{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7DTCDGGOFFBNWITLXFYXNDXRLM","short_pith_number":"pith:7DTCDGGO","schema_version":"1.0","canonical_sha256":"f8e62198ce2942db226bb971768ef15b3aecff6813c1ca0fdda8d3565ca78124","source":{"kind":"arxiv","id":"2605.24183","version":1},"attestation_state":"computed","paper":{"title":"AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Alexander W. Lee, Anupam Datta, Darek Kleczek, Fuheng Zhao, Julien Tissier, Pawel Liskowski, Ugur Cetintemel","submitted_at":"2026-05-22T20:16:41Z","abstract_excerpt":"We introduce AvalancheBench, a benchmark for evaluating enterprise data agents through \\emph{latent world recovery}. AvalancheBench improves on existing benchmarks in three ways. First, it evaluates analytical understanding rather than pipeline completion: systems are scored on whether they recover the segments, drivers, temporal events, and relationships that explain the data, not merely on whether they execute a workflow or produce a plausible report. Second, it provides ground truth for goal-driven analytics by generating observations from a known latent world, enabling partial credit for i"},"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":"2605.24183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-05-22T20:16:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9bbc455b961e9758ade4e989e558b95de8e39509f829531ca369132e53c1f4e6","abstract_canon_sha256":"befc95f5fad69129e2c20b54614c226a6b22a500e08aa28675f04425d4c82d32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:51.217827Z","signature_b64":"/e+A7cA2BkNQJ9Uq2VrdKBR4BjqCtrvyoNfAeGn8qkH1ZHDCohn/GJyw4HMUtuFWWUKNmDyq0XAFrUQL7kTqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8e62198ce2942db226bb971768ef15b3aecff6813c1ca0fdda8d3565ca78124","last_reissued_at":"2026-05-26T01:02:51.217142Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:51.217142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Alexander W. Lee, Anupam Datta, Darek Kleczek, Fuheng Zhao, Julien Tissier, Pawel Liskowski, Ugur Cetintemel","submitted_at":"2026-05-22T20:16:41Z","abstract_excerpt":"We introduce AvalancheBench, a benchmark for evaluating enterprise data agents through \\emph{latent world recovery}. AvalancheBench improves on existing benchmarks in three ways. First, it evaluates analytical understanding rather than pipeline completion: systems are scored on whether they recover the segments, drivers, temporal events, and relationships that explain the data, not merely on whether they execute a workflow or produce a plausible report. Second, it provides ground truth for goal-driven analytics by generating observations from a known latent world, enabling partial credit for i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24183","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/2605.24183/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":"2605.24183","created_at":"2026-05-26T01:02:51.217234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24183v1","created_at":"2026-05-26T01:02:51.217234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24183","created_at":"2026-05-26T01:02:51.217234+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DTCDGGOFFBN","created_at":"2026-05-26T01:02:51.217234+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DTCDGGOFFBNWITL","created_at":"2026-05-26T01:02:51.217234+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DTCDGGO","created_at":"2026-05-26T01:02:51.217234+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM","json":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM.json","graph_json":"https://pith.science/api/pith-number/7DTCDGGOFFBNWITLXFYXNDXRLM/graph.json","events_json":"https://pith.science/api/pith-number/7DTCDGGOFFBNWITLXFYXNDXRLM/events.json","paper":"https://pith.science/paper/7DTCDGGO"},"agent_actions":{"view_html":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM","download_json":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM.json","view_paper":"https://pith.science/paper/7DTCDGGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24183&json=true","fetch_graph":"https://pith.science/api/pith-number/7DTCDGGOFFBNWITLXFYXNDXRLM/graph.json","fetch_events":"https://pith.science/api/pith-number/7DTCDGGOFFBNWITLXFYXNDXRLM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM/action/storage_attestation","attest_author":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM/action/author_attestation","sign_citation":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM/action/citation_signature","submit_replication":"https://pith.science/pith/7DTCDGGOFFBNWITLXFYXNDXRLM/action/replication_record"}},"created_at":"2026-05-26T01:02:51.217234+00:00","updated_at":"2026-05-26T01:02:51.217234+00:00"}