{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RL42Y5NVQJAMYLNJSCIWM3ELQK","short_pith_number":"pith:RL42Y5NV","schema_version":"1.0","canonical_sha256":"8af9ac75b58240cc2da99091666c8b82b6efe723e396eb03835079909025002a","source":{"kind":"arxiv","id":"2608.04593","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DS"],"primary_cat":"cs.LG","authors_text":"Puspa Raj Adhikari, Sudip Laudari","submitted_at":"2026-08-05T08:56:17Z","abstract_excerpt":"Echo State Networks (ESNs) offer an efficient framework for temporal prediction, but their randomly initialized reservoirs are often over-parameterized and dynamically redundant. Existing pruning methods largely rely on static connectivity or activation statistics, which may overlook neurons that shape input-driven state transitions. We propose Dynamical Mode Pruning (DMP), a reservoir pruning method that ranks neurons by their contribution to dominant transition modes obtained from a trajectory-averaged Jacobian Gramian. DMP removes low-impact units and retrains only the readout. Experiments "},"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":"2608.04593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-05T08:56:17Z","cross_cats_sorted":["cs.AI","math.DS"],"title_canon_sha256":"9a5d63fe4e61cbb25e77cebfe70d05f85e84e0675cb303fdcc56dcd511adef27","abstract_canon_sha256":"17c38c45c38864e0561614bb171f3fa60eea3eedbd28ef378d749215846afc92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:36:14.003565Z","signature_b64":"NVy8/7mt1EHFX8pKkKPaRNA5zwzGlbpn9tuBDLQeml0rsqpwMtPypYpX4u8mU4OBS7GEuSbi0vM85ZbC5WgWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8af9ac75b58240cc2da99091666c8b82b6efe723e396eb03835079909025002a","last_reissued_at":"2026-08-06T01:36:14.002106Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:36:14.002106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.DS"],"primary_cat":"cs.LG","authors_text":"Puspa Raj Adhikari, Sudip Laudari","submitted_at":"2026-08-05T08:56:17Z","abstract_excerpt":"Echo State Networks (ESNs) offer an efficient framework for temporal prediction, but their randomly initialized reservoirs are often over-parameterized and dynamically redundant. Existing pruning methods largely rely on static connectivity or activation statistics, which may overlook neurons that shape input-driven state transitions. We propose Dynamical Mode Pruning (DMP), a reservoir pruning method that ranks neurons by their contribution to dominant transition modes obtained from a trajectory-averaged Jacobian Gramian. DMP removes low-impact units and retrains only the readout. Experiments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04593","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/2608.04593/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":"2608.04593","created_at":"2026-08-06T01:36:14.003859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04593v1","created_at":"2026-08-06T01:36:14.003859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04593","created_at":"2026-08-06T01:36:14.003859+00:00"},{"alias_kind":"pith_short_12","alias_value":"RL42Y5NVQJAM","created_at":"2026-08-06T01:36:14.003859+00:00"},{"alias_kind":"pith_short_16","alias_value":"RL42Y5NVQJAMYLNJ","created_at":"2026-08-06T01:36:14.003859+00:00"},{"alias_kind":"pith_short_8","alias_value":"RL42Y5NV","created_at":"2026-08-06T01:36:14.003859+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/RL42Y5NVQJAMYLNJSCIWM3ELQK","json":"https://pith.science/pith/RL42Y5NVQJAMYLNJSCIWM3ELQK.json","graph_json":"https://pith.science/api/pith-number/RL42Y5NVQJAMYLNJSCIWM3ELQK/graph.json","events_json":"https://pith.science/api/pith-number/RL42Y5NVQJAMYLNJSCIWM3ELQK/events.json","paper":"https://pith.science/paper/RL42Y5NV"},"agent_actions":{"view_html":"https://pith.science/pith/RL42Y5NVQJAMYLNJSCIWM3ELQK","download_json":"https://pith.science/pith/RL42Y5NVQJAMYLNJSCIWM3ELQK.json","view_paper":"https://pith.science/paper/RL42Y5NV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04593&json=true","fetch_graph":"https://pith.science/api/pith-number/RL42Y5NVQJAMYLNJSCIWM3ELQK/graph.json","fetch_events":"https://pith.science/api/pith-number/RL42Y5NVQJAMYLNJSCIWM3ELQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RL42Y5NVQJAMYLNJSCIWM3ELQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RL42Y5NVQJAMYLNJSCIWM3ELQK/action/storage_attestation","attest_author":"https://pith.science/pith/RL42Y5NVQJAMYLNJSCIWM3ELQK/action/author_attestation","sign_citation":"https://pith.science/pith/RL42Y5NVQJAMYLNJSCIWM3ELQK/action/citation_signature","submit_replication":"https://pith.science/pith/RL42Y5NVQJAMYLNJSCIWM3ELQK/action/replication_record"}},"created_at":"2026-08-06T01:36:14.003859+00:00","updated_at":"2026-08-06T01:36:14.003859+00:00"}