{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L3TO7Z2YFTZGCL4M27EB7IVU64","short_pith_number":"pith:L3TO7Z2Y","schema_version":"1.0","canonical_sha256":"5ee6efe7582cf2612f8cd7c81fa2b4f73cb95e53ebece80111eecd50df1d6d89","source":{"kind":"arxiv","id":"2403.11743","version":3},"attestation_state":"computed","paper":{"title":"PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Astrid Berg, David Major, Dimitrios Lenis, Gaia Romana De Paolis, Johannes Novotny, Katja B\\\"uhler, Maria Wimmer, Philip Matthias Winter, Sophia Ulonska, Theresa Neubauer","submitted_at":"2024-03-18T12:55:40Z","abstract_excerpt":"This work addresses flexibility in deep learning by means of transductive reasoning. For adaptation to new data and tasks, e.g., in continual learning, existing methods typically involve tuning learnable parameters or complete re-training from scratch, rendering such approaches unflexible in practice. We argue that the notion of separating computation from memory by the means of transduction can act as a stepping stone for solving these issues. We therefore propose PARMESAN (parameter-free memory search and transduction), a scalable method which leverages a memory module for solving dense pred"},"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":"2403.11743","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T12:55:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"de0294d5e0fc9c4a23b15ced59c3a4e697e25122ee08420671d51689bbcd50b0","abstract_canon_sha256":"64c46844aa4ca09bdfae9500fda8b04332da918adec8483c16144aa0c6c9610c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:09.598216Z","signature_b64":"N6KxFsnJudvaRrCu1LXun3EVOvxNHp81hoHO2Fl2FFq1TVaBgMO7AlSFO0wbBQF+ZxpcqFTdX0VWbHIDLbwEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ee6efe7582cf2612f8cd7c81fa2b4f73cb95e53ebece80111eecd50df1d6d89","last_reissued_at":"2026-07-05T10:53:09.597643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:09.597643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Astrid Berg, David Major, Dimitrios Lenis, Gaia Romana De Paolis, Johannes Novotny, Katja B\\\"uhler, Maria Wimmer, Philip Matthias Winter, Sophia Ulonska, Theresa Neubauer","submitted_at":"2024-03-18T12:55:40Z","abstract_excerpt":"This work addresses flexibility in deep learning by means of transductive reasoning. For adaptation to new data and tasks, e.g., in continual learning, existing methods typically involve tuning learnable parameters or complete re-training from scratch, rendering such approaches unflexible in practice. We argue that the notion of separating computation from memory by the means of transduction can act as a stepping stone for solving these issues. We therefore propose PARMESAN (parameter-free memory search and transduction), a scalable method which leverages a memory module for solving dense pred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11743","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/2403.11743/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":"2403.11743","created_at":"2026-07-05T10:53:09.597712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11743v3","created_at":"2026-07-05T10:53:09.597712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11743","created_at":"2026-07-05T10:53:09.597712+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3TO7Z2YFTZG","created_at":"2026-07-05T10:53:09.597712+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3TO7Z2YFTZGCL4M","created_at":"2026-07-05T10:53:09.597712+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3TO7Z2Y","created_at":"2026-07-05T10:53:09.597712+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/L3TO7Z2YFTZGCL4M27EB7IVU64","json":"https://pith.science/pith/L3TO7Z2YFTZGCL4M27EB7IVU64.json","graph_json":"https://pith.science/api/pith-number/L3TO7Z2YFTZGCL4M27EB7IVU64/graph.json","events_json":"https://pith.science/api/pith-number/L3TO7Z2YFTZGCL4M27EB7IVU64/events.json","paper":"https://pith.science/paper/L3TO7Z2Y"},"agent_actions":{"view_html":"https://pith.science/pith/L3TO7Z2YFTZGCL4M27EB7IVU64","download_json":"https://pith.science/pith/L3TO7Z2YFTZGCL4M27EB7IVU64.json","view_paper":"https://pith.science/paper/L3TO7Z2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11743&json=true","fetch_graph":"https://pith.science/api/pith-number/L3TO7Z2YFTZGCL4M27EB7IVU64/graph.json","fetch_events":"https://pith.science/api/pith-number/L3TO7Z2YFTZGCL4M27EB7IVU64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3TO7Z2YFTZGCL4M27EB7IVU64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3TO7Z2YFTZGCL4M27EB7IVU64/action/storage_attestation","attest_author":"https://pith.science/pith/L3TO7Z2YFTZGCL4M27EB7IVU64/action/author_attestation","sign_citation":"https://pith.science/pith/L3TO7Z2YFTZGCL4M27EB7IVU64/action/citation_signature","submit_replication":"https://pith.science/pith/L3TO7Z2YFTZGCL4M27EB7IVU64/action/replication_record"}},"created_at":"2026-07-05T10:53:09.597712+00:00","updated_at":"2026-07-05T10:53:09.597712+00:00"}