{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6NZFWESWYUHQPEWIHS4VI7XS34","short_pith_number":"pith:6NZFWESW","canonical_record":{"source":{"id":"2205.14311","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-28T03:03:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af9b1bdba48220bf331344d761da4ea0df52bf6ef5eb4d9205a60f655db1e640","abstract_canon_sha256":"da39ce9906e2754b417c58f37e1554487e9965aefafc3d1800c801b48836195d"},"schema_version":"1.0"},"canonical_sha256":"f3725b1256c50f0792c83cb9547ef2df000cb7d07592af98c2f687d9c76a2e89","source":{"kind":"arxiv","id":"2205.14311","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14311","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14311v2","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14311","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"6NZFWESWYUHQ","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"6NZFWESWYUHQPEWI","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"6NZFWESW","created_at":"2026-07-05T05:52:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6NZFWESWYUHQPEWIHS4VI7XS34","target":"record","payload":{"canonical_record":{"source":{"id":"2205.14311","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-28T03:03:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af9b1bdba48220bf331344d761da4ea0df52bf6ef5eb4d9205a60f655db1e640","abstract_canon_sha256":"da39ce9906e2754b417c58f37e1554487e9965aefafc3d1800c801b48836195d"},"schema_version":"1.0"},"canonical_sha256":"f3725b1256c50f0792c83cb9547ef2df000cb7d07592af98c2f687d9c76a2e89","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:55.645879Z","signature_b64":"75lsihBb7T2O7f+oYFFRhOW96OT4NsWPSN9e32+LMI/9AxVk6SMuobfJ7CceZVF+2n2jptkRVdjhpUnUe4G+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3725b1256c50f0792c83cb9547ef2df000cb7d07592af98c2f687d9c76a2e89","last_reissued_at":"2026-07-05T05:52:55.645389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:55.645389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.14311","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":"2026-07-05T05:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yn5u/VNDICXHlqD0pEYrj6xwIvYWBK7O/xOxgz6i+PxSq6twZ2PzYguti4D2/caBoieumPR3cd1ftGbN0eW8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:35:15.901829Z"},"content_sha256":"5e5a1fba37bcbe0431cc2c4ee29f37cff2bcce9c6af54496d0e7e1ff34bd3b3d","schema_version":"1.0","event_id":"sha256:5e5a1fba37bcbe0431cc2c4ee29f37cff2bcce9c6af54496d0e7e1ff34bd3b3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6NZFWESWYUHQPEWIHS4VI7XS34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MolScribe: Robust Molecular Structure Recognition with Image-To-Graph Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Connor W. Coley, Jiang Guo, Regina Barzilay, Yujie Qian, Zhengkai Tu, Zhening Li","submitted_at":"2022-05-28T03:03:45Z","abstract_excerpt":"Molecular structure recognition is the task of translating a molecular image into its graph structure. Significant variation in drawing styles and conventions exhibited in chemical literature poses a significant challenge for automating this task. In this paper, we propose MolScribe, a novel image-to-graph generation model that explicitly predicts atoms and bonds, along with their geometric layouts, to construct the molecular structure. Our model flexibly incorporates symbolic chemistry constraints to recognize chirality and expand abbreviated structures. We further develop data augmentation s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14311","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/2205.14311/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":"2026-07-05T05:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZxVsTrtJjtjAqpq1HHxAxINwTVhM/NS2vAJzNWvLgrhkZbE4GEYlk639vZMOAtjOKVGaRgl7WE+JTXnHwHdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:35:15.902548Z"},"content_sha256":"2f55a118b731c83169076aa22cf535b9db334581a874d9dfb08d10137c2fd653","schema_version":"1.0","event_id":"sha256:2f55a118b731c83169076aa22cf535b9db334581a874d9dfb08d10137c2fd653"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6NZFWESWYUHQPEWIHS4VI7XS34/bundle.json","state_url":"https://pith.science/pith/6NZFWESWYUHQPEWIHS4VI7XS34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6NZFWESWYUHQPEWIHS4VI7XS34/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":"2026-08-06T18:35:15Z","links":{"resolver":"https://pith.science/pith/6NZFWESWYUHQPEWIHS4VI7XS34","bundle":"https://pith.science/pith/6NZFWESWYUHQPEWIHS4VI7XS34/bundle.json","state":"https://pith.science/pith/6NZFWESWYUHQPEWIHS4VI7XS34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6NZFWESWYUHQPEWIHS4VI7XS34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6NZFWESWYUHQPEWIHS4VI7XS34","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":"da39ce9906e2754b417c58f37e1554487e9965aefafc3d1800c801b48836195d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-28T03:03:45Z","title_canon_sha256":"af9b1bdba48220bf331344d761da4ea0df52bf6ef5eb4d9205a60f655db1e640"},"schema_version":"1.0","source":{"id":"2205.14311","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14311","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14311v2","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14311","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"6NZFWESWYUHQ","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"pith_short_16","alias_value":"6NZFWESWYUHQPEWI","created_at":"2026-07-05T05:52:55Z"},{"alias_kind":"pith_short_8","alias_value":"6NZFWESW","created_at":"2026-07-05T05:52:55Z"}],"graph_snapshots":[{"event_id":"sha256:2f55a118b731c83169076aa22cf535b9db334581a874d9dfb08d10137c2fd653","target":"graph","created_at":"2026-07-05T05:52:55Z","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/2205.14311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Molecular structure recognition is the task of translating a molecular image into its graph structure. Significant variation in drawing styles and conventions exhibited in chemical literature poses a significant challenge for automating this task. In this paper, we propose MolScribe, a novel image-to-graph generation model that explicitly predicts atoms and bonds, along with their geometric layouts, to construct the molecular structure. Our model flexibly incorporates symbolic chemistry constraints to recognize chirality and expand abbreviated structures. We further develop data augmentation s","authors_text":"Connor W. Coley, Jiang Guo, Regina Barzilay, Yujie Qian, Zhengkai Tu, Zhening Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-28T03:03:45Z","title":"MolScribe: Robust Molecular Structure Recognition with Image-To-Graph Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14311","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":"sha256:5e5a1fba37bcbe0431cc2c4ee29f37cff2bcce9c6af54496d0e7e1ff34bd3b3d","target":"record","created_at":"2026-07-05T05:52:55Z","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":"da39ce9906e2754b417c58f37e1554487e9965aefafc3d1800c801b48836195d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-28T03:03:45Z","title_canon_sha256":"af9b1bdba48220bf331344d761da4ea0df52bf6ef5eb4d9205a60f655db1e640"},"schema_version":"1.0","source":{"id":"2205.14311","kind":"arxiv","version":2}},"canonical_sha256":"f3725b1256c50f0792c83cb9547ef2df000cb7d07592af98c2f687d9c76a2e89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3725b1256c50f0792c83cb9547ef2df000cb7d07592af98c2f687d9c76a2e89","first_computed_at":"2026-07-05T05:52:55.645389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:55.645389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"75lsihBb7T2O7f+oYFFRhOW96OT4NsWPSN9e32+LMI/9AxVk6SMuobfJ7CceZVF+2n2jptkRVdjhpUnUe4G+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:55.645879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14311","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e5a1fba37bcbe0431cc2c4ee29f37cff2bcce9c6af54496d0e7e1ff34bd3b3d","sha256:2f55a118b731c83169076aa22cf535b9db334581a874d9dfb08d10137c2fd653"],"state_sha256":"293f7572f706a6b1ea24056d73c86b93c3ffb80c7aca4ccd56e8e9d76e3b7537"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLkbsviPHQZWMlEfpgcp7v3rIpdyJHyHwsNq4Zl0F4uCBCotWeZZ27mYhC5Olec2fQJauP7KbyWVWqxKMG//DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:35:15.909515Z","bundle_sha256":"26e8df2d4ff05ddaf59515b99598ab05ce301f4e48bca9e951c089cafeefad07"}}