{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RGTADYYJOKEWITUNNIGE72N4MX","short_pith_number":"pith:RGTADYYJ","schema_version":"1.0","canonical_sha256":"89a601e3097289644e8d6a0c4fe9bc65d6a8316834f45e4ab2490567926a38db","source":{"kind":"arxiv","id":"2211.15120","version":2},"attestation_state":"computed","paper":{"title":"Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Phillip Isola, Tongzhou Wang","submitted_at":"2022-11-28T08:22:26Z","abstract_excerpt":"Asymmetrical distance structures (quasimetrics) are ubiquitous in our lives and are gaining more attention in machine learning applications. Imposing such quasimetric structures in model representations has been shown to improve many tasks, including reinforcement learning (RL) and causal relation learning. In this work, we present four desirable properties in such quasimetric models, and show how prior works fail at them. We propose Interval Quasimetric Embedding (IQE), which is designed to satisfy all four criteria. On three quasimetric learning experiments, IQEs show strong approximation an"},"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":"2211.15120","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T08:22:26Z","cross_cats_sorted":[],"title_canon_sha256":"643a14bf55e51d7a901689e054eb638693f64f2facaf0a39a20c32aad402b30b","abstract_canon_sha256":"a362389474b23e1576c0e1763c9a15e563c2a7bcf5928e6b11b566f32276083e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:45.656036Z","signature_b64":"/6LGLN1s3VNzqYvhf0zgOHS7IlSA4biVYNwuUPvqb4KWpW0euUYggVH9m7pHvgPiWycUcC5uY+w/QAuPyVbaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89a601e3097289644e8d6a0c4fe9bc65d6a8316834f45e4ab2490567926a38db","last_reissued_at":"2026-07-05T07:30:45.655511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:45.655511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Phillip Isola, Tongzhou Wang","submitted_at":"2022-11-28T08:22:26Z","abstract_excerpt":"Asymmetrical distance structures (quasimetrics) are ubiquitous in our lives and are gaining more attention in machine learning applications. Imposing such quasimetric structures in model representations has been shown to improve many tasks, including reinforcement learning (RL) and causal relation learning. In this work, we present four desirable properties in such quasimetric models, and show how prior works fail at them. We propose Interval Quasimetric Embedding (IQE), which is designed to satisfy all four criteria. On three quasimetric learning experiments, IQEs show strong approximation an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15120","kind":"arxiv","version":2},"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/2211.15120/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":"2211.15120","created_at":"2026-07-05T07:30:45.655566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15120v2","created_at":"2026-07-05T07:30:45.655566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15120","created_at":"2026-07-05T07:30:45.655566+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGTADYYJOKEW","created_at":"2026-07-05T07:30:45.655566+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGTADYYJOKEWITUN","created_at":"2026-07-05T07:30:45.655566+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGTADYYJ","created_at":"2026-07-05T07:30:45.655566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20609","citing_title":"Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.10137","citing_title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12651","citing_title":"Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12651","citing_title":"Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic","ref_index":130,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX","json":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX.json","graph_json":"https://pith.science/api/pith-number/RGTADYYJOKEWITUNNIGE72N4MX/graph.json","events_json":"https://pith.science/api/pith-number/RGTADYYJOKEWITUNNIGE72N4MX/events.json","paper":"https://pith.science/paper/RGTADYYJ"},"agent_actions":{"view_html":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX","download_json":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX.json","view_paper":"https://pith.science/paper/RGTADYYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15120&json=true","fetch_graph":"https://pith.science/api/pith-number/RGTADYYJOKEWITUNNIGE72N4MX/graph.json","fetch_events":"https://pith.science/api/pith-number/RGTADYYJOKEWITUNNIGE72N4MX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX/action/storage_attestation","attest_author":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX/action/author_attestation","sign_citation":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX/action/citation_signature","submit_replication":"https://pith.science/pith/RGTADYYJOKEWITUNNIGE72N4MX/action/replication_record"}},"created_at":"2026-07-05T07:30:45.655566+00:00","updated_at":"2026-07-05T07:30:45.655566+00:00"}