{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PYBTA3MDWOKTE24BGL42J4XVKX","short_pith_number":"pith:PYBTA3MD","schema_version":"1.0","canonical_sha256":"7e03306d83b395326b8132f9a4f2f555d99a62cc73d05aead0d5ae6011425747","source":{"kind":"arxiv","id":"2409.06706","version":3},"attestation_state":"computed","paper":{"title":"SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Cheng-Ching Tseng, Chun-Kai Fan, Gaole Dai, Qizhe Zhang, Shanghang Zhang, Tiejun Huang, Yiming Tang, Yuan Zhang, Yulu Gan, Zhi Zhang","submitted_at":"2024-08-24T03:27:29Z","abstract_excerpt":"Advances in Parameter-Efficient Fine-Tuning (PEFT) bridged the performance gap with Full Fine-Tuning (FFT) through sophisticated analysis of pre-trained parameter spaces. Starting from drawing insights from Neural Engrams (NE) in Biological Neural Networks (BNNs), we establish a connection between the low-rank property observed during PEFT's parameter space shifting and neurobiological mechanisms. This observation leads to our proposed method, Synapse and Neuron (SAN), which decomposes and propagates scaling components from anterior feature adjusting vectors towards posterior weight matrices. "},"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":"2409.06706","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-08-24T03:27:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"94e8401f4ad48a4e1aa914705fbcf3c378171e99dbb3695aa0700cf333b9e10c","abstract_canon_sha256":"64f92f299e099bff33bfbb477dfd87d96d09cc76a1eac834dc7f146875fc0ba0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:15.047789Z","signature_b64":"GAtW6s4eGW6bqbtP/8IlO0Z3J6HQLrslNJQi5HlmZZhjkpSm+UME2+U7LIdFe345Oz1qSULU83z8bbML0rbXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e03306d83b395326b8132f9a4f2f555d99a62cc73d05aead0d5ae6011425747","last_reissued_at":"2026-07-05T10:20:15.047274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:15.047274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Cheng-Ching Tseng, Chun-Kai Fan, Gaole Dai, Qizhe Zhang, Shanghang Zhang, Tiejun Huang, Yiming Tang, Yuan Zhang, Yulu Gan, Zhi Zhang","submitted_at":"2024-08-24T03:27:29Z","abstract_excerpt":"Advances in Parameter-Efficient Fine-Tuning (PEFT) bridged the performance gap with Full Fine-Tuning (FFT) through sophisticated analysis of pre-trained parameter spaces. Starting from drawing insights from Neural Engrams (NE) in Biological Neural Networks (BNNs), we establish a connection between the low-rank property observed during PEFT's parameter space shifting and neurobiological mechanisms. This observation leads to our proposed method, Synapse and Neuron (SAN), which decomposes and propagates scaling components from anterior feature adjusting vectors towards posterior weight matrices. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06706","kind":"arxiv","version":3},"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/2409.06706/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":"2409.06706","created_at":"2026-07-05T10:20:15.047344+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06706v3","created_at":"2026-07-05T10:20:15.047344+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06706","created_at":"2026-07-05T10:20:15.047344+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYBTA3MDWOKT","created_at":"2026-07-05T10:20:15.047344+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYBTA3MDWOKTE24B","created_at":"2026-07-05T10:20:15.047344+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYBTA3MD","created_at":"2026-07-05T10:20:15.047344+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.18235","citing_title":"Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX","json":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX.json","graph_json":"https://pith.science/api/pith-number/PYBTA3MDWOKTE24BGL42J4XVKX/graph.json","events_json":"https://pith.science/api/pith-number/PYBTA3MDWOKTE24BGL42J4XVKX/events.json","paper":"https://pith.science/paper/PYBTA3MD"},"agent_actions":{"view_html":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX","download_json":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX.json","view_paper":"https://pith.science/paper/PYBTA3MD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06706&json=true","fetch_graph":"https://pith.science/api/pith-number/PYBTA3MDWOKTE24BGL42J4XVKX/graph.json","fetch_events":"https://pith.science/api/pith-number/PYBTA3MDWOKTE24BGL42J4XVKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX/action/storage_attestation","attest_author":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX/action/author_attestation","sign_citation":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX/action/citation_signature","submit_replication":"https://pith.science/pith/PYBTA3MDWOKTE24BGL42J4XVKX/action/replication_record"}},"created_at":"2026-07-05T10:20:15.047344+00:00","updated_at":"2026-07-05T10:20:15.047344+00:00"}