{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:352LIYARLLWQIMUVMWJSJG66L7","short_pith_number":"pith:352LIYAR","canonical_record":{"source":{"id":"2504.02486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-03T11:07:52Z","cross_cats_sorted":[],"title_canon_sha256":"df996481f366d7dd53a5d3a2b868537585a0dcda8e3e86fc51d40abf79ec0d08","abstract_canon_sha256":"771b9586b77a0c1182fd1e0609ec87a84f77c411f1228062cd73019040cbbeb2"},"schema_version":"1.0"},"canonical_sha256":"df74b460115aed0432956593249bde5fe654fda070f1e8b91ed39e82755ffaf7","source":{"kind":"arxiv","id":"2504.02486","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02486","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02486v1","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02486","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"pith_short_12","alias_value":"352LIYARLLWQ","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"pith_short_16","alias_value":"352LIYARLLWQIMUV","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"pith_short_8","alias_value":"352LIYAR","created_at":"2026-07-05T10:43:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:352LIYARLLWQIMUVMWJSJG66L7","target":"record","payload":{"canonical_record":{"source":{"id":"2504.02486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-03T11:07:52Z","cross_cats_sorted":[],"title_canon_sha256":"df996481f366d7dd53a5d3a2b868537585a0dcda8e3e86fc51d40abf79ec0d08","abstract_canon_sha256":"771b9586b77a0c1182fd1e0609ec87a84f77c411f1228062cd73019040cbbeb2"},"schema_version":"1.0"},"canonical_sha256":"df74b460115aed0432956593249bde5fe654fda070f1e8b91ed39e82755ffaf7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:57.862277Z","signature_b64":"idxfw+TPUp6QOufJ2VFs1Mrsxie8cYN4Euok/gD8RbbL5amZyz2D8SbYTtcJMhyROklW5PR8HpH4PbpOOTz0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df74b460115aed0432956593249bde5fe654fda070f1e8b91ed39e82755ffaf7","last_reissued_at":"2026-07-05T10:43:57.861655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:57.861655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.02486","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":"2026-07-05T10:43:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGNesxtA/sd8jdBr+u8XmHXHe/IW/+od4sMlDx9bJrWBzw5RDwROSv2tkQtuiS0JjP4mOy4US2TJIYUZlSE5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:58:31.907198Z"},"content_sha256":"9f07762f3f2cc2b973d17d3d7879b609dc26abe1ba5e7978a4bfd8d84ccf7428","schema_version":"1.0","event_id":"sha256:9f07762f3f2cc2b973d17d3d7879b609dc26abe1ba5e7978a4bfd8d84ccf7428"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:352LIYARLLWQIMUVMWJSJG66L7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"We Need Improved Data Curation and Attribution in AI for Scientific Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Antonio Foncubierta, Dimitrios Christofidellis, Irina Espejo-Morales, Jannis Born, Malina Molnar, Mara Graziani, Marvin Alberts, Matteo Manica","submitted_at":"2025-04-03T11:07:52Z","abstract_excerpt":"As the interplay between human-generated and synthetic data evolves, new challenges arise in scientific discovery concerning the integrity of the data and the stability of the models. In this work, we examine the role of synthetic data as opposed to that of real experimental data for scientific research. Our analyses indicate that nearly three-quarters of experimental datasets available on open-access platforms have relatively low adoption rates, opening new opportunities to enhance their discoverability and usability by automated methods. Additionally, we observe an increasing difficulty in d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02486","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/2504.02486/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":"2026-07-05T10:43:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4f2nzVtTpSoX5X6R+Gpvyat9VMepfs9VxtyPKmQQi2BDNVCqERkFZp/wgyoVpNRwF9Mm6xbv0gUbyj06CtygAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T13:58:31.907591Z"},"content_sha256":"3b01c0e7ca832d3ea86b9cdc2defc1c92306c21a7ceddbade288729890d4e777","schema_version":"1.0","event_id":"sha256:3b01c0e7ca832d3ea86b9cdc2defc1c92306c21a7ceddbade288729890d4e777"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/352LIYARLLWQIMUVMWJSJG66L7/bundle.json","state_url":"https://pith.science/pith/352LIYARLLWQIMUVMWJSJG66L7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/352LIYARLLWQIMUVMWJSJG66L7/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":"2026-07-08T13:58:31Z","links":{"resolver":"https://pith.science/pith/352LIYARLLWQIMUVMWJSJG66L7","bundle":"https://pith.science/pith/352LIYARLLWQIMUVMWJSJG66L7/bundle.json","state":"https://pith.science/pith/352LIYARLLWQIMUVMWJSJG66L7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/352LIYARLLWQIMUVMWJSJG66L7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:352LIYARLLWQIMUVMWJSJG66L7","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":"771b9586b77a0c1182fd1e0609ec87a84f77c411f1228062cd73019040cbbeb2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-03T11:07:52Z","title_canon_sha256":"df996481f366d7dd53a5d3a2b868537585a0dcda8e3e86fc51d40abf79ec0d08"},"schema_version":"1.0","source":{"id":"2504.02486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02486","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02486v1","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02486","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"pith_short_12","alias_value":"352LIYARLLWQ","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"pith_short_16","alias_value":"352LIYARLLWQIMUV","created_at":"2026-07-05T10:43:57Z"},{"alias_kind":"pith_short_8","alias_value":"352LIYAR","created_at":"2026-07-05T10:43:57Z"}],"graph_snapshots":[{"event_id":"sha256:3b01c0e7ca832d3ea86b9cdc2defc1c92306c21a7ceddbade288729890d4e777","target":"graph","created_at":"2026-07-05T10:43:57Z","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/2504.02486/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the interplay between human-generated and synthetic data evolves, new challenges arise in scientific discovery concerning the integrity of the data and the stability of the models. In this work, we examine the role of synthetic data as opposed to that of real experimental data for scientific research. Our analyses indicate that nearly three-quarters of experimental datasets available on open-access platforms have relatively low adoption rates, opening new opportunities to enhance their discoverability and usability by automated methods. Additionally, we observe an increasing difficulty in d","authors_text":"Antonio Foncubierta, Dimitrios Christofidellis, Irina Espejo-Morales, Jannis Born, Malina Molnar, Mara Graziani, Marvin Alberts, Matteo Manica","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-03T11:07:52Z","title":"We Need Improved Data Curation and Attribution in AI for Scientific Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02486","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":"sha256:9f07762f3f2cc2b973d17d3d7879b609dc26abe1ba5e7978a4bfd8d84ccf7428","target":"record","created_at":"2026-07-05T10:43:57Z","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":"771b9586b77a0c1182fd1e0609ec87a84f77c411f1228062cd73019040cbbeb2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-03T11:07:52Z","title_canon_sha256":"df996481f366d7dd53a5d3a2b868537585a0dcda8e3e86fc51d40abf79ec0d08"},"schema_version":"1.0","source":{"id":"2504.02486","kind":"arxiv","version":1}},"canonical_sha256":"df74b460115aed0432956593249bde5fe654fda070f1e8b91ed39e82755ffaf7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df74b460115aed0432956593249bde5fe654fda070f1e8b91ed39e82755ffaf7","first_computed_at":"2026-07-05T10:43:57.861655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:57.861655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"idxfw+TPUp6QOufJ2VFs1Mrsxie8cYN4Euok/gD8RbbL5amZyz2D8SbYTtcJMhyROklW5PR8HpH4PbpOOTz0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:57.862277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f07762f3f2cc2b973d17d3d7879b609dc26abe1ba5e7978a4bfd8d84ccf7428","sha256:3b01c0e7ca832d3ea86b9cdc2defc1c92306c21a7ceddbade288729890d4e777"],"state_sha256":"245ef6ee6bf4e6e55c09003424431d2bdf11dec01008ad44901d2f2f79312354"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cx/sQXRvDUxM/B+3uZfIGu599IPyR7xQUVY9LnUxj2c1WaKqgampGbce/IVR4GfpH854aJPw8/vY7aaZntWlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T13:58:31.909658Z","bundle_sha256":"33839e1666aa498b4154b22014db271e3a34d7462a2cb8e1d5f11bef983a8587"}}