{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4RWU7AQWULJT4IN2PYZXLAOR6B","short_pith_number":"pith:4RWU7AQW","canonical_record":{"source":{"id":"2402.14373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T08:26:56Z","cross_cats_sorted":[],"title_canon_sha256":"7bb17cd0d313a2f061c69618d66233b20e40b4e5e4d008d54def4b5b930a0485","abstract_canon_sha256":"93fb8c4fb6e0ca7afaa718705827ed79543b2a157144ceea1ff1097ab3c98c96"},"schema_version":"1.0"},"canonical_sha256":"e46d4f8216a2d33e21ba7e337581d1f07a46f0407ae045923c30112503a19a56","source":{"kind":"arxiv","id":"2402.14373","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14373","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14373v2","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14373","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"4RWU7AQWULJT","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"4RWU7AQWULJT4IN2","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"4RWU7AQW","created_at":"2026-07-05T09:52:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4RWU7AQWULJT4IN2PYZXLAOR6B","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T08:26:56Z","cross_cats_sorted":[],"title_canon_sha256":"7bb17cd0d313a2f061c69618d66233b20e40b4e5e4d008d54def4b5b930a0485","abstract_canon_sha256":"93fb8c4fb6e0ca7afaa718705827ed79543b2a157144ceea1ff1097ab3c98c96"},"schema_version":"1.0"},"canonical_sha256":"e46d4f8216a2d33e21ba7e337581d1f07a46f0407ae045923c30112503a19a56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:09.906364Z","signature_b64":"EEyOHrQtR7zViTsuOHiWEuqObnlcvrM93udQlYFZkDicihYhW7Nu84Y2r8S4T7A/8dZPRcbAdR2ML5+HEn4KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e46d4f8216a2d33e21ba7e337581d1f07a46f0407ae045923c30112503a19a56","last_reissued_at":"2026-07-05T09:52:09.905986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:09.905986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14373","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":"2026-07-05T09:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MFwaPZayq6eW7yPBE3mNJDJRUbk3VhiHqBA7tRBudfNzall0iEt8rwa84OtFHjJk57z2o6YSJvejLWdnifxuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:46:31.123923Z"},"content_sha256":"fd814c3db39372c7cd7cf4ec93800faf365af1dfff372333383c06e7802f3ce7","schema_version":"1.0","event_id":"sha256:fd814c3db39372c7cd7cf4ec93800faf365af1dfff372333383c06e7802f3ce7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4RWU7AQWULJT4IN2PYZXLAOR6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Small Language Models as Effective Guides for Large Language Models in Chinese Relation Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Wang, Xuemei Tang","submitted_at":"2024-02-22T08:26:56Z","abstract_excerpt":"Recently, large language models (LLMs) have been successful in relational extraction (RE) tasks, especially in the few-shot learning. An important problem in the field of RE is long-tailed data, while not much attention is paid to this problem using LLM approaches. Therefore, in this paper, we propose SLCoLM, a model collaboration framework, to mitigate the data long-tail problem. In our framework, we use the ``\\textit{Training-Guide-Predict}'' strategy to combine the strengths of small pre-trained language models (SLMs) and LLMs, where a task-specific SLM framework acts as a guider, transfers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14373","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/2402.14373/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":"2026-07-05T09:52:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PrIGD+qTr+zLjKR0CSLi9Ah6C/k7sQDnpFTk7X2FlFGpoHN4C1v3GdxmFny09Vo69W22E9bh6RsuJt7Tl53zAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:46:31.124301Z"},"content_sha256":"7e1746007f1b8dfd20fe76e5262f6cf0db7b8e5b25cd9a868ad48d45a0d5ea91","schema_version":"1.0","event_id":"sha256:7e1746007f1b8dfd20fe76e5262f6cf0db7b8e5b25cd9a868ad48d45a0d5ea91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RWU7AQWULJT4IN2PYZXLAOR6B/bundle.json","state_url":"https://pith.science/pith/4RWU7AQWULJT4IN2PYZXLAOR6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RWU7AQWULJT4IN2PYZXLAOR6B/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":"2026-07-07T10:46:31Z","links":{"resolver":"https://pith.science/pith/4RWU7AQWULJT4IN2PYZXLAOR6B","bundle":"https://pith.science/pith/4RWU7AQWULJT4IN2PYZXLAOR6B/bundle.json","state":"https://pith.science/pith/4RWU7AQWULJT4IN2PYZXLAOR6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RWU7AQWULJT4IN2PYZXLAOR6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4RWU7AQWULJT4IN2PYZXLAOR6B","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":"93fb8c4fb6e0ca7afaa718705827ed79543b2a157144ceea1ff1097ab3c98c96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T08:26:56Z","title_canon_sha256":"7bb17cd0d313a2f061c69618d66233b20e40b4e5e4d008d54def4b5b930a0485"},"schema_version":"1.0","source":{"id":"2402.14373","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14373","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14373v2","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14373","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"4RWU7AQWULJT","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"4RWU7AQWULJT4IN2","created_at":"2026-07-05T09:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"4RWU7AQW","created_at":"2026-07-05T09:52:09Z"}],"graph_snapshots":[{"event_id":"sha256:7e1746007f1b8dfd20fe76e5262f6cf0db7b8e5b25cd9a868ad48d45a0d5ea91","target":"graph","created_at":"2026-07-05T09:52:09Z","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/2402.14373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, large language models (LLMs) have been successful in relational extraction (RE) tasks, especially in the few-shot learning. An important problem in the field of RE is long-tailed data, while not much attention is paid to this problem using LLM approaches. Therefore, in this paper, we propose SLCoLM, a model collaboration framework, to mitigate the data long-tail problem. In our framework, we use the ``\\textit{Training-Guide-Predict}'' strategy to combine the strengths of small pre-trained language models (SLMs) and LLMs, where a task-specific SLM framework acts as a guider, transfers","authors_text":"Jun Wang, Xuemei Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T08:26:56Z","title":"Small Language Models as Effective Guides for Large Language Models in Chinese Relation Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14373","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:fd814c3db39372c7cd7cf4ec93800faf365af1dfff372333383c06e7802f3ce7","target":"record","created_at":"2026-07-05T09:52:09Z","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":"93fb8c4fb6e0ca7afaa718705827ed79543b2a157144ceea1ff1097ab3c98c96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T08:26:56Z","title_canon_sha256":"7bb17cd0d313a2f061c69618d66233b20e40b4e5e4d008d54def4b5b930a0485"},"schema_version":"1.0","source":{"id":"2402.14373","kind":"arxiv","version":2}},"canonical_sha256":"e46d4f8216a2d33e21ba7e337581d1f07a46f0407ae045923c30112503a19a56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e46d4f8216a2d33e21ba7e337581d1f07a46f0407ae045923c30112503a19a56","first_computed_at":"2026-07-05T09:52:09.905986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:09.905986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EEyOHrQtR7zViTsuOHiWEuqObnlcvrM93udQlYFZkDicihYhW7Nu84Y2r8S4T7A/8dZPRcbAdR2ML5+HEn4KCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:09.906364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14373","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd814c3db39372c7cd7cf4ec93800faf365af1dfff372333383c06e7802f3ce7","sha256:7e1746007f1b8dfd20fe76e5262f6cf0db7b8e5b25cd9a868ad48d45a0d5ea91"],"state_sha256":"f96b8a7e34d6f35d814c3b16b2c4bc78478e6acc250305a82445091df8f93ef4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XID+oH0laRyXp2JF9OLAebGhTgMVlu6SBoRsaOPHDyW7Oj3jvvJd/dDZR8dIwwr0/2ZeM0nGPr+BSP76D2K3Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:46:31.126324Z","bundle_sha256":"1cf052b6a84d7179040739916f6a831cfb8d91f06873370e613a555319b444b5"}}