{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:H3YILGZ6DQUX6EKLCLOXRXKTS3","short_pith_number":"pith:H3YILGZ6","schema_version":"1.0","canonical_sha256":"3ef0859b3e1c297f114b12dd78dd5396c9d7e084a3bee529ad5c9451f044c44e","source":{"kind":"arxiv","id":"2010.16263","version":1},"attestation_state":"computed","paper":{"title":"Learning to Unknot","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-th"],"primary_cat":"math.GT","authors_text":"Fabian Ruehle, James Halverson, Piotr Su{\\l}kowski, Sergei Gukov","submitted_at":"2020-10-28T18:00:05Z","abstract_excerpt":"We introduce natural language processing into the study of knot theory, as made natural by the braid word representation of knots. We study the UNKNOT problem of determining whether or not a given knot is the unknot. After describing an algorithm to randomly generate $N$-crossing braids and their knot closures and discussing the induced prior on the distribution of knots, we apply binary classification to the UNKNOT decision problem. We find that the Reformer and shared-QK Transformer network architectures outperform fully-connected networks, though all perform well. Perhaps surprisingly, we f"},"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":"2010.16263","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.GT","submitted_at":"2020-10-28T18:00:05Z","cross_cats_sorted":["cs.LG","hep-th"],"title_canon_sha256":"619ad29f983316909aac50fd2838cec7f7bac73308b33130260351921c0fcdd2","abstract_canon_sha256":"178e3c343cd5c1d17d307b832d36f3051b951c294a487b0999ee459893e838a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:51.341071Z","signature_b64":"oD8aXt7TDwda281b4J8sHw/90yNr+nuhPYlkAYDL5SQOSyQMf+ff3KmcBHECs2PmA23PbXWKwv8nZSzNgE5NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ef0859b3e1c297f114b12dd78dd5396c9d7e084a3bee529ad5c9451f044c44e","last_reissued_at":"2026-07-05T01:47:51.340645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:51.340645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Unknot","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-th"],"primary_cat":"math.GT","authors_text":"Fabian Ruehle, James Halverson, Piotr Su{\\l}kowski, Sergei Gukov","submitted_at":"2020-10-28T18:00:05Z","abstract_excerpt":"We introduce natural language processing into the study of knot theory, as made natural by the braid word representation of knots. We study the UNKNOT problem of determining whether or not a given knot is the unknot. After describing an algorithm to randomly generate $N$-crossing braids and their knot closures and discussing the induced prior on the distribution of knots, we apply binary classification to the UNKNOT decision problem. We find that the Reformer and shared-QK Transformer network architectures outperform fully-connected networks, though all perform well. Perhaps surprisingly, we f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.16263","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/2010.16263/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":"2010.16263","created_at":"2026-07-05T01:47:51.340710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.16263v1","created_at":"2026-07-05T01:47:51.340710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.16263","created_at":"2026-07-05T01:47:51.340710+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3YILGZ6DQUX","created_at":"2026-07-05T01:47:51.340710+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3YILGZ6DQUX6EKL","created_at":"2026-07-05T01:47:51.340710+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3YILGZ6","created_at":"2026-07-05T01:47:51.340710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.15251","citing_title":"Machine Learning Toric Duality in Brane Tilings","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12717","citing_title":"Learning the symmetric group: large from small","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2601.19979","citing_title":"Exploring the holographic entropy cone via reinforcement learning","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3","json":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3.json","graph_json":"https://pith.science/api/pith-number/H3YILGZ6DQUX6EKLCLOXRXKTS3/graph.json","events_json":"https://pith.science/api/pith-number/H3YILGZ6DQUX6EKLCLOXRXKTS3/events.json","paper":"https://pith.science/paper/H3YILGZ6"},"agent_actions":{"view_html":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3","download_json":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3.json","view_paper":"https://pith.science/paper/H3YILGZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.16263&json=true","fetch_graph":"https://pith.science/api/pith-number/H3YILGZ6DQUX6EKLCLOXRXKTS3/graph.json","fetch_events":"https://pith.science/api/pith-number/H3YILGZ6DQUX6EKLCLOXRXKTS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3/action/storage_attestation","attest_author":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3/action/author_attestation","sign_citation":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3/action/citation_signature","submit_replication":"https://pith.science/pith/H3YILGZ6DQUX6EKLCLOXRXKTS3/action/replication_record"}},"created_at":"2026-07-05T01:47:51.340710+00:00","updated_at":"2026-07-05T01:47:51.340710+00:00"}