{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IW5REGCYRNUB5U2QVMIGMZCJY2","short_pith_number":"pith:IW5REGCY","schema_version":"1.0","canonical_sha256":"45bb1218588b681ed350ab10666449c68c68cbccffbd8b62a923817df31a5ca5","source":{"kind":"arxiv","id":"2010.02180","version":3},"attestation_state":"computed","paper":{"title":"Pareto Probing: Trading Off Accuracy for Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adina Williams, Naomi Saphra, Ryan Cotterell, Tiago Pimentel","submitted_at":"2020-10-05T17:27:31Z","abstract_excerpt":"The question of how to probe contextual word representations for linguistic structure in a way that is both principled and useful has seen significant attention recently in the NLP literature. In our contribution to this discussion, we argue for a probe metric that reflects the fundamental trade-off between probe complexity and performance: the Pareto hypervolume. To measure complexity, we present a number of parametric and non-parametric metrics. Our experiments using Pareto hypervolume as an evaluation metric show that probes often do not conform to our expectations -- e.g., why should the n"},"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":"2010.02180","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T17:27:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f1a6d67cc803f4d359319609b44a05cd581f585728d54ef10f2cb7acea68a87","abstract_canon_sha256":"97af3e60539b03a9054f68a80633c36311543690bb3069cc7c7f551a9510621e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:39.883622Z","signature_b64":"MDKaa0C6+ElJVz9sQRRcqDtkUEK5I/NReCoIGtOH/pH694188HNT8baJkjocIlP4sDi2ea/mkZ4spjtxs89CAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45bb1218588b681ed350ab10666449c68c68cbccffbd8b62a923817df31a5ca5","last_reissued_at":"2026-07-05T07:19:39.883126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:39.883126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pareto Probing: Trading Off Accuracy for Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adina Williams, Naomi Saphra, Ryan Cotterell, Tiago Pimentel","submitted_at":"2020-10-05T17:27:31Z","abstract_excerpt":"The question of how to probe contextual word representations for linguistic structure in a way that is both principled and useful has seen significant attention recently in the NLP literature. In our contribution to this discussion, we argue for a probe metric that reflects the fundamental trade-off between probe complexity and performance: the Pareto hypervolume. To measure complexity, we present a number of parametric and non-parametric metrics. Our experiments using Pareto hypervolume as an evaluation metric show that probes often do not conform to our expectations -- e.g., why should the n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02180","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/2010.02180/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":"2010.02180","created_at":"2026-07-05T07:19:39.883186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.02180v3","created_at":"2026-07-05T07:19:39.883186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02180","created_at":"2026-07-05T07:19:39.883186+00:00"},{"alias_kind":"pith_short_12","alias_value":"IW5REGCYRNUB","created_at":"2026-07-05T07:19:39.883186+00:00"},{"alias_kind":"pith_short_16","alias_value":"IW5REGCYRNUB5U2Q","created_at":"2026-07-05T07:19:39.883186+00:00"},{"alias_kind":"pith_short_8","alias_value":"IW5REGCY","created_at":"2026-07-05T07:19:39.883186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01168","citing_title":"Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2","json":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2.json","graph_json":"https://pith.science/api/pith-number/IW5REGCYRNUB5U2QVMIGMZCJY2/graph.json","events_json":"https://pith.science/api/pith-number/IW5REGCYRNUB5U2QVMIGMZCJY2/events.json","paper":"https://pith.science/paper/IW5REGCY"},"agent_actions":{"view_html":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2","download_json":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2.json","view_paper":"https://pith.science/paper/IW5REGCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.02180&json=true","fetch_graph":"https://pith.science/api/pith-number/IW5REGCYRNUB5U2QVMIGMZCJY2/graph.json","fetch_events":"https://pith.science/api/pith-number/IW5REGCYRNUB5U2QVMIGMZCJY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2/action/storage_attestation","attest_author":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2/action/author_attestation","sign_citation":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2/action/citation_signature","submit_replication":"https://pith.science/pith/IW5REGCYRNUB5U2QVMIGMZCJY2/action/replication_record"}},"created_at":"2026-07-05T07:19:39.883186+00:00","updated_at":"2026-07-05T07:19:39.883186+00:00"}