{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QQM7U4YUUDNJ47ODNFWI3QHCQV","short_pith_number":"pith:QQM7U4YU","schema_version":"1.0","canonical_sha256":"8419fa7314a0da9e7dc3696c8dc0e28567c3c3fbe8987ec14336fd5fd1412495","source":{"kind":"arxiv","id":"2605.27469","version":1},"attestation_state":"computed","paper":{"title":"Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ruilin Tang, Yu Hu, Zhong Ye","submitted_at":"2026-05-26T08:41:13Z","abstract_excerpt":"Continual Learning (CL) is a practical paradigm to utilize power of deep pre-trained neural networks, but which pre-trained model has a better ability to balance ``Plasticity-Stability\", deserving to be chosen? The logit shift serves as a natural proxy because it represents the logit shift in CL scenarios. However, obtaining the logit shift requires huge computational cost, which hinders large-scale model selection. Existing theoretical analyses fail to offer an efficient alternative because of the assumption of uniform hidden layer widths, which ignores the structural heterogeneity (variable "},"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":"2605.27469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T08:41:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0eb4196c74ce705ce65e96aeb8d8982bcc43e13f431500c781ab989f12dfec49","abstract_canon_sha256":"e5a960ceb113ebcc849b9af63caac7b79e4c2f91385566c88782b763c4acdc19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T00:05:20.209124Z","signature_b64":"x6OYPDsAneRd5MEGrDApf2s3DF51P4+Nyt4cO9uV5dTJr0LUF65mka7vq+BLfH5O2LwTMPilaBFl+i3XHSJQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8419fa7314a0da9e7dc3696c8dc0e28567c3c3fbe8987ec14336fd5fd1412495","last_reissued_at":"2026-05-28T00:05:20.208480Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T00:05:20.208480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ruilin Tang, Yu Hu, Zhong Ye","submitted_at":"2026-05-26T08:41:13Z","abstract_excerpt":"Continual Learning (CL) is a practical paradigm to utilize power of deep pre-trained neural networks, but which pre-trained model has a better ability to balance ``Plasticity-Stability\", deserving to be chosen? The logit shift serves as a natural proxy because it represents the logit shift in CL scenarios. However, obtaining the logit shift requires huge computational cost, which hinders large-scale model selection. Existing theoretical analyses fail to offer an efficient alternative because of the assumption of uniform hidden layer widths, which ignores the structural heterogeneity (variable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27469","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/2605.27469/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":"2605.27469","created_at":"2026-05-28T00:05:20.208591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27469v1","created_at":"2026-05-28T00:05:20.208591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27469","created_at":"2026-05-28T00:05:20.208591+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQM7U4YUUDNJ","created_at":"2026-05-28T00:05:20.208591+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQM7U4YUUDNJ47OD","created_at":"2026-05-28T00:05:20.208591+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQM7U4YU","created_at":"2026-05-28T00:05:20.208591+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/QQM7U4YUUDNJ47ODNFWI3QHCQV","json":"https://pith.science/pith/QQM7U4YUUDNJ47ODNFWI3QHCQV.json","graph_json":"https://pith.science/api/pith-number/QQM7U4YUUDNJ47ODNFWI3QHCQV/graph.json","events_json":"https://pith.science/api/pith-number/QQM7U4YUUDNJ47ODNFWI3QHCQV/events.json","paper":"https://pith.science/paper/QQM7U4YU"},"agent_actions":{"view_html":"https://pith.science/pith/QQM7U4YUUDNJ47ODNFWI3QHCQV","download_json":"https://pith.science/pith/QQM7U4YUUDNJ47ODNFWI3QHCQV.json","view_paper":"https://pith.science/paper/QQM7U4YU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27469&json=true","fetch_graph":"https://pith.science/api/pith-number/QQM7U4YUUDNJ47ODNFWI3QHCQV/graph.json","fetch_events":"https://pith.science/api/pith-number/QQM7U4YUUDNJ47ODNFWI3QHCQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQM7U4YUUDNJ47ODNFWI3QHCQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQM7U4YUUDNJ47ODNFWI3QHCQV/action/storage_attestation","attest_author":"https://pith.science/pith/QQM7U4YUUDNJ47ODNFWI3QHCQV/action/author_attestation","sign_citation":"https://pith.science/pith/QQM7U4YUUDNJ47ODNFWI3QHCQV/action/citation_signature","submit_replication":"https://pith.science/pith/QQM7U4YUUDNJ47ODNFWI3QHCQV/action/replication_record"}},"created_at":"2026-05-28T00:05:20.208591+00:00","updated_at":"2026-05-28T00:05:20.208591+00:00"}