{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ECAKKYA43HXSAWMSHTUHJVQE5U","short_pith_number":"pith:ECAKKYA4","canonical_record":{"source":{"id":"2407.16127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T02:25:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"affbd34903a473f50ae95f352c7f0528a45f0477bb199eec8c72a9edb247c0b9","abstract_canon_sha256":"7e61e6f61f84631c9480f20365c94a9e1be7c80a6c89873365a7d15a278efb80"},"schema_version":"1.0"},"canonical_sha256":"2080a5601cd9ef2059923ce874d604ed24fd8d9fbe65de3f2a8a6009d75d461d","source":{"kind":"arxiv","id":"2407.16127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16127","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16127v1","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16127","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_12","alias_value":"ECAKKYA43HXS","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_16","alias_value":"ECAKKYA43HXSAWMS","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_8","alias_value":"ECAKKYA4","created_at":"2026-07-05T08:47:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ECAKKYA43HXSAWMSHTUHJVQE5U","target":"record","payload":{"canonical_record":{"source":{"id":"2407.16127","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T02:25:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"affbd34903a473f50ae95f352c7f0528a45f0477bb199eec8c72a9edb247c0b9","abstract_canon_sha256":"7e61e6f61f84631c9480f20365c94a9e1be7c80a6c89873365a7d15a278efb80"},"schema_version":"1.0"},"canonical_sha256":"2080a5601cd9ef2059923ce874d604ed24fd8d9fbe65de3f2a8a6009d75d461d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:27.482823Z","signature_b64":"QB7eQfeMW5GpeTsHJnzNQZCvnlh+UliTMP/XPwW/bAIkP2GNUznb0uud+/1F0PNAGj5fT8X8oOFYpxroCUeACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2080a5601cd9ef2059923ce874d604ed24fd8d9fbe65de3f2a8a6009d75d461d","last_reissued_at":"2026-07-05T08:47:27.482240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:27.482240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.16127","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":"2026-07-05T08:47:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"emg70bAGa2QVpGMnOYOkhSNfStBaq4Ts8NRsU/67VOROGdC+XIOILPm7nXG5CdO161B81fe0rP8sRR2B46kOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:35:15.111249Z"},"content_sha256":"00b475225a398c55fdce4d12343cd79f8ecdeedfc2a9b9ef014775d64ad64292","schema_version":"1.0","event_id":"sha256:00b475225a398c55fdce4d12343cd79f8ecdeedfc2a9b9ef014775d64ad64292"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ECAKKYA43HXSAWMSHTUHJVQE5U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Wei Hu, Xiaobin Tian, Yang Liu, Zequn Sun","submitted_at":"2024-07-23T02:25:01Z","abstract_excerpt":"Traditional knowledge graph (KG) completion models learn embeddings to predict missing facts. Recent works attempt to complete KGs in a text-generation manner with large language models (LLMs). However, they need to ground the output of LLMs to KG entities, which inevitably brings errors. In this paper, we present a finetuning framework, DIFT, aiming to unleash the KG completion ability of LLMs and avoid grounding errors. Given an incomplete fact, DIFT employs a lightweight model to obtain candidate entities and finetunes an LLM with discrimination instructions to select the correct one from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16127","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/2407.16127/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":"2026-07-05T08:47:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7IPzewLIL4L7v07WLK8cDfAuNOjZDp2e+rmEK3txl1YnLhzzvks5Yag0dMXpoWDRsY6PWVxl3X8e9/sl9cfMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:35:15.112138Z"},"content_sha256":"db72c1399b6652daab06c17c7e65d3a86839e32a0319ed07528f1556d69bf133","schema_version":"1.0","event_id":"sha256:db72c1399b6652daab06c17c7e65d3a86839e32a0319ed07528f1556d69bf133"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECAKKYA43HXSAWMSHTUHJVQE5U/bundle.json","state_url":"https://pith.science/pith/ECAKKYA43HXSAWMSHTUHJVQE5U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECAKKYA43HXSAWMSHTUHJVQE5U/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":"2026-08-14T23:35:15Z","links":{"resolver":"https://pith.science/pith/ECAKKYA43HXSAWMSHTUHJVQE5U","bundle":"https://pith.science/pith/ECAKKYA43HXSAWMSHTUHJVQE5U/bundle.json","state":"https://pith.science/pith/ECAKKYA43HXSAWMSHTUHJVQE5U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECAKKYA43HXSAWMSHTUHJVQE5U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ECAKKYA43HXSAWMSHTUHJVQE5U","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":"7e61e6f61f84631c9480f20365c94a9e1be7c80a6c89873365a7d15a278efb80","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T02:25:01Z","title_canon_sha256":"affbd34903a473f50ae95f352c7f0528a45f0477bb199eec8c72a9edb247c0b9"},"schema_version":"1.0","source":{"id":"2407.16127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.16127","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"arxiv_version","alias_value":"2407.16127v1","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16127","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_12","alias_value":"ECAKKYA43HXS","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_16","alias_value":"ECAKKYA43HXSAWMS","created_at":"2026-07-05T08:47:27Z"},{"alias_kind":"pith_short_8","alias_value":"ECAKKYA4","created_at":"2026-07-05T08:47:27Z"}],"graph_snapshots":[{"event_id":"sha256:db72c1399b6652daab06c17c7e65d3a86839e32a0319ed07528f1556d69bf133","target":"graph","created_at":"2026-07-05T08:47:27Z","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/2407.16127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional knowledge graph (KG) completion models learn embeddings to predict missing facts. Recent works attempt to complete KGs in a text-generation manner with large language models (LLMs). However, they need to ground the output of LLMs to KG entities, which inevitably brings errors. In this paper, we present a finetuning framework, DIFT, aiming to unleash the KG completion ability of LLMs and avoid grounding errors. Given an incomplete fact, DIFT employs a lightweight model to obtain candidate entities and finetunes an LLM with discrimination instructions to select the correct one from t","authors_text":"Wei Hu, Xiaobin Tian, Yang Liu, Zequn Sun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T02:25:01Z","title":"Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16127","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":"sha256:00b475225a398c55fdce4d12343cd79f8ecdeedfc2a9b9ef014775d64ad64292","target":"record","created_at":"2026-07-05T08:47:27Z","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":"7e61e6f61f84631c9480f20365c94a9e1be7c80a6c89873365a7d15a278efb80","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-23T02:25:01Z","title_canon_sha256":"affbd34903a473f50ae95f352c7f0528a45f0477bb199eec8c72a9edb247c0b9"},"schema_version":"1.0","source":{"id":"2407.16127","kind":"arxiv","version":1}},"canonical_sha256":"2080a5601cd9ef2059923ce874d604ed24fd8d9fbe65de3f2a8a6009d75d461d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2080a5601cd9ef2059923ce874d604ed24fd8d9fbe65de3f2a8a6009d75d461d","first_computed_at":"2026-07-05T08:47:27.482240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:27.482240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QB7eQfeMW5GpeTsHJnzNQZCvnlh+UliTMP/XPwW/bAIkP2GNUznb0uud+/1F0PNAGj5fT8X8oOFYpxroCUeACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:27.482823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.16127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00b475225a398c55fdce4d12343cd79f8ecdeedfc2a9b9ef014775d64ad64292","sha256:db72c1399b6652daab06c17c7e65d3a86839e32a0319ed07528f1556d69bf133"],"state_sha256":"3d73648fb26d52c33f8128b5c7f9aa401c0e9712937a661e524537d6833c1238"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kyl+o9JkUqvvf89VmhHHthd0zVFXO03txbdv5ZDB1JvvYjoCHAhCx8t44uriBfFbgwAVH49M4sYqAaUrv64nDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T23:35:15.118806Z","bundle_sha256":"9e745e7be8c7cbb246983fbc65d8d5242c1a304d048b756f8d9c409b8d245755"}}