{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7EFKDMU32VRYPPIQEVG72PDYKK","short_pith_number":"pith:7EFKDMU3","canonical_record":{"source":{"id":"2607.10849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T17:21:32Z","cross_cats_sorted":[],"title_canon_sha256":"75f74d1d319ba224bdc5dd8c89eeeb8623f5da2e599d84de0d961839515bea04","abstract_canon_sha256":"198f2f261cee53ff2cdda89d63bf4a77dbef47ad4c93a4c6b4827ba4f59763f7"},"schema_version":"1.0"},"canonical_sha256":"f90aa1b29bd56387bd10254dfd3c785297831199025f1bba34c10910411bc73f","source":{"kind":"arxiv","id":"2607.10849","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10849","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10849v1","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10849","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"pith_short_12","alias_value":"7EFKDMU32VRY","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"pith_short_16","alias_value":"7EFKDMU32VRYPPIQ","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"pith_short_8","alias_value":"7EFKDMU3","created_at":"2026-07-14T01:21:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7EFKDMU32VRYPPIQEVG72PDYKK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.10849","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T17:21:32Z","cross_cats_sorted":[],"title_canon_sha256":"75f74d1d319ba224bdc5dd8c89eeeb8623f5da2e599d84de0d961839515bea04","abstract_canon_sha256":"198f2f261cee53ff2cdda89d63bf4a77dbef47ad4c93a4c6b4827ba4f59763f7"},"schema_version":"1.0"},"canonical_sha256":"f90aa1b29bd56387bd10254dfd3c785297831199025f1bba34c10910411bc73f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:43.449991Z","signature_b64":"DCmoTajU31PQ7xcnLHo9ctzsZblrE8nV1m7zjRbYJgVWs4P9At+P49Nk5Ei/NhHeTkvPUlToAjVmw0pOEb1ICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f90aa1b29bd56387bd10254dfd3c785297831199025f1bba34c10910411bc73f","last_reissued_at":"2026-07-14T01:21:43.449152Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:43.449152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.10849","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":"2026-07-14T01:21:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tTLzcfxrJzt77MtJxEt1oWgn5RbzQJneC6k7GKU9F5+GhPk8SCQi1aE/iSjbBhsonKkkoSZf0bIQY1jd4gcWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:30:51.493087Z"},"content_sha256":"58442cbb4ecd26f7b9219790285e84e2cc7570d0f4503eea1cea77c8cd9cf9b4","schema_version":"1.0","event_id":"sha256:58442cbb4ecd26f7b9219790285e84e2cc7570d0f4503eea1cea77c8cd9cf9b4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7EFKDMU32VRYPPIQEVG72PDYKK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Capabilities of Claude Fable 5 on Biomedical Challenge Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dominic Okonkwo, Magnus Hodgson, Susan Adanna Ihejirika, Temitope I. David","submitted_at":"2026-07-12T17:21:32Z","abstract_excerpt":"Frontier language models are increasingly evaluated on biomedical benchmarks, but two problems undermine most published evaluations: legacy benchmarks are near-saturated, and open-ended responses are graded by other language models. We evaluate Claude Fable 5, Anthropic's most capable publicly available model, across eight biomedical benchmarks, four text and four multimodal, using deterministic scoring against fixed answer keys throughout. We include two Claude predecessors and GPT-5 as baselines. Refusal is tracked as a distinct outcome in every result table. That decision produces the paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10849","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/2607.10849/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":"2026-07-14T01:21:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dfrsPt5L90uCttxf2iMTo/aRwFfeR4spOC0nFYtEK2/7bDdrM61tV8Ymbv7i994SulMIcn1DOmFJyWHH2P6SCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:30:51.493926Z"},"content_sha256":"5b872458b7da7c8e88a71388ece3a7e11157550cc38fe1fcef2608019cb97211","schema_version":"1.0","event_id":"sha256:5b872458b7da7c8e88a71388ece3a7e11157550cc38fe1fcef2608019cb97211"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7EFKDMU32VRYPPIQEVG72PDYKK/bundle.json","state_url":"https://pith.science/pith/7EFKDMU32VRYPPIQEVG72PDYKK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7EFKDMU32VRYPPIQEVG72PDYKK/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":"2026-08-05T12:30:51Z","links":{"resolver":"https://pith.science/pith/7EFKDMU32VRYPPIQEVG72PDYKK","bundle":"https://pith.science/pith/7EFKDMU32VRYPPIQEVG72PDYKK/bundle.json","state":"https://pith.science/pith/7EFKDMU32VRYPPIQEVG72PDYKK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7EFKDMU32VRYPPIQEVG72PDYKK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7EFKDMU32VRYPPIQEVG72PDYKK","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":"198f2f261cee53ff2cdda89d63bf4a77dbef47ad4c93a4c6b4827ba4f59763f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T17:21:32Z","title_canon_sha256":"75f74d1d319ba224bdc5dd8c89eeeb8623f5da2e599d84de0d961839515bea04"},"schema_version":"1.0","source":{"id":"2607.10849","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10849","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10849v1","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10849","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"pith_short_12","alias_value":"7EFKDMU32VRY","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"pith_short_16","alias_value":"7EFKDMU32VRYPPIQ","created_at":"2026-07-14T01:21:43Z"},{"alias_kind":"pith_short_8","alias_value":"7EFKDMU3","created_at":"2026-07-14T01:21:43Z"}],"graph_snapshots":[{"event_id":"sha256:5b872458b7da7c8e88a71388ece3a7e11157550cc38fe1fcef2608019cb97211","target":"graph","created_at":"2026-07-14T01:21:43Z","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/2607.10849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Frontier language models are increasingly evaluated on biomedical benchmarks, but two problems undermine most published evaluations: legacy benchmarks are near-saturated, and open-ended responses are graded by other language models. We evaluate Claude Fable 5, Anthropic's most capable publicly available model, across eight biomedical benchmarks, four text and four multimodal, using deterministic scoring against fixed answer keys throughout. We include two Claude predecessors and GPT-5 as baselines. Refusal is tracked as a distinct outcome in every result table. That decision produces the paper","authors_text":"Dominic Okonkwo, Magnus Hodgson, Susan Adanna Ihejirika, Temitope I. David","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T17:21:32Z","title":"Capabilities of Claude Fable 5 on Biomedical Challenge Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10849","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":"sha256:58442cbb4ecd26f7b9219790285e84e2cc7570d0f4503eea1cea77c8cd9cf9b4","target":"record","created_at":"2026-07-14T01:21:43Z","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":"198f2f261cee53ff2cdda89d63bf4a77dbef47ad4c93a4c6b4827ba4f59763f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-12T17:21:32Z","title_canon_sha256":"75f74d1d319ba224bdc5dd8c89eeeb8623f5da2e599d84de0d961839515bea04"},"schema_version":"1.0","source":{"id":"2607.10849","kind":"arxiv","version":1}},"canonical_sha256":"f90aa1b29bd56387bd10254dfd3c785297831199025f1bba34c10910411bc73f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f90aa1b29bd56387bd10254dfd3c785297831199025f1bba34c10910411bc73f","first_computed_at":"2026-07-14T01:21:43.449152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:43.449152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DCmoTajU31PQ7xcnLHo9ctzsZblrE8nV1m7zjRbYJgVWs4P9At+P49Nk5Ei/NhHeTkvPUlToAjVmw0pOEb1ICg==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:43.449991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10849","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58442cbb4ecd26f7b9219790285e84e2cc7570d0f4503eea1cea77c8cd9cf9b4","sha256:5b872458b7da7c8e88a71388ece3a7e11157550cc38fe1fcef2608019cb97211"],"state_sha256":"8002637c46b49e5196f376fee631978f2ec94ace7e8ba9789d49f5defa1ffc6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXQQ42/v6wG7q36qGKF0sNB3thpfeCNcXJpWKNnE9r4xifhpCDZAvv0ZMai3jXE7MJIegPsOhWFFrihct0syAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:30:51.498422Z","bundle_sha256":"b8d18405194c86b611e0cb5414066f647205b65cdc8421020389ae3f62ef040d"}}