{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GQD62BWYQUZE2NRJO7T5QW7ESU","short_pith_number":"pith:GQD62BWY","canonical_record":{"source":{"id":"2505.18040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T15:44:26Z","cross_cats_sorted":[],"title_canon_sha256":"a459c6361f56c5430e9d563e1aa88cd1cbd8244dbcea92c670cbb79b4d30a2ce","abstract_canon_sha256":"05d194bb91efbe1d997e280d8c11ada3866b5b6b225bedc1afdd8f34aea0b129"},"schema_version":"1.0"},"canonical_sha256":"3407ed06d885324d362977e7d85be49517b85b6ac5cbe982c783effe9054f7be","source":{"kind":"arxiv","id":"2505.18040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18040","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18040v1","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18040","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"GQD62BWYQUZE","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"GQD62BWYQUZE2NRJ","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"GQD62BWY","created_at":"2026-07-05T11:08:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GQD62BWYQUZE2NRJO7T5QW7ESU","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T15:44:26Z","cross_cats_sorted":[],"title_canon_sha256":"a459c6361f56c5430e9d563e1aa88cd1cbd8244dbcea92c670cbb79b4d30a2ce","abstract_canon_sha256":"05d194bb91efbe1d997e280d8c11ada3866b5b6b225bedc1afdd8f34aea0b129"},"schema_version":"1.0"},"canonical_sha256":"3407ed06d885324d362977e7d85be49517b85b6ac5cbe982c783effe9054f7be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:35.812018Z","signature_b64":"G31xIaz5GDVfZ86P3byXYyt/lHTzqTH+DkshCH2ueyBX6VZFUP6ItC9m9Uw5ae6eoCfR4C+VbljEJ9VPkMsmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3407ed06d885324d362977e7d85be49517b85b6ac5cbe982c783effe9054f7be","last_reissued_at":"2026-07-05T11:08:35.811535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:35.811535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18040","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":"2026-07-05T11:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YwYZyI9ONGa5ZXramg0Hwdj89AVfiEQ/Ta3C2OKPzH52er4RQpnbMLYdS31LSEiuEAncshnDTCNZbkA6+eGeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:50:57.886365Z"},"content_sha256":"53962cd654edd748a467038fefc0850701a7201f94359a43a6b2baf699510349","schema_version":"1.0","event_id":"sha256:53962cd654edd748a467038fefc0850701a7201f94359a43a6b2baf699510349"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GQD62BWYQUZE2NRJO7T5QW7ESU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Emily Mower Provost, Minxue Niu","submitted_at":"2025-05-23T15:44:26Z","abstract_excerpt":"The ability to handle various emotion labels without dedicated training is crucial for building adaptable Emotion Recognition (ER) systems. Conventional ER models rely on training using fixed label sets and struggle to generalize beyond them. On the other hand, Large Language Models (LLMs) have shown strong zero-shot ER performance across diverse label spaces, but their scale limits their use on edge devices. In this work, we propose a contrastive distillation framework that transfers rich emotional knowledge from LLMs into a compact model without the use of human annotations. We use GPT-4 to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18040","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/2505.18040/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":"2026-07-05T11:08:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fhPDtmWwEXLhhU2Rl0GXHiVOklO9PSdC701859vuAuD46ULLGII3QGucP6GtdyQrYq8njthBQb0T8oqW5gALAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:50:57.886739Z"},"content_sha256":"663e50b1f0d3c2e57afc9329e92d0b6f5151d161cdc0bbfdddf7f42885962cd6","schema_version":"1.0","event_id":"sha256:663e50b1f0d3c2e57afc9329e92d0b6f5151d161cdc0bbfdddf7f42885962cd6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQD62BWYQUZE2NRJO7T5QW7ESU/bundle.json","state_url":"https://pith.science/pith/GQD62BWYQUZE2NRJO7T5QW7ESU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQD62BWYQUZE2NRJO7T5QW7ESU/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":"2026-08-18T16:50:57Z","links":{"resolver":"https://pith.science/pith/GQD62BWYQUZE2NRJO7T5QW7ESU","bundle":"https://pith.science/pith/GQD62BWYQUZE2NRJO7T5QW7ESU/bundle.json","state":"https://pith.science/pith/GQD62BWYQUZE2NRJO7T5QW7ESU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQD62BWYQUZE2NRJO7T5QW7ESU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GQD62BWYQUZE2NRJO7T5QW7ESU","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":"05d194bb91efbe1d997e280d8c11ada3866b5b6b225bedc1afdd8f34aea0b129","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T15:44:26Z","title_canon_sha256":"a459c6361f56c5430e9d563e1aa88cd1cbd8244dbcea92c670cbb79b4d30a2ce"},"schema_version":"1.0","source":{"id":"2505.18040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18040","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18040v1","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18040","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"GQD62BWYQUZE","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"GQD62BWYQUZE2NRJ","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"GQD62BWY","created_at":"2026-07-05T11:08:35Z"}],"graph_snapshots":[{"event_id":"sha256:663e50b1f0d3c2e57afc9329e92d0b6f5151d161cdc0bbfdddf7f42885962cd6","target":"graph","created_at":"2026-07-05T11:08:35Z","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/2505.18040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability to handle various emotion labels without dedicated training is crucial for building adaptable Emotion Recognition (ER) systems. Conventional ER models rely on training using fixed label sets and struggle to generalize beyond them. On the other hand, Large Language Models (LLMs) have shown strong zero-shot ER performance across diverse label spaces, but their scale limits their use on edge devices. In this work, we propose a contrastive distillation framework that transfers rich emotional knowledge from LLMs into a compact model without the use of human annotations. We use GPT-4 to ","authors_text":"Emily Mower Provost, Minxue Niu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T15:44:26Z","title":"Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18040","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":"sha256:53962cd654edd748a467038fefc0850701a7201f94359a43a6b2baf699510349","target":"record","created_at":"2026-07-05T11:08:35Z","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":"05d194bb91efbe1d997e280d8c11ada3866b5b6b225bedc1afdd8f34aea0b129","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T15:44:26Z","title_canon_sha256":"a459c6361f56c5430e9d563e1aa88cd1cbd8244dbcea92c670cbb79b4d30a2ce"},"schema_version":"1.0","source":{"id":"2505.18040","kind":"arxiv","version":1}},"canonical_sha256":"3407ed06d885324d362977e7d85be49517b85b6ac5cbe982c783effe9054f7be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3407ed06d885324d362977e7d85be49517b85b6ac5cbe982c783effe9054f7be","first_computed_at":"2026-07-05T11:08:35.811535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:35.811535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G31xIaz5GDVfZ86P3byXYyt/lHTzqTH+DkshCH2ueyBX6VZFUP6ItC9m9Uw5ae6eoCfR4C+VbljEJ9VPkMsmBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:35.812018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53962cd654edd748a467038fefc0850701a7201f94359a43a6b2baf699510349","sha256:663e50b1f0d3c2e57afc9329e92d0b6f5151d161cdc0bbfdddf7f42885962cd6"],"state_sha256":"7d6163c44827bdd941c7df8339c5bcd6fc6b81369ab8f1a753779338895b4826"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ddNqP9fPZP82K6YdFjXfaEZWqk4PDfTc6jYxAyYfEPaSPJLprsMqUf/AK0ZSYLnHbhiwsZ3YZjoI9fkZ4YRAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:50:57.889144Z","bundle_sha256":"c2aecfe2fdbd8141b5aab4d9cabda1db954862e4b7069a5bf4dea014f3384974"}}