{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DQIOLBSZ3DIFRCVG2R2AZ42ZKA","short_pith_number":"pith:DQIOLBSZ","schema_version":"1.0","canonical_sha256":"1c10e58659d8d0588aa6d4740cf3595030293e6ceb98ff22659925118ca978be","source":{"kind":"arxiv","id":"2502.10463","version":1},"attestation_state":"computed","paper":{"title":"From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.LG","authors_text":"Guodong Li, Lequan Yu, Qinshuo Liu, Wei Huang, Weiqin Zhao, Yanwen Fang","submitted_at":"2025-02-12T08:12:33Z","abstract_excerpt":"The depth of neural networks is a critical factor for their capability, with deeper models often demonstrating superior performance. Motivated by this, significant efforts have been made to enhance layer aggregation - reusing information from previous layers to better extract features at the current layer, to improve the representational power of deep neural networks. However, previous works have primarily addressed this problem from a discrete-state perspective which is not suitable as the number of network layers grows. This paper novelly treats the outputs from layers as states of a continu"},"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":"2502.10463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T08:12:33Z","cross_cats_sorted":["cs.AI","cs.NI"],"title_canon_sha256":"5c2911062e00b2c93baadbf4f8218feca3def4a99fd410fd912a9e8a166e4fd0","abstract_canon_sha256":"81540e7ff62f42669dca5992b2bd559c1e9cfa3f4a68a237edfb568ac285b841"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:53.097453Z","signature_b64":"BYUUSCUl4koTL0KtjfF4GrJmrQgf0A/iKFtqDuPE/WMMZWxalJ9I24nAVmPF8BFCRao/CCGBjlKqMo5ITBqYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c10e58659d8d0588aa6d4740cf3595030293e6ceb98ff22659925118ca978be","last_reissued_at":"2026-07-05T10:14:53.096945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:53.096945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.LG","authors_text":"Guodong Li, Lequan Yu, Qinshuo Liu, Wei Huang, Weiqin Zhao, Yanwen Fang","submitted_at":"2025-02-12T08:12:33Z","abstract_excerpt":"The depth of neural networks is a critical factor for their capability, with deeper models often demonstrating superior performance. Motivated by this, significant efforts have been made to enhance layer aggregation - reusing information from previous layers to better extract features at the current layer, to improve the representational power of deep neural networks. However, previous works have primarily addressed this problem from a discrete-state perspective which is not suitable as the number of network layers grows. This paper novelly treats the outputs from layers as states of a continu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10463","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/2502.10463/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":"2502.10463","created_at":"2026-07-05T10:14:53.097027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10463v1","created_at":"2026-07-05T10:14:53.097027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10463","created_at":"2026-07-05T10:14:53.097027+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQIOLBSZ3DIF","created_at":"2026-07-05T10:14:53.097027+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQIOLBSZ3DIFRCVG","created_at":"2026-07-05T10:14:53.097027+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQIOLBSZ","created_at":"2026-07-05T10:14:53.097027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28405","citing_title":"Enhancing Layer Interaction Using Key-Correlated Layer Attention","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA","json":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA.json","graph_json":"https://pith.science/api/pith-number/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/graph.json","events_json":"https://pith.science/api/pith-number/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/events.json","paper":"https://pith.science/paper/DQIOLBSZ"},"agent_actions":{"view_html":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA","download_json":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA.json","view_paper":"https://pith.science/paper/DQIOLBSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10463&json=true","fetch_graph":"https://pith.science/api/pith-number/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/graph.json","fetch_events":"https://pith.science/api/pith-number/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/action/storage_attestation","attest_author":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/action/author_attestation","sign_citation":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/action/citation_signature","submit_replication":"https://pith.science/pith/DQIOLBSZ3DIFRCVG2R2AZ42ZKA/action/replication_record"}},"created_at":"2026-07-05T10:14:53.097027+00:00","updated_at":"2026-07-05T10:14:53.097027+00:00"}