{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ORAMMATQQ3L3BUTJP3CL6IOHOF","short_pith_number":"pith:ORAMMATQ","schema_version":"1.0","canonical_sha256":"7440c6027086d7b0d2697ec4bf21c7714b42496928d7c761e7520148556d0da9","source":{"kind":"arxiv","id":"2607.09059","version":1},"attestation_state":"computed","paper":{"title":"ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kejian Tong, Kunbo Zhang, Lei Fu, Zeyu Wang, Zijing Liu","submitted_at":"2026-07-10T03:03:42Z","abstract_excerpt":"We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic execution, and reflective refinement. A perceptual grounding agent builds object centric scene graphs from raw grids, a latent program policy proposes diverse DSL programs, a symbolic executor verifies candidates on demonstrations, and a reflective agent synthesizes failure driven feedback for the next turn. These agents communicate through a shared differentiable blackboard a"},"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":"2607.09059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-10T03:03:42Z","cross_cats_sorted":[],"title_canon_sha256":"43067712920454f08ea8fdd1b54017598a6b3ec58f1307853f392ea43366f5f8","abstract_canon_sha256":"5deca4a87fbbb1efb5bfcef4fa2c5777a2bf552e8832b2ceb0fb971f79a98a5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:38.503956Z","signature_b64":"1XJSzTqk97PN//sni0TfoWlvQq5OMQbX12FzUZlXZN94R0mqKzWYA5hXneKSsRTYUnit7Q0WG62yFRwXGO37Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7440c6027086d7b0d2697ec4bf21c7714b42496928d7c761e7520148556d0da9","last_reissued_at":"2026-07-13T00:17:38.502647Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:38.502647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kejian Tong, Kunbo Zhang, Lei Fu, Zeyu Wang, Zijing Liu","submitted_at":"2026-07-10T03:03:42Z","abstract_excerpt":"We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic execution, and reflective refinement. A perceptual grounding agent builds object centric scene graphs from raw grids, a latent program policy proposes diverse DSL programs, a symbolic executor verifies candidates on demonstrations, and a reflective agent synthesizes failure driven feedback for the next turn. These agents communicate through a shared differentiable blackboard a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09059","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/2607.09059/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":"2607.09059","created_at":"2026-07-13T00:17:38.503339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09059v1","created_at":"2026-07-13T00:17:38.503339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09059","created_at":"2026-07-13T00:17:38.503339+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORAMMATQQ3L3","created_at":"2026-07-13T00:17:38.503339+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORAMMATQQ3L3BUTJ","created_at":"2026-07-13T00:17:38.503339+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORAMMATQ","created_at":"2026-07-13T00:17:38.503339+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/ORAMMATQQ3L3BUTJP3CL6IOHOF","json":"https://pith.science/pith/ORAMMATQQ3L3BUTJP3CL6IOHOF.json","graph_json":"https://pith.science/api/pith-number/ORAMMATQQ3L3BUTJP3CL6IOHOF/graph.json","events_json":"https://pith.science/api/pith-number/ORAMMATQQ3L3BUTJP3CL6IOHOF/events.json","paper":"https://pith.science/paper/ORAMMATQ"},"agent_actions":{"view_html":"https://pith.science/pith/ORAMMATQQ3L3BUTJP3CL6IOHOF","download_json":"https://pith.science/pith/ORAMMATQQ3L3BUTJP3CL6IOHOF.json","view_paper":"https://pith.science/paper/ORAMMATQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09059&json=true","fetch_graph":"https://pith.science/api/pith-number/ORAMMATQQ3L3BUTJP3CL6IOHOF/graph.json","fetch_events":"https://pith.science/api/pith-number/ORAMMATQQ3L3BUTJP3CL6IOHOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORAMMATQQ3L3BUTJP3CL6IOHOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORAMMATQQ3L3BUTJP3CL6IOHOF/action/storage_attestation","attest_author":"https://pith.science/pith/ORAMMATQQ3L3BUTJP3CL6IOHOF/action/author_attestation","sign_citation":"https://pith.science/pith/ORAMMATQQ3L3BUTJP3CL6IOHOF/action/citation_signature","submit_replication":"https://pith.science/pith/ORAMMATQQ3L3BUTJP3CL6IOHOF/action/replication_record"}},"created_at":"2026-07-13T00:17:38.503339+00:00","updated_at":"2026-07-13T00:17:38.503339+00:00"}