{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CRPGDC6MS5JIGRL3B6RP7SVSRC","short_pith_number":"pith:CRPGDC6M","canonical_record":{"source":{"id":"2606.30304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-29T13:45:28Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"9db6127861ee3ce5befc42086e265a235c4890f4e94045c3a4bfa919e444eb65","abstract_canon_sha256":"1fdbe2330e697594f5fcf375d230cb1f8299ce7aa4d11062fc0e2f3e1f00de9e"},"schema_version":"1.0"},"canonical_sha256":"145e618bcc975283457b0fa2ffcab288b4fb77ce5194fcbb1b622e04aec57755","source":{"kind":"arxiv","id":"2606.30304","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30304","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30304v1","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30304","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"CRPGDC6MS5JI","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"CRPGDC6MS5JIGRL3","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"CRPGDC6M","created_at":"2026-06-30T02:17:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CRPGDC6MS5JIGRL3B6RP7SVSRC","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-29T13:45:28Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"9db6127861ee3ce5befc42086e265a235c4890f4e94045c3a4bfa919e444eb65","abstract_canon_sha256":"1fdbe2330e697594f5fcf375d230cb1f8299ce7aa4d11062fc0e2f3e1f00de9e"},"schema_version":"1.0"},"canonical_sha256":"145e618bcc975283457b0fa2ffcab288b4fb77ce5194fcbb1b622e04aec57755","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:58.198627Z","signature_b64":"J1J6PKkOVC/Ia3cxQ+m90Ybxemwjx2/NDwWhO7LizCThTSV6rd2Qgq7yNxMAdPCMvuo2oL800pkEnTjw8rtICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"145e618bcc975283457b0fa2ffcab288b4fb77ce5194fcbb1b622e04aec57755","last_reissued_at":"2026-06-30T02:17:58.198012Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:58.198012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30304","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":"2026-06-30T02:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uW2RqjoQ5sVCg7DlSRzbyakRwNUZHIhd4RMwrGLJp2MKcHUmipEHFle2f34LWZz4rNwS2Bv4bpkHOshI6T1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:31:41.207641Z"},"content_sha256":"c98d900cfd0512f64230591d5bbcb5da5e2eb7488a1b10e17c1f12f471565fd9","schema_version":"1.0","event_id":"sha256:c98d900cfd0512f64230591d5bbcb5da5e2eb7488a1b10e17c1f12f471565fd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CRPGDC6MS5JIGRL3B6RP7SVSRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Research Entity Extraction and Topic Detection from UKRI Grant Proposals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DL","authors_text":"Alexandru Marcoci, Angelo Salatino, Gemma Derrick, Kara Moraw, Rosa Filgueira, Sarah Callaghan, Xingran Ruan","submitted_at":"2026-06-29T13:45:28Z","abstract_excerpt":"This paper presents preliminary findings from a UKRI-funded Metascience project comparing three LLM-based approaches, GPT-4o, Mistral, and a bespoke algorithm, DSIT-Taxonomies, for extracting and classifying research entities from funding proposals. Our project \"Tracking Stars and Unicorns\" aims to identify early signals of emerging research areas to inform public investment. Our methodology employed a three-stage pipeline, leveraging Mistral for primary entity extraction and mapping against the OpenAlex Topics taxonomy. We evaluated our approach across 42 proposals' abstracts from different a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30304","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/2606.30304/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":"2026-06-30T02:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PFfc/7G/ftnVyDXhs9m0aQCvKm3f1w7HjJMIxh2TrS4Tsn8YhUmgYSmKbmPXnXtVPvSIZOPaFEbJGekOrnJIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:31:41.208149Z"},"content_sha256":"51f22aa95cd1c107d097acb4b76efeb1bd7f5401f4e1170f77bf66920b082695","schema_version":"1.0","event_id":"sha256:51f22aa95cd1c107d097acb4b76efeb1bd7f5401f4e1170f77bf66920b082695"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRPGDC6MS5JIGRL3B6RP7SVSRC/bundle.json","state_url":"https://pith.science/pith/CRPGDC6MS5JIGRL3B6RP7SVSRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRPGDC6MS5JIGRL3B6RP7SVSRC/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":"2026-08-04T14:31:41Z","links":{"resolver":"https://pith.science/pith/CRPGDC6MS5JIGRL3B6RP7SVSRC","bundle":"https://pith.science/pith/CRPGDC6MS5JIGRL3B6RP7SVSRC/bundle.json","state":"https://pith.science/pith/CRPGDC6MS5JIGRL3B6RP7SVSRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRPGDC6MS5JIGRL3B6RP7SVSRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CRPGDC6MS5JIGRL3B6RP7SVSRC","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":"1fdbe2330e697594f5fcf375d230cb1f8299ce7aa4d11062fc0e2f3e1f00de9e","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-29T13:45:28Z","title_canon_sha256":"9db6127861ee3ce5befc42086e265a235c4890f4e94045c3a4bfa919e444eb65"},"schema_version":"1.0","source":{"id":"2606.30304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30304","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30304v1","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30304","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"CRPGDC6MS5JI","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"CRPGDC6MS5JIGRL3","created_at":"2026-06-30T02:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"CRPGDC6M","created_at":"2026-06-30T02:17:58Z"}],"graph_snapshots":[{"event_id":"sha256:51f22aa95cd1c107d097acb4b76efeb1bd7f5401f4e1170f77bf66920b082695","target":"graph","created_at":"2026-06-30T02:17:58Z","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/2606.30304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents preliminary findings from a UKRI-funded Metascience project comparing three LLM-based approaches, GPT-4o, Mistral, and a bespoke algorithm, DSIT-Taxonomies, for extracting and classifying research entities from funding proposals. Our project \"Tracking Stars and Unicorns\" aims to identify early signals of emerging research areas to inform public investment. Our methodology employed a three-stage pipeline, leveraging Mistral for primary entity extraction and mapping against the OpenAlex Topics taxonomy. We evaluated our approach across 42 proposals' abstracts from different a","authors_text":"Alexandru Marcoci, Angelo Salatino, Gemma Derrick, Kara Moraw, Rosa Filgueira, Sarah Callaghan, Xingran Ruan","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-29T13:45:28Z","title":"Research Entity Extraction and Topic Detection from UKRI Grant Proposals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30304","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:c98d900cfd0512f64230591d5bbcb5da5e2eb7488a1b10e17c1f12f471565fd9","target":"record","created_at":"2026-06-30T02:17:58Z","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":"1fdbe2330e697594f5fcf375d230cb1f8299ce7aa4d11062fc0e2f3e1f00de9e","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-29T13:45:28Z","title_canon_sha256":"9db6127861ee3ce5befc42086e265a235c4890f4e94045c3a4bfa919e444eb65"},"schema_version":"1.0","source":{"id":"2606.30304","kind":"arxiv","version":1}},"canonical_sha256":"145e618bcc975283457b0fa2ffcab288b4fb77ce5194fcbb1b622e04aec57755","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"145e618bcc975283457b0fa2ffcab288b4fb77ce5194fcbb1b622e04aec57755","first_computed_at":"2026-06-30T02:17:58.198012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:58.198012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J1J6PKkOVC/Ia3cxQ+m90Ybxemwjx2/NDwWhO7LizCThTSV6rd2Qgq7yNxMAdPCMvuo2oL800pkEnTjw8rtICQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:58.198627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c98d900cfd0512f64230591d5bbcb5da5e2eb7488a1b10e17c1f12f471565fd9","sha256:51f22aa95cd1c107d097acb4b76efeb1bd7f5401f4e1170f77bf66920b082695"],"state_sha256":"d15cf74f6ac98dba4b9502870afb0f7345e706997c32ec1b359b809d1af3a3da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fFV6+qJmEIdJZw95dd6W3XS6H4xPlJ17RxBvYjJf/C+PaAtlErgF8RnchYUVyXBODAmzPjgxRpw3YM5Zw+F1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:31:41.249354Z","bundle_sha256":"f294f680f9986ceaf7536879ce2d61685824000e81017f175c788158244e2e68"}}