{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5NQBBU63AUJIV2EHECEPAMITCF","short_pith_number":"pith:5NQBBU63","schema_version":"1.0","canonical_sha256":"eb6010d3db05128ae8872088f031131169ad64fa6e15897f9a749f0305651137","source":{"kind":"arxiv","id":"2605.22343","version":1},"attestation_state":"computed","paper":{"title":"Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.MA","authors_text":"Chang Xu, Chengcheng Wang, Jianyuan Guo, Qinhua Xie, Shiqi Wang, Wei He","submitted_at":"2026-05-21T11:29:08Z","abstract_excerpt":"Autonomous research systems increasingly make the scientific workflow executable: agents can propose ideas, run code, inspect results, and draft papers. But executable workflows do not by themselves produce research judgment. We analyze where current systems lose trial experience: weak evidence becomes prose, pilot signals become broad claims, memory remains textual, and recurring process failures do not change later behavior. We introduce Sibyl-AutoResearch, a self-evolving AutoResearch framework built around Scientific Trial-and-Error Harnesses. A harness lets agents run bounded trials, pres"},"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":"2605.22343","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-05-21T11:29:08Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"2dfd36b989134e7d61d89f819bd7b98966ae8486daeb9e0328058d40b3d315be","abstract_canon_sha256":"83ec676de5bea3f20fd00e45fcb2895dc4ef81d6815eac992c6312f267bc1eb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:38.756271Z","signature_b64":"ln8MlHLhnmNKp1evikpz/9OmmUr+IHLR6/89gKaoyY8gQZRDI6e18OIVrkKUepiRQvJcux+zZ2EYgh97T0iWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb6010d3db05128ae8872088f031131169ad64fa6e15897f9a749f0305651137","last_reissued_at":"2026-05-22T01:04:38.755644Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:38.755644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.MA","authors_text":"Chang Xu, Chengcheng Wang, Jianyuan Guo, Qinhua Xie, Shiqi Wang, Wei He","submitted_at":"2026-05-21T11:29:08Z","abstract_excerpt":"Autonomous research systems increasingly make the scientific workflow executable: agents can propose ideas, run code, inspect results, and draft papers. But executable workflows do not by themselves produce research judgment. We analyze where current systems lose trial experience: weak evidence becomes prose, pilot signals become broad claims, memory remains textual, and recurring process failures do not change later behavior. We introduce Sibyl-AutoResearch, a self-evolving AutoResearch framework built around Scientific Trial-and-Error Harnesses. A harness lets agents run bounded trials, pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22343","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/2605.22343/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":"2605.22343","created_at":"2026-05-22T01:04:38.755761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22343v1","created_at":"2026-05-22T01:04:38.755761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22343","created_at":"2026-05-22T01:04:38.755761+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NQBBU63AUJI","created_at":"2026-05-22T01:04:38.755761+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NQBBU63AUJIV2EH","created_at":"2026-05-22T01:04:38.755761+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NQBBU63","created_at":"2026-05-22T01:04:38.755761+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/5NQBBU63AUJIV2EHECEPAMITCF","json":"https://pith.science/pith/5NQBBU63AUJIV2EHECEPAMITCF.json","graph_json":"https://pith.science/api/pith-number/5NQBBU63AUJIV2EHECEPAMITCF/graph.json","events_json":"https://pith.science/api/pith-number/5NQBBU63AUJIV2EHECEPAMITCF/events.json","paper":"https://pith.science/paper/5NQBBU63"},"agent_actions":{"view_html":"https://pith.science/pith/5NQBBU63AUJIV2EHECEPAMITCF","download_json":"https://pith.science/pith/5NQBBU63AUJIV2EHECEPAMITCF.json","view_paper":"https://pith.science/paper/5NQBBU63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22343&json=true","fetch_graph":"https://pith.science/api/pith-number/5NQBBU63AUJIV2EHECEPAMITCF/graph.json","fetch_events":"https://pith.science/api/pith-number/5NQBBU63AUJIV2EHECEPAMITCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NQBBU63AUJIV2EHECEPAMITCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NQBBU63AUJIV2EHECEPAMITCF/action/storage_attestation","attest_author":"https://pith.science/pith/5NQBBU63AUJIV2EHECEPAMITCF/action/author_attestation","sign_citation":"https://pith.science/pith/5NQBBU63AUJIV2EHECEPAMITCF/action/citation_signature","submit_replication":"https://pith.science/pith/5NQBBU63AUJIV2EHECEPAMITCF/action/replication_record"}},"created_at":"2026-05-22T01:04:38.755761+00:00","updated_at":"2026-05-22T01:04:38.755761+00:00"}