{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZJAAEM6WCBXFRDTS7WPL5WBQHG","short_pith_number":"pith:ZJAAEM6W","canonical_record":{"source":{"id":"2412.18552","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:05:26Z","cross_cats_sorted":[],"title_canon_sha256":"c2c85bec35b63b3e447563ead36ab0a8088ac9d70a00108e2a7305eac7310372","abstract_canon_sha256":"32ef0b521db99df5f71a422d28e04d13e8f6846a622cc982a6d90589f352b08c"},"schema_version":"1.0"},"canonical_sha256":"ca400233d6106e588e72fd9ebed83039befb1501d550fe90cdae907f6fb45d37","source":{"kind":"arxiv","id":"2412.18552","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18552","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18552v2","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18552","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZJAAEM6WCBXF","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_16","alias_value":"ZJAAEM6WCBXFRDTS","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_8","alias_value":"ZJAAEM6W","created_at":"2026-07-05T09:55:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZJAAEM6WCBXFRDTS7WPL5WBQHG","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18552","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:05:26Z","cross_cats_sorted":[],"title_canon_sha256":"c2c85bec35b63b3e447563ead36ab0a8088ac9d70a00108e2a7305eac7310372","abstract_canon_sha256":"32ef0b521db99df5f71a422d28e04d13e8f6846a622cc982a6d90589f352b08c"},"schema_version":"1.0"},"canonical_sha256":"ca400233d6106e588e72fd9ebed83039befb1501d550fe90cdae907f6fb45d37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:15.703291Z","signature_b64":"bUw52MJaUxe5d1XlpJUFEFWI4Ttyi9YYhHGnXo1zr68e9r9LzPZxTU6McYOBDI6T+ROx48gY1AcI2RB3QCrqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca400233d6106e588e72fd9ebed83039befb1501d550fe90cdae907f6fb45d37","last_reissued_at":"2026-07-05T09:55:15.702869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:15.702869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18552","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":"2026-07-05T09:55:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wioXLR0VJiUZVN+TZCE5SmrMJ59KQT8+evWFB4Hh4JstK0YZTb4ps2ES7vmDFRK14JGNdun8dS5FkDLdm2aAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:38:26.815531Z"},"content_sha256":"086b79ae6a198f71a5c6fde894255413419d1f4cae5a7c1772516de30ed47884","schema_version":"1.0","event_id":"sha256:086b79ae6a198f71a5c6fde894255413419d1f4cae5a7c1772516de30ed47884"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZJAAEM6WCBXFRDTS7WPL5WBQHG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Fine-grained Sentiment Understanding from Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guangyu Xie, Hongling Xu, Jianzhu Bao, Kaiheng Hou, Qianlong Wang, Ruifeng Xu, Shiwei Chen, Yice Zhang","submitted_at":"2024-12-24T17:05:26Z","abstract_excerpt":"Fine-grained sentiment analysis (FSA) aims to extract and summarize user opinions from vast opinionated text. Recent studies demonstrate that large language models (LLMs) possess exceptional sentiment understanding capabilities. However, directly deploying LLMs for FSA applications incurs high inference costs. Therefore, this paper investigates the distillation of fine-grained sentiment understanding from LLMs into small language models (SLMs). We prompt LLMs to examine and interpret the sentiments of given reviews and then utilize the generated content to pretrain SLMs. Additionally, we devel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18552","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/2412.18552/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":"2026-07-05T09:55:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bifAbWHSz1h0Q8Fl5nk5LOS3bQK2m5WV3GZlsqtWiDX/DSdc1OJ6kC8FCSwFAF/6Rt+kKqk7PeiFv7K4gV+4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:38:26.815912Z"},"content_sha256":"c7e5714a0ccf55fde4c98d464db2431dca43a8e9830cc74d0a0bc365320571b7","schema_version":"1.0","event_id":"sha256:c7e5714a0ccf55fde4c98d464db2431dca43a8e9830cc74d0a0bc365320571b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJAAEM6WCBXFRDTS7WPL5WBQHG/bundle.json","state_url":"https://pith.science/pith/ZJAAEM6WCBXFRDTS7WPL5WBQHG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJAAEM6WCBXFRDTS7WPL5WBQHG/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":"2026-08-07T03:38:26Z","links":{"resolver":"https://pith.science/pith/ZJAAEM6WCBXFRDTS7WPL5WBQHG","bundle":"https://pith.science/pith/ZJAAEM6WCBXFRDTS7WPL5WBQHG/bundle.json","state":"https://pith.science/pith/ZJAAEM6WCBXFRDTS7WPL5WBQHG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJAAEM6WCBXFRDTS7WPL5WBQHG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZJAAEM6WCBXFRDTS7WPL5WBQHG","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":"32ef0b521db99df5f71a422d28e04d13e8f6846a622cc982a6d90589f352b08c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:05:26Z","title_canon_sha256":"c2c85bec35b63b3e447563ead36ab0a8088ac9d70a00108e2a7305eac7310372"},"schema_version":"1.0","source":{"id":"2412.18552","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18552","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18552v2","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18552","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_12","alias_value":"ZJAAEM6WCBXF","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_16","alias_value":"ZJAAEM6WCBXFRDTS","created_at":"2026-07-05T09:55:15Z"},{"alias_kind":"pith_short_8","alias_value":"ZJAAEM6W","created_at":"2026-07-05T09:55:15Z"}],"graph_snapshots":[{"event_id":"sha256:c7e5714a0ccf55fde4c98d464db2431dca43a8e9830cc74d0a0bc365320571b7","target":"graph","created_at":"2026-07-05T09:55:15Z","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/2412.18552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained sentiment analysis (FSA) aims to extract and summarize user opinions from vast opinionated text. Recent studies demonstrate that large language models (LLMs) possess exceptional sentiment understanding capabilities. However, directly deploying LLMs for FSA applications incurs high inference costs. Therefore, this paper investigates the distillation of fine-grained sentiment understanding from LLMs into small language models (SLMs). We prompt LLMs to examine and interpret the sentiments of given reviews and then utilize the generated content to pretrain SLMs. Additionally, we devel","authors_text":"Guangyu Xie, Hongling Xu, Jianzhu Bao, Kaiheng Hou, Qianlong Wang, Ruifeng Xu, Shiwei Chen, Yice Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:05:26Z","title":"Distilling Fine-grained Sentiment Understanding from Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18552","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":"sha256:086b79ae6a198f71a5c6fde894255413419d1f4cae5a7c1772516de30ed47884","target":"record","created_at":"2026-07-05T09:55:15Z","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":"32ef0b521db99df5f71a422d28e04d13e8f6846a622cc982a6d90589f352b08c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-24T17:05:26Z","title_canon_sha256":"c2c85bec35b63b3e447563ead36ab0a8088ac9d70a00108e2a7305eac7310372"},"schema_version":"1.0","source":{"id":"2412.18552","kind":"arxiv","version":2}},"canonical_sha256":"ca400233d6106e588e72fd9ebed83039befb1501d550fe90cdae907f6fb45d37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca400233d6106e588e72fd9ebed83039befb1501d550fe90cdae907f6fb45d37","first_computed_at":"2026-07-05T09:55:15.702869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:15.702869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bUw52MJaUxe5d1XlpJUFEFWI4Ttyi9YYhHGnXo1zr68e9r9LzPZxTU6McYOBDI6T+ROx48gY1AcI2RB3QCrqCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:15.703291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18552","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:086b79ae6a198f71a5c6fde894255413419d1f4cae5a7c1772516de30ed47884","sha256:c7e5714a0ccf55fde4c98d464db2431dca43a8e9830cc74d0a0bc365320571b7"],"state_sha256":"4d53c556a1a0ac46a0ebf81a273d4f3dea11c680e40cd9f0b6749de76a2ea22c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ZLYfYf2/D0iOlJlix0xU3sG5gvlPwtJByVbfWma1/5hAhVVl7E0CQav0RS+NK1VmZZ9hCD9HS8/R/aACxXnCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:38:26.818660Z","bundle_sha256":"489aabbd5dadf7a3296615d89cc2d834542c41a67d4c849500b827a141cd4374"}}