{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:X3ZBMQV7CUBUMZC7YWOBRIX7OW","short_pith_number":"pith:X3ZBMQV7","canonical_record":{"source":{"id":"2209.13136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-27T03:47:03Z","cross_cats_sorted":["cond-mat.mtrl-sci","cond-mat.soft"],"title_canon_sha256":"8996aaf88e68a25696f823485bff9ea1ffb158053c1c0ecbcd1f67404ea2e1c2","abstract_canon_sha256":"c9ebfd12e05d6ffffb74ca08df1a0b64afa02a50dbae4089f5dd62d3480e60af"},"schema_version":"1.0"},"canonical_sha256":"bef21642bf150346645fc59c18a2ff759d125d82471718c6bd1d12acb7a9328c","source":{"kind":"arxiv","id":"2209.13136","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.13136","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2209.13136v1","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13136","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"X3ZBMQV7CUBU","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"X3ZBMQV7CUBUMZC7","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"X3ZBMQV7","created_at":"2026-07-05T05:58:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:X3ZBMQV7CUBUMZC7YWOBRIX7OW","target":"record","payload":{"canonical_record":{"source":{"id":"2209.13136","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-27T03:47:03Z","cross_cats_sorted":["cond-mat.mtrl-sci","cond-mat.soft"],"title_canon_sha256":"8996aaf88e68a25696f823485bff9ea1ffb158053c1c0ecbcd1f67404ea2e1c2","abstract_canon_sha256":"c9ebfd12e05d6ffffb74ca08df1a0b64afa02a50dbae4089f5dd62d3480e60af"},"schema_version":"1.0"},"canonical_sha256":"bef21642bf150346645fc59c18a2ff759d125d82471718c6bd1d12acb7a9328c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:17.043214Z","signature_b64":"V1mguiEdmaLKencN4W7X9yjU7HJQoZEL6TKQ2g6Kb6/g3jpzkIeoKBgPeg+JQjU4BogPRryVzg8F7DgZzaJdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef21642bf150346645fc59c18a2ff759d125d82471718c6bd1d12acb7a9328c","last_reissued_at":"2026-07-05T05:58:17.042785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:17.042785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.13136","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":"2026-07-05T05:58:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dWCN8fXIoUC6fIOiscL3v99MB6AocQAf0NfU66Ab6KnU3DIFdGzCE0XVocsO6kuWv35pr2SaR2fmR3qejrmhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:44:02.269926Z"},"content_sha256":"9a819d3399505f5b35c7386f2021c920fdc8b54328cbebe6f2504958d6799959","schema_version":"1.0","event_id":"sha256:9a819d3399505f5b35c7386f2021c920fdc8b54328cbebe6f2504958d6799959"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:X3ZBMQV7CUBUMZC7YWOBRIX7OW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A general-purpose material property data extraction pipeline from large polymer corpora using Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cond-mat.soft"],"primary_cat":"cs.CL","authors_text":"Arunkumar Chitteth Rajan, Chao Zhang, Christopher Kuenneth, Lakshmi Prerana Panchumarti, Lauren Holm, Pranav Shetty, Rampi Ramprasad, Sonkakshi Gupta","submitted_at":"2022-09-27T03:47:03Z","abstract_excerpt":"The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from published literature. We used natural language processing (NLP) methods to automatically extract material property data from the abstracts of polymer literature. As a component of our pipeline, we trained MaterialsBERT, a language model, using 2.4 million materials science abstracts, which outperforms other baseline models in three out of five named entity recognition datasets when used as the encoder for text. Using this pipeline, we obtained ~300,000 material property r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13136","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/2209.13136/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":"2026-07-05T05:58:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t03XPulS4/oh3DkVa7uvTlk0Ye6NB1aSnMhGe91ew871R4Z3RCTuxJ3qvmqUq6niPsQ1281OGbDOrI+pQqkHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:44:02.270303Z"},"content_sha256":"8557479f5521750154ce8566add3f65be8c1d4e7f12067d856c2be1effce3ef6","schema_version":"1.0","event_id":"sha256:8557479f5521750154ce8566add3f65be8c1d4e7f12067d856c2be1effce3ef6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X3ZBMQV7CUBUMZC7YWOBRIX7OW/bundle.json","state_url":"https://pith.science/pith/X3ZBMQV7CUBUMZC7YWOBRIX7OW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X3ZBMQV7CUBUMZC7YWOBRIX7OW/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":"2026-07-07T12:44:02Z","links":{"resolver":"https://pith.science/pith/X3ZBMQV7CUBUMZC7YWOBRIX7OW","bundle":"https://pith.science/pith/X3ZBMQV7CUBUMZC7YWOBRIX7OW/bundle.json","state":"https://pith.science/pith/X3ZBMQV7CUBUMZC7YWOBRIX7OW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X3ZBMQV7CUBUMZC7YWOBRIX7OW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:X3ZBMQV7CUBUMZC7YWOBRIX7OW","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":"c9ebfd12e05d6ffffb74ca08df1a0b64afa02a50dbae4089f5dd62d3480e60af","cross_cats_sorted":["cond-mat.mtrl-sci","cond-mat.soft"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-27T03:47:03Z","title_canon_sha256":"8996aaf88e68a25696f823485bff9ea1ffb158053c1c0ecbcd1f67404ea2e1c2"},"schema_version":"1.0","source":{"id":"2209.13136","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.13136","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"arxiv_version","alias_value":"2209.13136v1","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13136","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_12","alias_value":"X3ZBMQV7CUBU","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_16","alias_value":"X3ZBMQV7CUBUMZC7","created_at":"2026-07-05T05:58:17Z"},{"alias_kind":"pith_short_8","alias_value":"X3ZBMQV7","created_at":"2026-07-05T05:58:17Z"}],"graph_snapshots":[{"event_id":"sha256:8557479f5521750154ce8566add3f65be8c1d4e7f12067d856c2be1effce3ef6","target":"graph","created_at":"2026-07-05T05:58:17Z","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/2209.13136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from published literature. We used natural language processing (NLP) methods to automatically extract material property data from the abstracts of polymer literature. As a component of our pipeline, we trained MaterialsBERT, a language model, using 2.4 million materials science abstracts, which outperforms other baseline models in three out of five named entity recognition datasets when used as the encoder for text. Using this pipeline, we obtained ~300,000 material property r","authors_text":"Arunkumar Chitteth Rajan, Chao Zhang, Christopher Kuenneth, Lakshmi Prerana Panchumarti, Lauren Holm, Pranav Shetty, Rampi Ramprasad, Sonkakshi Gupta","cross_cats":["cond-mat.mtrl-sci","cond-mat.soft"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-27T03:47:03Z","title":"A general-purpose material property data extraction pipeline from large polymer corpora using Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13136","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":"sha256:9a819d3399505f5b35c7386f2021c920fdc8b54328cbebe6f2504958d6799959","target":"record","created_at":"2026-07-05T05:58:17Z","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":"c9ebfd12e05d6ffffb74ca08df1a0b64afa02a50dbae4089f5dd62d3480e60af","cross_cats_sorted":["cond-mat.mtrl-sci","cond-mat.soft"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-27T03:47:03Z","title_canon_sha256":"8996aaf88e68a25696f823485bff9ea1ffb158053c1c0ecbcd1f67404ea2e1c2"},"schema_version":"1.0","source":{"id":"2209.13136","kind":"arxiv","version":1}},"canonical_sha256":"bef21642bf150346645fc59c18a2ff759d125d82471718c6bd1d12acb7a9328c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bef21642bf150346645fc59c18a2ff759d125d82471718c6bd1d12acb7a9328c","first_computed_at":"2026-07-05T05:58:17.042785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:17.042785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V1mguiEdmaLKencN4W7X9yjU7HJQoZEL6TKQ2g6Kb6/g3jpzkIeoKBgPeg+JQjU4BogPRryVzg8F7DgZzaJdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:17.043214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.13136","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a819d3399505f5b35c7386f2021c920fdc8b54328cbebe6f2504958d6799959","sha256:8557479f5521750154ce8566add3f65be8c1d4e7f12067d856c2be1effce3ef6"],"state_sha256":"0667db81842b3271f793a597a0022ef65e07a671b6384a6185913eea28667a18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnhxPMYtYduJOgWzcj72gyZ8AZm4HhkxVPx+Cm2/+s/qRYvvoDE2dY6+Rk6N9q0H43vr1d2svWDD7b0+mekqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:44:02.272257Z","bundle_sha256":"71964112a5add8d354b992d21b58cfd8713f711d2f1182f06cf999c0363a8036"}}