{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JRVXXQGC7KGY5F6ISMK4BL4D7P","short_pith_number":"pith:JRVXXQGC","canonical_record":{"source":{"id":"2404.03868","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:53:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b53662630a5dfbf1e5d0903bb4b40f324013a1eb8041cc6a0eaf49ef9afe7c90","abstract_canon_sha256":"e6e081e349f012f4467b796afaa66ec2b3e3192f47301180eca742433b6243c4"},"schema_version":"1.0"},"canonical_sha256":"4c6b7bc0c2fa8d8e97c89315c0af83fbf96844ff6fec96fb1f51101c606ea8d5","source":{"kind":"arxiv","id":"2404.03868","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03868","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03868v2","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03868","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"JRVXXQGC7KGY","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"JRVXXQGC7KGY5F6I","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"JRVXXQGC","created_at":"2026-07-05T09:14:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JRVXXQGC7KGY5F6ISMK4BL4D7P","target":"record","payload":{"canonical_record":{"source":{"id":"2404.03868","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:53:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b53662630a5dfbf1e5d0903bb4b40f324013a1eb8041cc6a0eaf49ef9afe7c90","abstract_canon_sha256":"e6e081e349f012f4467b796afaa66ec2b3e3192f47301180eca742433b6243c4"},"schema_version":"1.0"},"canonical_sha256":"4c6b7bc0c2fa8d8e97c89315c0af83fbf96844ff6fec96fb1f51101c606ea8d5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:31.621400Z","signature_b64":"C0AgBUoJbRyiygKniKsUo6ja87KLHeaMbCC9MOXTnlsC1vmxgXHD0RWmY5k1Wu+ienCQb0o0oSzChlVUZqZLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c6b7bc0c2fa8d8e97c89315c0af83fbf96844ff6fec96fb1f51101c606ea8d5","last_reissued_at":"2026-07-05T09:14:31.620891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:31.620891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.03868","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":"2026-07-05T09:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcFBYa42/vLR6A1JXwo+u4FDxOhZ0pB8s5GdB7t9NgTJB4U/G3UhPDczO1rSvjPq4SBlPgyuVxZJoC2e+PwTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:02:20.301962Z"},"content_sha256":"1ffd20955a53b639bf8f33ab6bf4602a86f399867e76ffc79e47b0e090996042","schema_version":"1.0","event_id":"sha256:1ffd20955a53b639bf8f33ab6bf4602a86f399867e76ffc79e47b0e090996042"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JRVXXQGC7KGY5F6ISMK4BL4D7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Zhang, Harold Soh","submitted_at":"2024-04-05T02:53:51Z","abstract_excerpt":"In this work, we are interested in automated methods for knowledge graph creation (KGC) from input text. Progress on large language models (LLMs) has prompted a series of recent works applying them to KGC, e.g., via zero/few-shot prompting. Despite successes on small domain-specific datasets, these models face difficulties scaling up to text common in many real-world applications. A principal issue is that, in prior methods, the KG schema has to be included in the LLM prompt to generate valid triplets; larger and more complex schemas easily exceed the LLMs' context window length. Furthermore, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03868","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/2404.03868/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":"2026-07-05T09:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7iRqsnzgILywSDGHgCjw9pPmWFXZpoPJhkwBYjsPZN3F+oONgcfusUgq2ytDuw13KrYiA20rGcwLJbAxW5zWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:02:20.302870Z"},"content_sha256":"9c5e43a014deb5af9937dde3ba7eb744515eb4fe18130dc5b0dc176f575e5b5c","schema_version":"1.0","event_id":"sha256:9c5e43a014deb5af9937dde3ba7eb744515eb4fe18130dc5b0dc176f575e5b5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/bundle.json","state_url":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/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":"2026-08-09T11:02:20Z","links":{"resolver":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P","bundle":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/bundle.json","state":"https://pith.science/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JRVXXQGC7KGY5F6ISMK4BL4D7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JRVXXQGC7KGY5F6ISMK4BL4D7P","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":"e6e081e349f012f4467b796afaa66ec2b3e3192f47301180eca742433b6243c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:53:51Z","title_canon_sha256":"b53662630a5dfbf1e5d0903bb4b40f324013a1eb8041cc6a0eaf49ef9afe7c90"},"schema_version":"1.0","source":{"id":"2404.03868","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03868","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03868v2","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03868","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"JRVXXQGC7KGY","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"JRVXXQGC7KGY5F6I","created_at":"2026-07-05T09:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"JRVXXQGC","created_at":"2026-07-05T09:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:9c5e43a014deb5af9937dde3ba7eb744515eb4fe18130dc5b0dc176f575e5b5c","target":"graph","created_at":"2026-07-05T09:14:31Z","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/2404.03868/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we are interested in automated methods for knowledge graph creation (KGC) from input text. Progress on large language models (LLMs) has prompted a series of recent works applying them to KGC, e.g., via zero/few-shot prompting. Despite successes on small domain-specific datasets, these models face difficulties scaling up to text common in many real-world applications. A principal issue is that, in prior methods, the KG schema has to be included in the LLM prompt to generate valid triplets; larger and more complex schemas easily exceed the LLMs' context window length. Furthermore, ","authors_text":"Bowen Zhang, Harold Soh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:53:51Z","title":"Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03868","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":"sha256:1ffd20955a53b639bf8f33ab6bf4602a86f399867e76ffc79e47b0e090996042","target":"record","created_at":"2026-07-05T09:14:31Z","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":"e6e081e349f012f4467b796afaa66ec2b3e3192f47301180eca742433b6243c4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T02:53:51Z","title_canon_sha256":"b53662630a5dfbf1e5d0903bb4b40f324013a1eb8041cc6a0eaf49ef9afe7c90"},"schema_version":"1.0","source":{"id":"2404.03868","kind":"arxiv","version":2}},"canonical_sha256":"4c6b7bc0c2fa8d8e97c89315c0af83fbf96844ff6fec96fb1f51101c606ea8d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c6b7bc0c2fa8d8e97c89315c0af83fbf96844ff6fec96fb1f51101c606ea8d5","first_computed_at":"2026-07-05T09:14:31.620891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:31.620891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C0AgBUoJbRyiygKniKsUo6ja87KLHeaMbCC9MOXTnlsC1vmxgXHD0RWmY5k1Wu+ienCQb0o0oSzChlVUZqZLDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:31.621400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03868","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ffd20955a53b639bf8f33ab6bf4602a86f399867e76ffc79e47b0e090996042","sha256:9c5e43a014deb5af9937dde3ba7eb744515eb4fe18130dc5b0dc176f575e5b5c"],"state_sha256":"f39809bd18a724b8b595fb3d7351783a263699dad0a34487203955bc831b4973"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BntB8BiSExqDcwSLlsGPbF3MM+PlfBC5wMYPhJBEhz12HMTiyoJ3B25WpoeQ5YP1t/q0UM/MDlOrUvqzXIh8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:02:20.320138Z","bundle_sha256":"a157dfcd411154dd804192d1867329b676114ea4beea97a31463d8975997c458"}}