{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZIF2GF2SOQK4SD5KAQEPHPTO7C","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"258372495646db310b1e06e2e0435b1889c78ee3a54ef03cfcf6abf0ef294505","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T21:37:09Z","title_canon_sha256":"accbcbb5ed31a9504b76f9d549e57f52d563ff8d470b62c6b2ea4880b48689eb"},"schema_version":"1.0","source":{"id":"2605.15219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15219","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15219v1","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15219","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"ZIF2GF2SOQK4","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"ZIF2GF2SOQK4SD5K","created_at":"2026-05-20T00:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"ZIF2GF2S","created_at":"2026-05-20T00:00:46Z"}],"graph_snapshots":[{"event_id":"sha256:369e5c2d0314a06fa3568a2184ebc70f9f06a24c1fb644f12b7c892193e99a13","target":"graph","created_at":"2026-05-20T00:00:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Under a separate tail-equivalence assumption relating the model's effective discovery distribution to a Zipf law with exponent alpha greater than 1, we prove that the cumulative generation cost required to obtain D distinct genuine discoveries satisfies R_cum(D) = Theta(c_gen D^alpha)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The tail-equivalence assumption relating the model's effective discovery distribution to a Zipf law with exponent alpha greater than 1, which is invoked to derive the asymptotic scaling of cumulative generation cost."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"NOVA models the generate-verify-accumulate-retrain loop as adaptive sampling and proves that cumulative generation cost to obtain D genuine discoveries scales as Theta(c_gen D^alpha) under a Zipf tail-equivalence assumption with alpha greater than 1."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Under a Zipf-law assumption on discovery probabilities, the cost to gather D new AI discoveries grows as D to the power alpha."}],"snapshot_sha256":"dd8725f1e386d2e6938d20bfe51fe63ee845e958182a8c795d81ad45c23f040b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:01:57.275998Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T17:31:18.498417Z","status":"completed","version":"1.0.0"},{"findings_count":2,"name":"doi_compliance","ran_at":"2026-05-19T17:26:34.606049Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.837626Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15219/integrity.json","findings":[{"audited_at":"2026-05-19T17:26:34.606049Z","detected_arxiv_id":null,"detected_doi":"10.1109/TIT.2024.3440661.Prafulla","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/TIT.2024.3440661.Prafulla) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":2,"severity":"advisory","verdict_class":"incontrovertible"},{"audited_at":"2026-05-19T17:26:34.606049Z","detected_arxiv_id":null,"detected_doi":"10.1109/ISIT45174.2021.9518169.11","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/ISIT45174.2021.9518169.11) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":10,"severity":"advisory","verdict_class":"incontrovertible"}],"snapshot_sha256":"3d275e4690e55ada9052eb1bd741698c0336e2d3de37d247e4e3c822f666d5d2","summary":{"advisory":2,"by_detector":{"doi_compliance":{"advisory":2,"critical":0,"informational":0,"total":2}},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can AI systems discover genuinely new knowledge through iterative self improvement, and if so, at what cost? We introduce the NOVA framework, which models the common ``generate, verify, accumulate, retrain'' loop as an adaptive sampling process over a knowledge space. We identify sufficient conditions under which accumulated genuine knowledge eventually covers a finite domain, and show how their violations produce distinct failure modes: contamination, forgetting, exploration failure, and acceptance failure. We then analyze imperfect verification and identify a contamination trap: as easy-to-f","authors_text":"Ken Duffy, Muriel M\\'edard, Salman Avestimehr","cross_cats":["cs.IT","math.IT"],"headline":"Under a Zipf-law assumption on discovery probabilities, the cost to gather D new AI discoveries grows as D to the power alpha.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T21:37:09Z","title":"NOVA: Fundamental Limits of Knowledge Discovery Through AI"},"references":{"count":13,"internal_anchors":2,"resolved_work":13,"sample":[{"cited_arxiv_id":"","doi":"10.1109/isit.2018.8437620","is_internal_anchor":false,"ref_index":1,"title":"Anna Ben-Hamou, Stéphane Boucheron, and Mesrob I","work_id":"ee8c9c83-3ac9-4d3c-9304-75320bf313fa","year":2018},{"cited_arxiv_id":"","doi":"10.1109/tit","is_internal_anchor":false,"ref_index":2,"title":"2024.3440661","work_id":"4a747430-fdf9-4c15-9334-59f7e564e39c","year":2024},{"cited_arxiv_id":"","doi":"10.1109/tsp.2022.3186176","is_internal_anchor":false,"ref_index":3,"title":"Bradley Efron and Ronald Thisted","work_id":"678dedb2-63aa-4614-be07-a673050ca7ac","year":2022},{"cited_arxiv_id":"2308.08998","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Reinforced Self-Training (ReST) for Language Modeling","work_id":"db054f5c-62a3-405b-aae8-43e02c39f672","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Besting Good–Turing: Optimality of non-parametric maximum likelihood for distribution estimation","work_id":"31e68224-2ac6-4f06-882b-a426258827cf","year":null}],"snapshot_sha256":"8c75aee5565769e90388d16bed4dc74cd4b3ba376528f99fdf1f7d75a438454c"},"source":{"id":"2605.15219","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T17:13:38.327509Z","id":"363da110-87dd-47b4-b006-be2c545d6fad","model_set":{"reader":"grok-4.3"},"one_line_summary":"NOVA models the generate-verify-accumulate-retrain loop as adaptive sampling and proves that cumulative generation cost to obtain D genuine discoveries scales as Theta(c_gen D^alpha) under a Zipf tail-equivalence assumption with alpha greater than 1.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Under a Zipf-law assumption on discovery probabilities, the cost to gather D new AI discoveries grows as D to the power alpha.","strongest_claim":"Under a separate tail-equivalence assumption relating the model's effective discovery distribution to a Zipf law with exponent alpha greater than 1, we prove that the cumulative generation cost required to obtain D distinct genuine discoveries satisfies R_cum(D) = Theta(c_gen D^alpha).","weakest_assumption":"The tail-equivalence assumption relating the model's effective discovery distribution to a Zipf law with exponent alpha greater than 1, which is invoked to derive the asymptotic scaling of cumulative generation cost."}},"verdict_id":"363da110-87dd-47b4-b006-be2c545d6fad"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:355dc44aee3258545cdd463ea70e5df8116a9e41b0797a9e2a516fabcd2c075f","target":"record","created_at":"2026-05-20T00:00:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"258372495646db310b1e06e2e0435b1889c78ee3a54ef03cfcf6abf0ef294505","cross_cats_sorted":["cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T21:37:09Z","title_canon_sha256":"accbcbb5ed31a9504b76f9d549e57f52d563ff8d470b62c6b2ea4880b48689eb"},"schema_version":"1.0","source":{"id":"2605.15219","kind":"arxiv","version":1}},"canonical_sha256":"ca0ba317527415c90faa0408f3be6ef88603606f6531a430a733811a81a3d170","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca0ba317527415c90faa0408f3be6ef88603606f6531a430a733811a81a3d170","first_computed_at":"2026-05-20T00:00:46.866984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:46.866984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gmy/2/QLSEJTJjYKzyUnSYdpfH1z/wF20aFIOmuKyHqzHfnOSenGtN89uLyl0KQNvO/k8OMYyyzjZX713tJWDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:46.867794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15219","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:46447481e1b9b2679e27165bf0cab04e8ad65fc5dfd9e4053a0bf6ea27aa6076","sha256:547fb99076d68e2a1fca82901fb7e5df180499a2c6885ec9c1cbebd98a94f547"]}],"invalid_events":[],"applied_event_ids":["sha256:355dc44aee3258545cdd463ea70e5df8116a9e41b0797a9e2a516fabcd2c075f","sha256:369e5c2d0314a06fa3568a2184ebc70f9f06a24c1fb644f12b7c892193e99a13"],"state_sha256":"044764a84ea16f612d1423491046ba57a72819f76f267bf3129c81a5f6cf7b78"}