{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CKESZHD7AOIG3HWXUMHSPJC2R6","short_pith_number":"pith:CKESZHD7","canonical_record":{"source":{"id":"2311.08640","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T01:28:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"30560fd66542df310d52a3725e30037eaff34ba4898de58c2c3a403f1194a64a","abstract_canon_sha256":"87c4f9fb8a8c7642ba284976864ac46148149c56c20df45d1df8dfa9b091fd87"},"schema_version":"1.0"},"canonical_sha256":"12892c9c7f03906d9ed7a30f27a45a8fbe966a9249639edca5283669ed28c790","source":{"kind":"arxiv","id":"2311.08640","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08640","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08640v4","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08640","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_12","alias_value":"CKESZHD7AOIG","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_16","alias_value":"CKESZHD7AOIG3HWX","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_8","alias_value":"CKESZHD7","created_at":"2026-07-05T08:51:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CKESZHD7AOIG3HWXUMHSPJC2R6","target":"record","payload":{"canonical_record":{"source":{"id":"2311.08640","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T01:28:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"30560fd66542df310d52a3725e30037eaff34ba4898de58c2c3a403f1194a64a","abstract_canon_sha256":"87c4f9fb8a8c7642ba284976864ac46148149c56c20df45d1df8dfa9b091fd87"},"schema_version":"1.0"},"canonical_sha256":"12892c9c7f03906d9ed7a30f27a45a8fbe966a9249639edca5283669ed28c790","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:44.711239Z","signature_b64":"PL9B9xxMSeBihX+jugSlK7a8+YiZjRpfL/HZzz5P7ZOKa9EXZvLmoxnA4q91xnsLfKzaOBQTFvOImjefNEnoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12892c9c7f03906d9ed7a30f27a45a8fbe966a9249639edca5283669ed28c790","last_reissued_at":"2026-07-05T08:51:44.710769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:44.710769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.08640","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:51:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"reVI1W5VIp69Jx0RaQym707MVz8nfsfPCbmC90FiqDlARfokVqFm1MyG4+YnZLCHNPy2SUPZ9yjInmEAutCBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:11:20.867367Z"},"content_sha256":"a04ab83c6a8cdc766c65236a8de12962ce6b35c1527d6f3c136ecc7d6559fb86","schema_version":"1.0","event_id":"sha256:a04ab83c6a8cdc766c65236a8de12962ce6b35c1527d6f3c136ecc7d6559fb86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CKESZHD7AOIG3HWXUMHSPJC2R6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrew Drozdov, Andrew McCallum, Benjamin Rozonoyer, Jay-Yoon Lee, Jiachen Zhao, Md Arafat Sultan, Mohit Iyyer, Wenlong Zhao","submitted_at":"2023-11-15T01:28:28Z","abstract_excerpt":"We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model, and meanwhile, few-shot prompted large language models (LLMs) exhibit room for improvement. In this paper, we present the discovery that a student model distilled from a few-shot prompted LLM can commonly generalize better than its teacher to unseen examples on such tasks. We find that the student is able to learn a general pattern from the high-quality pseudolabels produced by the teacher during knowledge distillation (KD), and favorably not a general pattern from the low-qua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08640","kind":"arxiv","version":4},"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/2311.08640/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":"2026-07-05T08:51:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/svy+3DUJoHLyewgfLcpavICNHsC7RtfPa+STP74UhLGVO8Nzui3oCj/OcQTx7De7PmiUtd5Vz6IiPa40LgsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T00:11:20.867757Z"},"content_sha256":"a07f565314719967520d7b77a3da1ce31b279334f0d40e941b2c1bad46adb5b9","schema_version":"1.0","event_id":"sha256:a07f565314719967520d7b77a3da1ce31b279334f0d40e941b2c1bad46adb5b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKESZHD7AOIG3HWXUMHSPJC2R6/bundle.json","state_url":"https://pith.science/pith/CKESZHD7AOIG3HWXUMHSPJC2R6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKESZHD7AOIG3HWXUMHSPJC2R6/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":"2026-07-07T00:11:20Z","links":{"resolver":"https://pith.science/pith/CKESZHD7AOIG3HWXUMHSPJC2R6","bundle":"https://pith.science/pith/CKESZHD7AOIG3HWXUMHSPJC2R6/bundle.json","state":"https://pith.science/pith/CKESZHD7AOIG3HWXUMHSPJC2R6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKESZHD7AOIG3HWXUMHSPJC2R6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CKESZHD7AOIG3HWXUMHSPJC2R6","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":"87c4f9fb8a8c7642ba284976864ac46148149c56c20df45d1df8dfa9b091fd87","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T01:28:28Z","title_canon_sha256":"30560fd66542df310d52a3725e30037eaff34ba4898de58c2c3a403f1194a64a"},"schema_version":"1.0","source":{"id":"2311.08640","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.08640","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"arxiv_version","alias_value":"2311.08640v4","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.08640","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_12","alias_value":"CKESZHD7AOIG","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_16","alias_value":"CKESZHD7AOIG3HWX","created_at":"2026-07-05T08:51:44Z"},{"alias_kind":"pith_short_8","alias_value":"CKESZHD7","created_at":"2026-07-05T08:51:44Z"}],"graph_snapshots":[{"event_id":"sha256:a07f565314719967520d7b77a3da1ce31b279334f0d40e941b2c1bad46adb5b9","target":"graph","created_at":"2026-07-05T08:51:44Z","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/2311.08640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study semi-supervised sequence generation tasks, where the few labeled examples are too scarce to finetune a model, and meanwhile, few-shot prompted large language models (LLMs) exhibit room for improvement. In this paper, we present the discovery that a student model distilled from a few-shot prompted LLM can commonly generalize better than its teacher to unseen examples on such tasks. We find that the student is able to learn a general pattern from the high-quality pseudolabels produced by the teacher during knowledge distillation (KD), and favorably not a general pattern from the low-qua","authors_text":"Andrew Drozdov, Andrew McCallum, Benjamin Rozonoyer, Jay-Yoon Lee, Jiachen Zhao, Md Arafat Sultan, Mohit Iyyer, Wenlong Zhao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T01:28:28Z","title":"Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.08640","kind":"arxiv","version":4},"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:a04ab83c6a8cdc766c65236a8de12962ce6b35c1527d6f3c136ecc7d6559fb86","target":"record","created_at":"2026-07-05T08:51:44Z","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":"87c4f9fb8a8c7642ba284976864ac46148149c56c20df45d1df8dfa9b091fd87","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-15T01:28:28Z","title_canon_sha256":"30560fd66542df310d52a3725e30037eaff34ba4898de58c2c3a403f1194a64a"},"schema_version":"1.0","source":{"id":"2311.08640","kind":"arxiv","version":4}},"canonical_sha256":"12892c9c7f03906d9ed7a30f27a45a8fbe966a9249639edca5283669ed28c790","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12892c9c7f03906d9ed7a30f27a45a8fbe966a9249639edca5283669ed28c790","first_computed_at":"2026-07-05T08:51:44.710769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:44.710769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PL9B9xxMSeBihX+jugSlK7a8+YiZjRpfL/HZzz5P7ZOKa9EXZvLmoxnA4q91xnsLfKzaOBQTFvOImjefNEnoBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:44.711239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.08640","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a04ab83c6a8cdc766c65236a8de12962ce6b35c1527d6f3c136ecc7d6559fb86","sha256:a07f565314719967520d7b77a3da1ce31b279334f0d40e941b2c1bad46adb5b9"],"state_sha256":"94a4f35ae0519c6ef11b85c410c0a1f065e3566b6cc0235f631e8262101bf3e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Huaf4UMFQq0Zq3FEsWdl6LlkcXriSa82DXYGAlUJp6+6w/D/oOs24/VSXxgZGPaR6BfA+1fSSAi9ZJdRxYXJDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T00:11:20.870477Z","bundle_sha256":"18c886de5215ed789c04ee3322273e5ebd4774085fe8b49616e2863f56abbdbd"}}