{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NCMGNTUYEODHYRFZJHVTI5JAKN","short_pith_number":"pith:NCMGNTUY","canonical_record":{"source":{"id":"2606.30182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T11:57:32Z","cross_cats_sorted":[],"title_canon_sha256":"d8186f1104953768c9e2ce34552b1f09771e84b07a53c042136b37299664aed2","abstract_canon_sha256":"c1a813e0939fd81a00d08f5a374f83bb70e42cd149329ef407396ea79f08b65a"},"schema_version":"1.0"},"canonical_sha256":"689866ce9823867c44b949eb347520536ca057a134bfb10ff7d928c3686efdb9","source":{"kind":"arxiv","id":"2606.30182","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30182","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30182v1","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30182","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"NCMGNTUYEODH","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"pith_short_16","alias_value":"NCMGNTUYEODHYRFZ","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"pith_short_8","alias_value":"NCMGNTUY","created_at":"2026-06-30T02:17:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NCMGNTUYEODHYRFZJHVTI5JAKN","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T11:57:32Z","cross_cats_sorted":[],"title_canon_sha256":"d8186f1104953768c9e2ce34552b1f09771e84b07a53c042136b37299664aed2","abstract_canon_sha256":"c1a813e0939fd81a00d08f5a374f83bb70e42cd149329ef407396ea79f08b65a"},"schema_version":"1.0"},"canonical_sha256":"689866ce9823867c44b949eb347520536ca057a134bfb10ff7d928c3686efdb9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:52.836579Z","signature_b64":"akWHM08m7oIJt00fJvaRH2y2U9zomEpEmpwVBEUcC0cD9iehb21guGiA+Uk2QbsBCi4cbceFUt9/g7AsbqcjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"689866ce9823867c44b949eb347520536ca057a134bfb10ff7d928c3686efdb9","last_reissued_at":"2026-06-30T02:17:52.836119Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:52.836119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30182","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IThqn5HaJwueeL0ZigGps/j39mgOBUI2W8fOesw40TYH4Xc5jpJNyndDLfRN5wm1sIUkza3jKzKS+oDG9uquDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T20:11:11.776673Z"},"content_sha256":"6c9d1cf7f8f8fa160b4987622657a0f898da99ec80e71e9006bbd2cb93741798","schema_version":"1.0","event_id":"sha256:6c9d1cf7f8f8fa160b4987622657a0f898da99ec80e71e9006bbd2cb93741798"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NCMGNTUYEODHYRFZJHVTI5JAKN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MirrorCode: AI can rebuild entire programs from behavior alone","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Allen Hart, Daniel O'Connell, David Owen, David Rein, Florian Brand, Giles Edkins, Tom Adamczewski","submitted_at":"2026-06-29T11:57:32Z","abstract_excerpt":"AI models are rapidly improving at autonomous coding, as shown by benchmark progress and one-off demonstrations such as AI implementing a C compiler. However, existing coding benchmarks tend to focus on shorter tasks, and one-off demonstrations are hard to compare systematically because they often have some human guidance, and are not standardized or repeated across models. To address these challenges, we introduce MirrorCode, a long-horizon coding benchmark based on reimplementing entire software projects. In MirrorCode, AI agents must replicate the functionalities of an existing program, wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30182","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/2606.30182/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T02:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qrz6d9BkrWnBzw/9pFNt4jWdvBJC4IXAbotmpJoRoeBdwCcu4Sc48FCKxxHtdPKlnAfYWv7JrI7Jx37KrV/5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T20:11:11.777045Z"},"content_sha256":"11a994c120377642e38aa2f7514517719cfac9b6b84c38f85108c805159c903d","schema_version":"1.0","event_id":"sha256:11a994c120377642e38aa2f7514517719cfac9b6b84c38f85108c805159c903d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NCMGNTUYEODHYRFZJHVTI5JAKN/bundle.json","state_url":"https://pith.science/pith/NCMGNTUYEODHYRFZJHVTI5JAKN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NCMGNTUYEODHYRFZJHVTI5JAKN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-01T20:11:11Z","links":{"resolver":"https://pith.science/pith/NCMGNTUYEODHYRFZJHVTI5JAKN","bundle":"https://pith.science/pith/NCMGNTUYEODHYRFZJHVTI5JAKN/bundle.json","state":"https://pith.science/pith/NCMGNTUYEODHYRFZJHVTI5JAKN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NCMGNTUYEODHYRFZJHVTI5JAKN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NCMGNTUYEODHYRFZJHVTI5JAKN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c1a813e0939fd81a00d08f5a374f83bb70e42cd149329ef407396ea79f08b65a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T11:57:32Z","title_canon_sha256":"d8186f1104953768c9e2ce34552b1f09771e84b07a53c042136b37299664aed2"},"schema_version":"1.0","source":{"id":"2606.30182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30182","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30182v1","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30182","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"NCMGNTUYEODH","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"pith_short_16","alias_value":"NCMGNTUYEODHYRFZ","created_at":"2026-06-30T02:17:52Z"},{"alias_kind":"pith_short_8","alias_value":"NCMGNTUY","created_at":"2026-06-30T02:17:52Z"}],"graph_snapshots":[{"event_id":"sha256:11a994c120377642e38aa2f7514517719cfac9b6b84c38f85108c805159c903d","target":"graph","created_at":"2026-06-30T02:17:52Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.30182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI models are rapidly improving at autonomous coding, as shown by benchmark progress and one-off demonstrations such as AI implementing a C compiler. However, existing coding benchmarks tend to focus on shorter tasks, and one-off demonstrations are hard to compare systematically because they often have some human guidance, and are not standardized or repeated across models. To address these challenges, we introduce MirrorCode, a long-horizon coding benchmark based on reimplementing entire software projects. In MirrorCode, AI agents must replicate the functionalities of an existing program, wit","authors_text":"Allen Hart, Daniel O'Connell, David Owen, David Rein, Florian Brand, Giles Edkins, Tom Adamczewski","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T11:57:32Z","title":"MirrorCode: AI can rebuild entire programs from behavior alone"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30182","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6c9d1cf7f8f8fa160b4987622657a0f898da99ec80e71e9006bbd2cb93741798","target":"record","created_at":"2026-06-30T02:17:52Z","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":"c1a813e0939fd81a00d08f5a374f83bb70e42cd149329ef407396ea79f08b65a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T11:57:32Z","title_canon_sha256":"d8186f1104953768c9e2ce34552b1f09771e84b07a53c042136b37299664aed2"},"schema_version":"1.0","source":{"id":"2606.30182","kind":"arxiv","version":1}},"canonical_sha256":"689866ce9823867c44b949eb347520536ca057a134bfb10ff7d928c3686efdb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"689866ce9823867c44b949eb347520536ca057a134bfb10ff7d928c3686efdb9","first_computed_at":"2026-06-30T02:17:52.836119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:52.836119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"akWHM08m7oIJt00fJvaRH2y2U9zomEpEmpwVBEUcC0cD9iehb21guGiA+Uk2QbsBCi4cbceFUt9/g7AsbqcjBg==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:52.836579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c9d1cf7f8f8fa160b4987622657a0f898da99ec80e71e9006bbd2cb93741798","sha256:11a994c120377642e38aa2f7514517719cfac9b6b84c38f85108c805159c903d"],"state_sha256":"ecf7a19235966af471d10b8d96765c8596fe75192e08cd5c650df3fe9c8ffc91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WNKauhtrJSds+dbi4HvtJ4wezHUUv4imDaNxmsj+Afv0Bq6LBOieTEcHTNSLDAycFOF5mYdVpm+9rzL/ycaVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T20:11:11.779060Z","bundle_sha256":"4b014f97aa876e7fd04858754a937ea97bf27538e4fe53676d4799a0f95177c8"}}