{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:F4LHOEQ6K5L7IHAUDBAOPJOSU5","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":"d6ed89f59211e5cbe22bf4ac13daffcf9f06feb723a8a5b916085926d353bad7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-12T04:19:17Z","title_canon_sha256":"0003e76f56ceef2ced0248b77020953512ebe131d7b156a22a4d729ea5b62893"},"schema_version":"1.0","source":{"id":"2109.05427","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.05427","created_at":"2026-07-05T03:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2109.05427v1","created_at":"2026-07-05T03:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05427","created_at":"2026-07-05T03:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"F4LHOEQ6K5L7","created_at":"2026-07-05T03:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"F4LHOEQ6K5L7IHAU","created_at":"2026-07-05T03:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"F4LHOEQ6","created_at":"2026-07-05T03:13:38Z"}],"graph_snapshots":[{"event_id":"sha256:1e2f6a8badb05a45be0938a573698603420cbf08f571a653da43a58379340776","target":"graph","created_at":"2026-07-05T03:13:38Z","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/2109.05427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is key to improving performance on fine-grained tasks. In this work, we analyse the contrastive fine-tuning of pre-trained language models on two fine-grained text classification tasks, emotion classification and sentiment analysis. We adaptively embed class relationships into a contrastive objective function to help differently weigh the positives and negatives, and in p","authors_text":"Desmond C. Ong, Varsha Suresh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-12T04:19:17Z","title":"Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05427","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:a8ee83a842351c6d687c20d2a4bf37059a598111306557430ab9b4330db903b1","target":"record","created_at":"2026-07-05T03:13:38Z","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":"d6ed89f59211e5cbe22bf4ac13daffcf9f06feb723a8a5b916085926d353bad7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-12T04:19:17Z","title_canon_sha256":"0003e76f56ceef2ced0248b77020953512ebe131d7b156a22a4d729ea5b62893"},"schema_version":"1.0","source":{"id":"2109.05427","kind":"arxiv","version":1}},"canonical_sha256":"2f1677121e5757f41c141840e7a5d2a754b86e3e3edc51bbcf962807e78da580","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f1677121e5757f41c141840e7a5d2a754b86e3e3edc51bbcf962807e78da580","first_computed_at":"2026-07-05T03:13:38.830691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:13:38.830691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LlzOLdiNdtRJzt0koFmpP//ZgL2YIY0GT/5WL9mvWUh9TJghoMpD5VrbnIBZfgRBYSYYBjGYg4YtpM6AiU8HDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:13:38.831100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.05427","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8ee83a842351c6d687c20d2a4bf37059a598111306557430ab9b4330db903b1","sha256:1e2f6a8badb05a45be0938a573698603420cbf08f571a653da43a58379340776"],"state_sha256":"bb8aed40680e85e452ffd40362e49020a58452a6a5b2dd5458a8bc094c936e5d"}