{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T7LUGKLWYGNC7XSK6P5PRBC3T7","short_pith_number":"pith:T7LUGKLW","schema_version":"1.0","canonical_sha256":"9fd7432976c19a2fde4af3faf8845b9fc1f9981485b69801f9f479e393d162f4","source":{"kind":"arxiv","id":"2605.25170","version":1},"attestation_state":"computed","paper":{"title":"Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.RO"],"primary_cat":"cs.LG","authors_text":"Kordel K. France, Ovidiu Daescu","submitted_at":"2026-05-24T17:03:30Z","abstract_excerpt":"Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models. Olfactory navigation is a highly dynamic and non-stationary task that benefits from real-time continual learning. We introduce an adaptive framework called Grow-Prune-Freeze (GPF) networks that enable an agent to continually learn through growing, pruning, and freezing early layers of its policy in response to world complexity. Grounding GPFs in non-linear random matrix theory, we show that the work of Pennington & Worth (2017) can be extended from "},"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":"2605.25170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-24T17:03:30Z","cross_cats_sorted":["cs.AI","cs.ET","cs.RO"],"title_canon_sha256":"47438bd184ac299afeb503aa81c831555a7ba59e055c334e1bee727ea9600dd6","abstract_canon_sha256":"227918a5ec99cecdd97712df6d0129cef42fa96a9e21f754f44256b3c75a788c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:21.204366Z","signature_b64":"x6EsIuNnPLgNqox/lz7Y7bGqpL9wrCRIH/Lt0PI4lSa2gO/4tV148fI3fOg7BowsNnUdxLq38kFuhnUJpz5oAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fd7432976c19a2fde4af3faf8845b9fc1f9981485b69801f9f479e393d162f4","last_reissued_at":"2026-05-26T02:04:21.203572Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:21.203572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.RO"],"primary_cat":"cs.LG","authors_text":"Kordel K. France, Ovidiu Daescu","submitted_at":"2026-05-24T17:03:30Z","abstract_excerpt":"Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models. Olfactory navigation is a highly dynamic and non-stationary task that benefits from real-time continual learning. We introduce an adaptive framework called Grow-Prune-Freeze (GPF) networks that enable an agent to continually learn through growing, pruning, and freezing early layers of its policy in response to world complexity. Grounding GPFs in non-linear random matrix theory, we show that the work of Pennington & Worth (2017) can be extended from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25170","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/2605.25170/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":"2605.25170","created_at":"2026-05-26T02:04:21.203699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25170v1","created_at":"2026-05-26T02:04:21.203699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25170","created_at":"2026-05-26T02:04:21.203699+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7LUGKLWYGNC","created_at":"2026-05-26T02:04:21.203699+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7LUGKLWYGNC7XSK","created_at":"2026-05-26T02:04:21.203699+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7LUGKLW","created_at":"2026-05-26T02:04:21.203699+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/T7LUGKLWYGNC7XSK6P5PRBC3T7","json":"https://pith.science/pith/T7LUGKLWYGNC7XSK6P5PRBC3T7.json","graph_json":"https://pith.science/api/pith-number/T7LUGKLWYGNC7XSK6P5PRBC3T7/graph.json","events_json":"https://pith.science/api/pith-number/T7LUGKLWYGNC7XSK6P5PRBC3T7/events.json","paper":"https://pith.science/paper/T7LUGKLW"},"agent_actions":{"view_html":"https://pith.science/pith/T7LUGKLWYGNC7XSK6P5PRBC3T7","download_json":"https://pith.science/pith/T7LUGKLWYGNC7XSK6P5PRBC3T7.json","view_paper":"https://pith.science/paper/T7LUGKLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25170&json=true","fetch_graph":"https://pith.science/api/pith-number/T7LUGKLWYGNC7XSK6P5PRBC3T7/graph.json","fetch_events":"https://pith.science/api/pith-number/T7LUGKLWYGNC7XSK6P5PRBC3T7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7LUGKLWYGNC7XSK6P5PRBC3T7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7LUGKLWYGNC7XSK6P5PRBC3T7/action/storage_attestation","attest_author":"https://pith.science/pith/T7LUGKLWYGNC7XSK6P5PRBC3T7/action/author_attestation","sign_citation":"https://pith.science/pith/T7LUGKLWYGNC7XSK6P5PRBC3T7/action/citation_signature","submit_replication":"https://pith.science/pith/T7LUGKLWYGNC7XSK6P5PRBC3T7/action/replication_record"}},"created_at":"2026-05-26T02:04:21.203699+00:00","updated_at":"2026-05-26T02:04:21.203699+00:00"}