{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MZACJ7DDOKEQG2TSHJ4WS2TDRB","short_pith_number":"pith:MZACJ7DD","schema_version":"1.0","canonical_sha256":"664024fc637289036a723a79696a6388631c02985c16fa6db26ed9eebd51c51a","source":{"kind":"arxiv","id":"2605.04375","version":2},"attestation_state":"computed","paper":{"title":"Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Experiments can be encoded as declarative configurations that AI agents generate and systems compile to control any lab instrument.","cross_cats":["cs.AI","cs.SY"],"primary_cat":"eess.SY","authors_text":"Ang Chen, Danai Koutra, Hongyi Lin, Patrick Tser Jern Kon, Tongyuan Miao, Venkat Viswanathan, Yuhan Chen, Zhenning Yang","submitted_at":"2026-05-06T00:50:34Z","abstract_excerpt":"To unleash the full potential of AI for Science, we must untether the agents from a purely digital environment. The agent's ability to control and explore in real-world labs is essential because the physical lab remains foundational to scientific discovery. While some tasks can be performed on a computer (e.g., data analysis, running simulated experiments), Eureka moments could occur at any time while operating lab instruments (e.g., when a scientist notices unexpected clues, intuition may prompt a real-time course change). Although autonomous labs are on the rise, which expose programmable AP"},"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":"2605.04375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2026-05-06T00:50:34Z","cross_cats_sorted":["cs.AI","cs.SY"],"title_canon_sha256":"3662944d841f40726e4cff0a9286ee77744fd718e611844598c79cd5432e9444","abstract_canon_sha256":"f2172f23fbff89944dd25236ff66e9becafd9598bac8cc917602bc21566955cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:13.947468Z","signature_b64":"xoJVjOVkrHemM7UdtbIV7QKHaI1H4lI5v/aX9V9UodGI/sucomoD2SyOWlqkDT6WAU9bnOq6GAu2L+OCYvFNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"664024fc637289036a723a79696a6388631c02985c16fa6db26ed9eebd51c51a","last_reissued_at":"2026-05-20T00:03:13.946500Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:13.946500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Experiments can be encoded as declarative configurations that AI agents generate and systems compile to control any lab instrument.","cross_cats":["cs.AI","cs.SY"],"primary_cat":"eess.SY","authors_text":"Ang Chen, Danai Koutra, Hongyi Lin, Patrick Tser Jern Kon, Tongyuan Miao, Venkat Viswanathan, Yuhan Chen, Zhenning Yang","submitted_at":"2026-05-06T00:50:34Z","abstract_excerpt":"To unleash the full potential of AI for Science, we must untether the agents from a purely digital environment. The agent's ability to control and explore in real-world labs is essential because the physical lab remains foundational to scientific discovery. While some tasks can be performed on a computer (e.g., data analysis, running simulated experiments), Eureka moments could occur at any time while operating lab instruments (e.g., when a scientist notices unexpected clues, intuition may prompt a real-time course change). Although autonomous labs are on the rise, which expose programmable AP"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This is a general stack that is science-, lab-, and instrument-independent, representing a novel synthesis across the physical, systems, and intelligence layers to unleash the next breakthrough in AI for Science.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That declarative configurations can adequately capture the complexity, adaptability, and real-time decision-making required for physical experiments, including handling unexpected observations during execution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Experiment-as-Code Labs encodes experiments as declarative configurations that AI agents generate, systems software analyzes and orchestrates, and device APIs execute on physical lab hardware.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Experiments can be encoded as declarative configurations that AI agents generate and systems compile to control any lab instrument.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"16c9f7c27b058c1a81b5efad9d1d8662408dc5cb1e47b96aabe36e73b7b457f3"},"source":{"id":"2605.04375","kind":"arxiv","version":2},"verdict":{"id":"4a57655f-64e2-48bb-9ae1-c4e3d8e3834c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T17:25:42.152041Z","strongest_claim":"This is a general stack that is science-, lab-, and instrument-independent, representing a novel synthesis across the physical, systems, and intelligence layers to unleash the next breakthrough in AI for Science.","one_line_summary":"Experiment-as-Code Labs encodes experiments as declarative configurations that AI agents generate, systems software analyzes and orchestrates, and device APIs execute on physical lab hardware.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That declarative configurations can adequately capture the complexity, adaptability, and real-time decision-making required for physical experiments, including handling unexpected observations during execution.","pith_extraction_headline":"Experiments can be encoded as declarative configurations that AI agents generate and systems compile to control any lab instrument."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.04375/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T23:01:20.053007Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T14:29:50.528113Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"de47bc27c577ff55d558642953c25e3925c4ede784fcd31bfdfa14c4b0de3b06"},"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":"2605.04375","created_at":"2026-05-20T00:03:13.946653+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.04375v2","created_at":"2026-05-20T00:03:13.946653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04375","created_at":"2026-05-20T00:03:13.946653+00:00"},{"alias_kind":"pith_short_12","alias_value":"MZACJ7DDOKEQ","created_at":"2026-05-20T00:03:13.946653+00:00"},{"alias_kind":"pith_short_16","alias_value":"MZACJ7DDOKEQG2TS","created_at":"2026-05-20T00:03:13.946653+00:00"},{"alias_kind":"pith_short_8","alias_value":"MZACJ7DD","created_at":"2026-05-20T00:03:13.946653+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/MZACJ7DDOKEQG2TSHJ4WS2TDRB","json":"https://pith.science/pith/MZACJ7DDOKEQG2TSHJ4WS2TDRB.json","graph_json":"https://pith.science/api/pith-number/MZACJ7DDOKEQG2TSHJ4WS2TDRB/graph.json","events_json":"https://pith.science/api/pith-number/MZACJ7DDOKEQG2TSHJ4WS2TDRB/events.json","paper":"https://pith.science/paper/MZACJ7DD"},"agent_actions":{"view_html":"https://pith.science/pith/MZACJ7DDOKEQG2TSHJ4WS2TDRB","download_json":"https://pith.science/pith/MZACJ7DDOKEQG2TSHJ4WS2TDRB.json","view_paper":"https://pith.science/paper/MZACJ7DD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.04375&json=true","fetch_graph":"https://pith.science/api/pith-number/MZACJ7DDOKEQG2TSHJ4WS2TDRB/graph.json","fetch_events":"https://pith.science/api/pith-number/MZACJ7DDOKEQG2TSHJ4WS2TDRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MZACJ7DDOKEQG2TSHJ4WS2TDRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MZACJ7DDOKEQG2TSHJ4WS2TDRB/action/storage_attestation","attest_author":"https://pith.science/pith/MZACJ7DDOKEQG2TSHJ4WS2TDRB/action/author_attestation","sign_citation":"https://pith.science/pith/MZACJ7DDOKEQG2TSHJ4WS2TDRB/action/citation_signature","submit_replication":"https://pith.science/pith/MZACJ7DDOKEQG2TSHJ4WS2TDRB/action/replication_record"}},"created_at":"2026-05-20T00:03:13.946653+00:00","updated_at":"2026-05-20T00:03:13.946653+00:00"}