{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PRSC33JANHOBEQN4AKAEHIU4FI","short_pith_number":"pith:PRSC33JA","schema_version":"1.0","canonical_sha256":"7c642ded2069dc1241bc028043a29c2a3e0c9a1560da9d8e93a801e3979e65fa","source":{"kind":"arxiv","id":"2106.13414","version":2},"attestation_state":"computed","paper":{"title":"The Price of Tolerance in Distribution Testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Ayush Jain, Cl\\'ement L. Canonne, Gautam Kamath, Jerry Li","submitted_at":"2021-06-25T03:59:42Z","abstract_excerpt":"We revisit the problem of tolerant distribution testing. That is, given samples from an unknown distribution $p$ over $\\{1, \\dots, n\\}$, is it $\\varepsilon_1$-close to or $\\varepsilon_2$-far from a reference distribution $q$ (in total variation distance)? Despite significant interest over the past decade, this problem is well understood only in the extreme cases. In the noiseless setting (i.e., $\\varepsilon_1 = 0$) the sample complexity is $\\Theta(\\sqrt{n})$, strongly sublinear in the domain size. At the other end of the spectrum, when $\\varepsilon_1 = \\varepsilon_2/2$, the sample complexity j"},"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":"2106.13414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2021-06-25T03:59:42Z","cross_cats_sorted":["cs.IT","math.IT","math.PR","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"3943443233c78659a005c92d322380809c607afc92f17fe0564383141d5ca507","abstract_canon_sha256":"2175528c98a5444849f8abf29620763f4b85e89e57813636635d01180a2ac94f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:13.184913Z","signature_b64":"c+E6qDYKeC16eSpI5OYkhvyvCIp4JcgtLxBPojDm1s0VivvxdGujUTAQU1rB52rVjZlpIU90mWgapnzNyGuJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c642ded2069dc1241bc028043a29c2a3e0c9a1560da9d8e93a801e3979e65fa","last_reissued_at":"2026-07-05T03:30:13.184458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:13.184458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Price of Tolerance in Distribution Testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"Ayush Jain, Cl\\'ement L. Canonne, Gautam Kamath, Jerry Li","submitted_at":"2021-06-25T03:59:42Z","abstract_excerpt":"We revisit the problem of tolerant distribution testing. That is, given samples from an unknown distribution $p$ over $\\{1, \\dots, n\\}$, is it $\\varepsilon_1$-close to or $\\varepsilon_2$-far from a reference distribution $q$ (in total variation distance)? Despite significant interest over the past decade, this problem is well understood only in the extreme cases. In the noiseless setting (i.e., $\\varepsilon_1 = 0$) the sample complexity is $\\Theta(\\sqrt{n})$, strongly sublinear in the domain size. At the other end of the spectrum, when $\\varepsilon_1 = \\varepsilon_2/2$, the sample complexity j"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13414","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/2106.13414/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":"2106.13414","created_at":"2026-07-05T03:30:13.184514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13414v2","created_at":"2026-07-05T03:30:13.184514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13414","created_at":"2026-07-05T03:30:13.184514+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRSC33JANHOB","created_at":"2026-07-05T03:30:13.184514+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRSC33JANHOBEQN4","created_at":"2026-07-05T03:30:13.184514+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRSC33JA","created_at":"2026-07-05T03:30:13.184514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20197","citing_title":"Zero-Shot Attribution for Large Language Models: A Distribution Testing Approach","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI","json":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI.json","graph_json":"https://pith.science/api/pith-number/PRSC33JANHOBEQN4AKAEHIU4FI/graph.json","events_json":"https://pith.science/api/pith-number/PRSC33JANHOBEQN4AKAEHIU4FI/events.json","paper":"https://pith.science/paper/PRSC33JA"},"agent_actions":{"view_html":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI","download_json":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI.json","view_paper":"https://pith.science/paper/PRSC33JA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13414&json=true","fetch_graph":"https://pith.science/api/pith-number/PRSC33JANHOBEQN4AKAEHIU4FI/graph.json","fetch_events":"https://pith.science/api/pith-number/PRSC33JANHOBEQN4AKAEHIU4FI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI/action/storage_attestation","attest_author":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI/action/author_attestation","sign_citation":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI/action/citation_signature","submit_replication":"https://pith.science/pith/PRSC33JANHOBEQN4AKAEHIU4FI/action/replication_record"}},"created_at":"2026-07-05T03:30:13.184514+00:00","updated_at":"2026-07-05T03:30:13.184514+00:00"}