1z+5+MBpH0C+AIrgx6IZ0vso1AFP1+rRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:03:52.691359Z"},"content_sha256":"5d6e92d6e2242fb4e6a8b40cb4b21dce2fb0c54874d1a1e1d10f5e13c9990d61","schema_version":"1.0","event_id":"sha256:5d6e92d6e2242fb4e6a8b40cb4b21dce2fb0c54874d1a1e1d10f5e13c9990d61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3XV2I5MYNG6OTGO3ZQOSKWHHL/bundle.json","state_url":"https://pith.science/pith/B3XV2I5MYNG6OTGO3ZQOSKWHHL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3XV2I5MYNG6OTGO3ZQOSKWHHL/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":"2026-08-04T19:03:52Z","links":{"resolver":"https://pith.science/pith/B3XV2I5MYNG6OTGO3ZQOSKWHHL","bundle":"https://pith.science/pith/B3XV2I5MYNG6OTGO3ZQOSKWHHL/bundle.json","state":"https://pith.science/pith/B3XV2I5MYNG6OTGO3ZQOSKWHHL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3XV2I5MYNG6OTGO3ZQOSKWHHL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B3XV2I5MYNG6OTGO3ZQOSKWHHL","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":"0b8b781a9ac0ee4c796a4d941440948bc26aab848dd20ec93980da067e4499a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:22:02Z","title_canon_sha256":"560e7f280e1722d444a22c34ea1a7b432ab90d8ccbf11bdff985f5e91ae940b6"},"schema_version":"1.0","source":{"id":"2607.17593","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17593","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17593v1","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17593","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"B3XV2I5MYNG6","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"B3XV2I5MYNG6OTGO","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"B3XV2I5M","created_at":"2026-07-21T01:21:54Z"}],"graph_snapshots":[{"event_id":"sha256:5d6e92d6e2242fb4e6a8b40cb4b21dce2fb0c54874d1a1e1d10f5e13c9990d61","target":"graph","created_at":"2026-07-21T01:21:54Z","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/2607.17593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Class Incremental Learning (CIL) aims to learn new concepts consistently from a data stream without forgetting. Unlike typical CIL methods which need to learn a model from scratch, pre-trained model (PTM) can easily adapt to a new task with fine-tuning. However, existing PTM-based CIL methods fail to achieve a trade-off between performance and computational expenditure, i.e., they either adopt the same parameter space so that leading catastrophic forgetting, or expand a new branch for each task but adding more computational cost. To this end, we propose MetrIc Learning with Expandable Subspace","authors_text":"Hongyuan Zhang, Kai Jiang, Xuelong Li, Xueru Bai, Zisong Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:22:02Z","title":"Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17593","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":"sha256:0bc3fbaab7731801601993a6e411280e09a517238477147756a532bf5be1a7f1","target":"record","created_at":"2026-07-21T01:21:54Z","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":"0b8b781a9ac0ee4c796a4d941440948bc26aab848dd20ec93980da067e4499a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:22:02Z","title_canon_sha256":"560e7f280e1722d444a22c34ea1a7b432ab90d8ccbf11bdff985f5e91ae940b6"},"schema_version":"1.0","source":{"id":"2607.17593","kind":"arxiv","version":1}},"canonical_sha256":"0eef5d23acc34de74ccede60e92ac73ad130196486cc476b8f8c105328627572","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0eef5d23acc34de74ccede60e92ac73ad130196486cc476b8f8c105328627572","first_computed_at":"2026-07-21T01:21:54.154760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:54.154760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PGTOTC/p2pMSafo8T7EipIcVKw3Pu28V9ipYeBWEs+tYndDxOCc819GWMfk5LUf+ojsS/pwWcpfzDcKgr1qfCA==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:54.155631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17593","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bc3fbaab7731801601993a6e411280e09a517238477147756a532bf5be1a7f1","sha256:5d6e92d6e2242fb4e6a8b40cb4b21dce2fb0c54874d1a1e1d10f5e13c9990d61"],"state_sha256":"c41dcbfa48b8e9b8c08252e30beb9ef8cd99002af1c3733225a15e257c4d104f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Vj7idi6IMaraRrgC6VQn730NS2tUWXtTPXQkvSxhz5g36I92rLuz20Ne981da0Xmz2aEOlBI9yBrzPuRuIQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:03:52.695157Z","bundle_sha256":"161eb37e94c5dd1fcc57ca3b0815313a297fb145f7f9b15df49b477b66134809"}}