{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CGOVPHQR5PYYS6WWD3CKNRIEYM","short_pith_number":"pith:CGOVPHQR","canonical_record":{"source":{"id":"2505.03777","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T09:30:04Z","cross_cats_sorted":[],"title_canon_sha256":"1b454dd909c3e38249a6b837feaca9883ce0f791a2d8279f9eb8f8a5b062c015","abstract_canon_sha256":"e0a1db060c16565978e7c709a8e975bb281f00ec14482ef378af5ab00dd94a86"},"schema_version":"1.0"},"canonical_sha256":"119d579e11ebf1897ad61ec4a6c504c3036bbf64dcab459891098bc6f54b18de","source":{"kind":"arxiv","id":"2505.03777","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03777","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03777v2","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03777","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"CGOVPHQR5PYY","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"CGOVPHQR5PYYS6WW","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"CGOVPHQR","created_at":"2026-07-05T11:00:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CGOVPHQR5PYYS6WWD3CKNRIEYM","target":"record","payload":{"canonical_record":{"source":{"id":"2505.03777","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T09:30:04Z","cross_cats_sorted":[],"title_canon_sha256":"1b454dd909c3e38249a6b837feaca9883ce0f791a2d8279f9eb8f8a5b062c015","abstract_canon_sha256":"e0a1db060c16565978e7c709a8e975bb281f00ec14482ef378af5ab00dd94a86"},"schema_version":"1.0"},"canonical_sha256":"119d579e11ebf1897ad61ec4a6c504c3036bbf64dcab459891098bc6f54b18de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:08.353482Z","signature_b64":"FqFrjGgiccfGAcQuSiHkRH73G+JNs+oWRRZHZRRR2WSmGhYaDgMcIIpmthpu0p2Cq8O6JG60a1r9z9OrtpmkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"119d579e11ebf1897ad61ec4a6c504c3036bbf64dcab459891098bc6f54b18de","last_reissued_at":"2026-07-05T11:00:08.352981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:08.352981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.03777","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":"2026-07-05T11:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"untbHIAccwHRQPX9bhOWRA/KBX+dmUK+w+zQkbKIqN7HKw+ncaG08MKUaYTQXfIIqwD1VmEQ3vjEFpIAY3ziCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:52:55.955296Z"},"content_sha256":"87798bb17c8bcaf2c2f14c45b8a9dc3f3fca87da1e513f755148333670a2141e","schema_version":"1.0","event_id":"sha256:87798bb17c8bcaf2c2f14c45b8a9dc3f3fca87da1e513f755148333670a2141e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CGOVPHQR5PYYS6WWD3CKNRIEYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MolMole: Molecule Mining from Scientific Literature","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahra Jo, Byung Jun Kang, ChangYoung Park, Chanwoo Moon, Dongyun Kim, Edward Hwayoung Lee, Gerrard Jeongwon Jo, Haein Lee, Heejae Han, Jaeseung Byun, Jaewan Lee, Jeongsang Yu, Jiwon Ham, Jiye Kim, Jongmin Lee, Jun Ha Park, Kijeong Jeon, Kwangrok Ryoo, Kyunghoon Bae, Kyungjae Yoo, LG AI Research, Minju Ha, Sehui Han, Sehyun Chun, Seung Hwan Kim, Seungjun Lee, Seungyul Oh, Sihyuk Yi, Soojong Do, Soonyoung Lee, Woohyung Lim, Yeonjung Hong, Yeonsik Jo, Yongmin Park","submitted_at":"2025-04-30T09:30:04Z","abstract_excerpt":"The extraction of molecular structures and reaction data from scientific documents is challenging due to their varied, unstructured chemical formats and complex document layouts. To address this, we introduce MolMole, a vision-based deep learning framework that unifies molecule detection, reaction diagram parsing, and optical chemical structure recognition (OCSR) into a single pipeline for automating the extraction of chemical data directly from page-level documents. Recognizing the lack of a standard page-level benchmark and evaluation metric, we also present a testset of 550 pages annotated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03777","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/2505.03777/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":"2026-07-05T11:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukjIfpqr/WDi1o4gNM4tCI9NIlgyqAcb1XMmJb+e0F/6HRp4fB82naYQXf8K5R/rs7KmQ9Q5/Ro+N97TttzQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T14:52:55.955783Z"},"content_sha256":"306542f3a670b457dfe5ea524a61487225898fb7ba12e6b870fbb5dcf51b3554","schema_version":"1.0","event_id":"sha256:306542f3a670b457dfe5ea524a61487225898fb7ba12e6b870fbb5dcf51b3554"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CGOVPHQR5PYYS6WWD3CKNRIEYM/bundle.json","state_url":"https://pith.science/pith/CGOVPHQR5PYYS6WWD3CKNRIEYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CGOVPHQR5PYYS6WWD3CKNRIEYM/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":"2026-08-14T14:52:55Z","links":{"resolver":"https://pith.science/pith/CGOVPHQR5PYYS6WWD3CKNRIEYM","bundle":"https://pith.science/pith/CGOVPHQR5PYYS6WWD3CKNRIEYM/bundle.json","state":"https://pith.science/pith/CGOVPHQR5PYYS6WWD3CKNRIEYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CGOVPHQR5PYYS6WWD3CKNRIEYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CGOVPHQR5PYYS6WWD3CKNRIEYM","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":"e0a1db060c16565978e7c709a8e975bb281f00ec14482ef378af5ab00dd94a86","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T09:30:04Z","title_canon_sha256":"1b454dd909c3e38249a6b837feaca9883ce0f791a2d8279f9eb8f8a5b062c015"},"schema_version":"1.0","source":{"id":"2505.03777","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03777","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03777v2","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03777","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"CGOVPHQR5PYY","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"CGOVPHQR5PYYS6WW","created_at":"2026-07-05T11:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"CGOVPHQR","created_at":"2026-07-05T11:00:08Z"}],"graph_snapshots":[{"event_id":"sha256:306542f3a670b457dfe5ea524a61487225898fb7ba12e6b870fbb5dcf51b3554","target":"graph","created_at":"2026-07-05T11:00:08Z","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/2505.03777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The extraction of molecular structures and reaction data from scientific documents is challenging due to their varied, unstructured chemical formats and complex document layouts. To address this, we introduce MolMole, a vision-based deep learning framework that unifies molecule detection, reaction diagram parsing, and optical chemical structure recognition (OCSR) into a single pipeline for automating the extraction of chemical data directly from page-level documents. Recognizing the lack of a standard page-level benchmark and evaluation metric, we also present a testset of 550 pages annotated ","authors_text":"Ahra Jo, Byung Jun Kang, ChangYoung Park, Chanwoo Moon, Dongyun Kim, Edward Hwayoung Lee, Gerrard Jeongwon Jo, Haein Lee, Heejae Han, Jaeseung Byun, Jaewan Lee, Jeongsang Yu, Jiwon Ham, Jiye Kim, Jongmin Lee, Jun Ha Park, Kijeong Jeon, Kwangrok Ryoo, Kyunghoon Bae, Kyungjae Yoo, LG AI Research, Minju Ha, Sehui Han, Sehyun Chun, Seung Hwan Kim, Seungjun Lee, Seungyul Oh, Sihyuk Yi, Soojong Do, Soonyoung Lee, Woohyung Lim, Yeonjung Hong, Yeonsik Jo, Yongmin Park","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T09:30:04Z","title":"MolMole: Molecule Mining from Scientific Literature"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03777","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":"sha256:87798bb17c8bcaf2c2f14c45b8a9dc3f3fca87da1e513f755148333670a2141e","target":"record","created_at":"2026-07-05T11:00:08Z","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":"e0a1db060c16565978e7c709a8e975bb281f00ec14482ef378af5ab00dd94a86","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T09:30:04Z","title_canon_sha256":"1b454dd909c3e38249a6b837feaca9883ce0f791a2d8279f9eb8f8a5b062c015"},"schema_version":"1.0","source":{"id":"2505.03777","kind":"arxiv","version":2}},"canonical_sha256":"119d579e11ebf1897ad61ec4a6c504c3036bbf64dcab459891098bc6f54b18de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"119d579e11ebf1897ad61ec4a6c504c3036bbf64dcab459891098bc6f54b18de","first_computed_at":"2026-07-05T11:00:08.352981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:08.352981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqFrjGgiccfGAcQuSiHkRH73G+JNs+oWRRZHZRRR2WSmGhYaDgMcIIpmthpu0p2Cq8O6JG60a1r9z9OrtpmkBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:08.353482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03777","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87798bb17c8bcaf2c2f14c45b8a9dc3f3fca87da1e513f755148333670a2141e","sha256:306542f3a670b457dfe5ea524a61487225898fb7ba12e6b870fbb5dcf51b3554"],"state_sha256":"23674e81080727afd47e7fa2ee069608970cc9088beed2c55b03feec37646358"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MptxS5tUmqGQIp7BV+yTgGPnhHSbkpv4t4nAZnQ2vE89HgnB0RMwkvNrs6i/0Y/eSMuA4/MbXqNozJy40fUUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T14:52:55.960129Z","bundle_sha256":"8a38dc4aa2e14e259c75568a478c58eadc33e0a88ebcd92d5e417b23143231f5"}}