{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YNQPV7KAPQGXYPHEXUFOBVU5IU","short_pith_number":"pith:YNQPV7KA","canonical_record":{"source":{"id":"2608.02949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T23:26:06Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"7cf7250aa9444dce34fd25ba1025a8b846f055ee5c61f75c0a5cfb6c7d7eda17","abstract_canon_sha256":"995bb47626254572a2c7bbf1fb4ba6ada9a92fb99bf74cf7d34fe56d0e35f200"},"schema_version":"1.0"},"canonical_sha256":"c360fafd407c0d7c3ce4bd0ae0d69d45173638b2ba433c9b091e21f70416d510","source":{"kind":"arxiv","id":"2608.02949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02949","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02949v1","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02949","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"pith_short_12","alias_value":"YNQPV7KAPQGX","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"pith_short_16","alias_value":"YNQPV7KAPQGXYPHE","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"pith_short_8","alias_value":"YNQPV7KA","created_at":"2026-08-05T00:44:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YNQPV7KAPQGXYPHEXUFOBVU5IU","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T23:26:06Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"7cf7250aa9444dce34fd25ba1025a8b846f055ee5c61f75c0a5cfb6c7d7eda17","abstract_canon_sha256":"995bb47626254572a2c7bbf1fb4ba6ada9a92fb99bf74cf7d34fe56d0e35f200"},"schema_version":"1.0"},"canonical_sha256":"c360fafd407c0d7c3ce4bd0ae0d69d45173638b2ba433c9b091e21f70416d510","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:44:10.708551Z","signature_b64":"W+tiJlKUDLdfs/XzeWM8c31mfQCt9doDc9nvARCAsibO1f89TMNtJb1a1TyQ1IfgAQ+/oreCZOLAPSRd1N1MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c360fafd407c0d7c3ce4bd0ae0d69d45173638b2ba433c9b091e21f70416d510","last_reissued_at":"2026-08-05T00:44:10.705896Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:44:10.705896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02949","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":"2026-08-05T00:44:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sG0esgZcaGrrcR1welXs0X2gGhtS/Dr0xqUymlrAb+r87ZXlnda0rBTNkJ/jtnchXWn6bmkU+prQHwm2PtIuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:13:36.022534Z"},"content_sha256":"8cac1aeded923b676e2615752c7159524b3eecc845a745042ad9176f60271c5e","schema_version":"1.0","event_id":"sha256:8cac1aeded923b676e2615752c7159524b3eecc845a745042ad9176f60271c5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YNQPV7KAPQGXYPHEXUFOBVU5IU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the missing data layer and a potential solution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.AI","authors_text":"Francis F Daniel, Francis Perelman, Marian Basti, Mauro Iba\\~nez","submitted_at":"2026-08-03T23:26:06Z","abstract_excerpt":"Latin America is missing two foundational layers of AI infrastructure: the dataset layer and the benchmark layer. This paper targets the dataset layer. The dataset layer faces two compounding problems: discovery and supply. Latin American AI datasets exist but are scattered across platforms with no shared index. Even with perfect indexing, the total volume would remain far below what frontier AI development requires. We propose DataHub: a task-first data infrastructure organized through the ontology /<task?>/<domain?>/<language?>, with mechanisms for dataset discovery, metadata, contribution, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02949","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/2608.02949/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":"2026-08-05T00:44:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mC7DorvPH9XXsoIxIOn6j09MESzfB0oFuHqTxORzREAPqXjDG9RrGkvKxCMsCR5X/BXrZi2guZByiwSmt4p5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:13:36.023352Z"},"content_sha256":"7ebd87a8a2c1cde7c959a730eebd0e08b14adac06af83107e817ff9778744bf0","schema_version":"1.0","event_id":"sha256:7ebd87a8a2c1cde7c959a730eebd0e08b14adac06af83107e817ff9778744bf0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YNQPV7KAPQGXYPHEXUFOBVU5IU/bundle.json","state_url":"https://pith.science/pith/YNQPV7KAPQGXYPHEXUFOBVU5IU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YNQPV7KAPQGXYPHEXUFOBVU5IU/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":"2026-08-20T07:13:36Z","links":{"resolver":"https://pith.science/pith/YNQPV7KAPQGXYPHEXUFOBVU5IU","bundle":"https://pith.science/pith/YNQPV7KAPQGXYPHEXUFOBVU5IU/bundle.json","state":"https://pith.science/pith/YNQPV7KAPQGXYPHEXUFOBVU5IU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YNQPV7KAPQGXYPHEXUFOBVU5IU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YNQPV7KAPQGXYPHEXUFOBVU5IU","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":"995bb47626254572a2c7bbf1fb4ba6ada9a92fb99bf74cf7d34fe56d0e35f200","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T23:26:06Z","title_canon_sha256":"7cf7250aa9444dce34fd25ba1025a8b846f055ee5c61f75c0a5cfb6c7d7eda17"},"schema_version":"1.0","source":{"id":"2608.02949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02949","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02949v1","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02949","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"pith_short_12","alias_value":"YNQPV7KAPQGX","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"pith_short_16","alias_value":"YNQPV7KAPQGXYPHE","created_at":"2026-08-05T00:44:10Z"},{"alias_kind":"pith_short_8","alias_value":"YNQPV7KA","created_at":"2026-08-05T00:44:10Z"}],"graph_snapshots":[{"event_id":"sha256:7ebd87a8a2c1cde7c959a730eebd0e08b14adac06af83107e817ff9778744bf0","target":"graph","created_at":"2026-08-05T00:44:10Z","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/2608.02949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latin America is missing two foundational layers of AI infrastructure: the dataset layer and the benchmark layer. This paper targets the dataset layer. The dataset layer faces two compounding problems: discovery and supply. Latin American AI datasets exist but are scattered across platforms with no shared index. Even with perfect indexing, the total volume would remain far below what frontier AI development requires. We propose DataHub: a task-first data infrastructure organized through the ontology /<task?>/<domain?>/<language?>, with mechanisms for dataset discovery, metadata, contribution, ","authors_text":"Francis F Daniel, Francis Perelman, Marian Basti, Mauro Iba\\~nez","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T23:26:06Z","title":"On the missing data layer and a potential solution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02949","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":"sha256:8cac1aeded923b676e2615752c7159524b3eecc845a745042ad9176f60271c5e","target":"record","created_at":"2026-08-05T00:44:10Z","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":"995bb47626254572a2c7bbf1fb4ba6ada9a92fb99bf74cf7d34fe56d0e35f200","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T23:26:06Z","title_canon_sha256":"7cf7250aa9444dce34fd25ba1025a8b846f055ee5c61f75c0a5cfb6c7d7eda17"},"schema_version":"1.0","source":{"id":"2608.02949","kind":"arxiv","version":1}},"canonical_sha256":"c360fafd407c0d7c3ce4bd0ae0d69d45173638b2ba433c9b091e21f70416d510","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c360fafd407c0d7c3ce4bd0ae0d69d45173638b2ba433c9b091e21f70416d510","first_computed_at":"2026-08-05T00:44:10.705896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:44:10.705896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W+tiJlKUDLdfs/XzeWM8c31mfQCt9doDc9nvARCAsibO1f89TMNtJb1a1TyQ1IfgAQ+/oreCZOLAPSRd1N1MBA==","signature_status":"signed_v1","signed_at":"2026-08-05T00:44:10.708551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cac1aeded923b676e2615752c7159524b3eecc845a745042ad9176f60271c5e","sha256:7ebd87a8a2c1cde7c959a730eebd0e08b14adac06af83107e817ff9778744bf0"],"state_sha256":"0a906a32373782f666aaacafff4249a457d2f2804517ef42f7a0cd2a79b8d3c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQraS+78OHKeLB35SKPx1/3btDqlVrFAMf+5iwB5GqupUmf0/Af+CicOwGzqj0La+0Nm/qbmcsYPjQt2UV4OCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T07:13:36.029815Z","bundle_sha256":"e7996f05da839b91d42fc9f0a5d308bfcd49ec12c3b5da1602037592a831ce92"}}