{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:B2DP64MXI3Q3R7OCT32C6CSTJN","short_pith_number":"pith:B2DP64MX","canonical_record":{"source":{"id":"2602.03554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T14:03:32Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"title_canon_sha256":"ac32bc514838d143d1784e016ed9d1e507f2a04fa7c8f5e01150d45928b0fa97","abstract_canon_sha256":"6b72ea6b149f86dfaada50ba1facbdfea44f1f56f06b1e7bc5e9695a1ea1c663"},"schema_version":"1.0"},"canonical_sha256":"0e86ff719746e1b8fdc29ef42f0a534b7744010ff7d6775c2d972132f83d7066","source":{"kind":"arxiv","id":"2602.03554","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03554","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03554v2","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03554","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"B2DP64MXI3Q3","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"B2DP64MXI3Q3R7OC","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"B2DP64MX","created_at":"2026-06-02T01:03:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:B2DP64MXI3Q3R7OCT32C6CSTJN","target":"record","payload":{"canonical_record":{"source":{"id":"2602.03554","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T14:03:32Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"title_canon_sha256":"ac32bc514838d143d1784e016ed9d1e507f2a04fa7c8f5e01150d45928b0fa97","abstract_canon_sha256":"6b72ea6b149f86dfaada50ba1facbdfea44f1f56f06b1e7bc5e9695a1ea1c663"},"schema_version":"1.0"},"canonical_sha256":"0e86ff719746e1b8fdc29ef42f0a534b7744010ff7d6775c2d972132f83d7066","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:42.304298Z","signature_b64":"nRPBQdy9mCdFcJH/oWFWbqrAPKoNE9rtbhMlIniXJt9SROAW4JVbYbqktKuBSiKCR0JbWMQwLAV+pjybgQ5GAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e86ff719746e1b8fdc29ef42f0a534b7744010ff7d6775c2d972132f83d7066","last_reissued_at":"2026-06-02T01:03:42.303778Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:42.303778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.03554","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0TriQH8952P6YCjEhcV+xFbITedX2E3/MXYk2U6HtOVXLdt727TG61/Q06/rF9nl39aL0YygwnfMoQ2t+C8YCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:24:33.476984Z"},"content_sha256":"15b7f795b32422d0fd8d2ecd986c69003442a1289a5541e15998a35fb5cbc6cc","schema_version":"1.0","event_id":"sha256:15b7f795b32422d0fd8d2ecd986c69003442a1289a5541e15998a35fb5cbc6cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:B2DP64MXI3Q3R7OCT32C6CSTJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alex Aliper, Alex Zhavoronkov, Bogdan Zagribelnyy, Ivan Ilin, Maksim Kuznetsov, Mathieu Reymond, Mikolaj Mizera, Nikita Bondarev, Rim Shayakhmetov, Roman Schutski, Thomas MacDougall, Vladimir Aladinskiy, Zulfat Miftakhutdinov","submitted_at":"2026-02-03T14:03:32Z","abstract_excerpt":"Recent progress has expanded the use of large language models (LLMs) in drug discovery, including synthesis planning. However, objective evaluation of retrosynthesis performance remains limited. Existing benchmarks and metrics typically rely on published synthetic procedures and Top-K accuracy based on single ground-truth, which does not capture the open-ended nature of real-world synthesis planning. We propose a new benchmarking framework for single-step retrosynthesis that evaluates both general-purpose and chemistry-specialized LLMs using ChemCensor, a novel metric for chemical plausibility"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03554","kind":"arxiv","version":2},"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/2602.03554/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":"2026-06-02T01:03:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i/sWBUtco2MyAaFMP6jj5D91eKGbz51Suvio0Nw96gdTAyTSMTSS931747Knpu1cPyc27XGgnQmfJthc3uKmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:24:33.477376Z"},"content_sha256":"cb6e73ea7e65a42f46f820a1e708adc314b0741f90662438c2a6b5f43174026b","schema_version":"1.0","event_id":"sha256:cb6e73ea7e65a42f46f820a1e708adc314b0741f90662438c2a6b5f43174026b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2DP64MXI3Q3R7OCT32C6CSTJN/bundle.json","state_url":"https://pith.science/pith/B2DP64MXI3Q3R7OCT32C6CSTJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2DP64MXI3Q3R7OCT32C6CSTJN/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":"2026-06-02T19:24:33Z","links":{"resolver":"https://pith.science/pith/B2DP64MXI3Q3R7OCT32C6CSTJN","bundle":"https://pith.science/pith/B2DP64MXI3Q3R7OCT32C6CSTJN/bundle.json","state":"https://pith.science/pith/B2DP64MXI3Q3R7OCT32C6CSTJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2DP64MXI3Q3R7OCT32C6CSTJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B2DP64MXI3Q3R7OCT32C6CSTJN","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":"6b72ea6b149f86dfaada50ba1facbdfea44f1f56f06b1e7bc5e9695a1ea1c663","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T14:03:32Z","title_canon_sha256":"ac32bc514838d143d1784e016ed9d1e507f2a04fa7c8f5e01150d45928b0fa97"},"schema_version":"1.0","source":{"id":"2602.03554","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03554","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03554v2","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03554","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_12","alias_value":"B2DP64MXI3Q3","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_16","alias_value":"B2DP64MXI3Q3R7OC","created_at":"2026-06-02T01:03:42Z"},{"alias_kind":"pith_short_8","alias_value":"B2DP64MX","created_at":"2026-06-02T01:03:42Z"}],"graph_snapshots":[{"event_id":"sha256:cb6e73ea7e65a42f46f820a1e708adc314b0741f90662438c2a6b5f43174026b","target":"graph","created_at":"2026-06-02T01:03:42Z","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/2602.03554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress has expanded the use of large language models (LLMs) in drug discovery, including synthesis planning. However, objective evaluation of retrosynthesis performance remains limited. Existing benchmarks and metrics typically rely on published synthetic procedures and Top-K accuracy based on single ground-truth, which does not capture the open-ended nature of real-world synthesis planning. We propose a new benchmarking framework for single-step retrosynthesis that evaluates both general-purpose and chemistry-specialized LLMs using ChemCensor, a novel metric for chemical plausibility","authors_text":"Alex Aliper, Alex Zhavoronkov, Bogdan Zagribelnyy, Ivan Ilin, Maksim Kuznetsov, Mathieu Reymond, Mikolaj Mizera, Nikita Bondarev, Rim Shayakhmetov, Roman Schutski, Thomas MacDougall, Vladimir Aladinskiy, Zulfat Miftakhutdinov","cross_cats":["cs.AI","cs.CE","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T14:03:32Z","title":"When Single Answer Is Not Enough: Rethinking Single-Step Retrosynthesis Benchmarks for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03554","kind":"arxiv","version":2},"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":"sha256:15b7f795b32422d0fd8d2ecd986c69003442a1289a5541e15998a35fb5cbc6cc","target":"record","created_at":"2026-06-02T01:03:42Z","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":"6b72ea6b149f86dfaada50ba1facbdfea44f1f56f06b1e7bc5e9695a1ea1c663","cross_cats_sorted":["cs.AI","cs.CE","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-03T14:03:32Z","title_canon_sha256":"ac32bc514838d143d1784e016ed9d1e507f2a04fa7c8f5e01150d45928b0fa97"},"schema_version":"1.0","source":{"id":"2602.03554","kind":"arxiv","version":2}},"canonical_sha256":"0e86ff719746e1b8fdc29ef42f0a534b7744010ff7d6775c2d972132f83d7066","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e86ff719746e1b8fdc29ef42f0a534b7744010ff7d6775c2d972132f83d7066","first_computed_at":"2026-06-02T01:03:42.303778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:42.303778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nRPBQdy9mCdFcJH/oWFWbqrAPKoNE9rtbhMlIniXJt9SROAW4JVbYbqktKuBSiKCR0JbWMQwLAV+pjybgQ5GAA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:42.304298Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.03554","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15b7f795b32422d0fd8d2ecd986c69003442a1289a5541e15998a35fb5cbc6cc","sha256:cb6e73ea7e65a42f46f820a1e708adc314b0741f90662438c2a6b5f43174026b"],"state_sha256":"c4fc8534ea2a710eea9cf5f890d5194bbab75538ee1f0ea52bbf38472db87eed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A92fSUvqkpW1ou5DYYB2QmJrJK6l4zjDHEo6jaqCmNj+tS8WCwBg5Mt3D9dPCGvVL9AvpHIKOX2asExhCBsvDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T19:24:33.479435Z","bundle_sha256":"a1b924faf88541d5493ecd449dd40e3dbe6fcc507d79a36741c3c4f1bc9d5f51"}}