{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MMGY7HECG3DGK6YOEK4KK4XKCI","short_pith_number":"pith:MMGY7HEC","canonical_record":{"source":{"id":"2406.07288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T14:16:14Z","cross_cats_sorted":[],"title_canon_sha256":"6d7cf29e6f1fb4f4b5c8e7d9cbfc6c60f5b80b4d68d8aaf4e4056dcd37a1363b","abstract_canon_sha256":"c7dfd12261cdb02aee525751faca7770858328a8db7ece478ed0fb96b5c0750f"},"schema_version":"1.0"},"canonical_sha256":"630d8f9c8236c6657b0e22b8a572ea1232db0f55a1f2a4abcb0a3f53a7c0b7c0","source":{"kind":"arxiv","id":"2406.07288","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07288","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07288v1","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07288","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_12","alias_value":"MMGY7HECG3DG","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_16","alias_value":"MMGY7HECG3DGK6YO","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_8","alias_value":"MMGY7HEC","created_at":"2026-07-05T08:30:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MMGY7HECG3DGK6YOEK4KK4XKCI","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T14:16:14Z","cross_cats_sorted":[],"title_canon_sha256":"6d7cf29e6f1fb4f4b5c8e7d9cbfc6c60f5b80b4d68d8aaf4e4056dcd37a1363b","abstract_canon_sha256":"c7dfd12261cdb02aee525751faca7770858328a8db7ece478ed0fb96b5c0750f"},"schema_version":"1.0"},"canonical_sha256":"630d8f9c8236c6657b0e22b8a572ea1232db0f55a1f2a4abcb0a3f53a7c0b7c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:21.164617Z","signature_b64":"KBI+59hPdaXWzBduvQnQuUWGM+lLRvNPuKIzPC1DFJff++mxXIE2uvYw8DQv1yE8ZwTImhWopF8OqUMXGVS5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"630d8f9c8236c6657b0e22b8a572ea1232db0f55a1f2a4abcb0a3f53a7c0b7c0","last_reissued_at":"2026-07-05T08:30:21.164143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:21.164143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07288","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":"2026-07-05T08:30:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CHn9rThnKaYhSe3TusIVKKkHJIkn9SNoLRvszKXXwfXSgilB2Q4cFW6A2GrKnMLgCwz2oKOyxDxCqx97tqIzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:45:08.990243Z"},"content_sha256":"3ea795645135c489c8d39857608e5f7606669939771b4437330715432c2f2511","schema_version":"1.0","event_id":"sha256:3ea795645135c489c8d39857608e5f7606669939771b4437330715432c2f2511"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MMGY7HECG3DGK6YOEK4KK4XKCI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela Occhipinti, Felice Dell'Orletta, Huiyuan Lai, Irene Mondella, Malvina Nissim, Marco Guerini, Michele Marchi","submitted_at":"2024-06-11T14:16:14Z","abstract_excerpt":"Automatic methods for generating and gathering linguistic data have proven effective for fine-tuning Language Models (LMs) in languages less resourced than English. Still, while there has been emphasis on data quantity, less attention has been given to its quality. In this work, we investigate the impact of human intervention on machine-generated data when fine-tuning dialogical models. In particular, we study (1) whether post-edited dialogues exhibit higher perceived quality compared to the originals that were automatically generated; (2) whether fine-tuning with post-edited dialogues results"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07288","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/2406.07288/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":"2026-07-05T08:30:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FYCpqXzef9XyDgYKQkcdWHReEQDZIJNJuOPIQ+TUGIpSkZJYB/OuuP/quufgO3CvSNlW5d2Bvvqmbt55TDYqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:45:08.990621Z"},"content_sha256":"10e5fb96d0a2305bc77b5b29dd2fa695f7e4d4e1faec432be57cf98a9bb668b2","schema_version":"1.0","event_id":"sha256:10e5fb96d0a2305bc77b5b29dd2fa695f7e4d4e1faec432be57cf98a9bb668b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMGY7HECG3DGK6YOEK4KK4XKCI/bundle.json","state_url":"https://pith.science/pith/MMGY7HECG3DGK6YOEK4KK4XKCI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMGY7HECG3DGK6YOEK4KK4XKCI/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":"2026-07-07T12:45:08Z","links":{"resolver":"https://pith.science/pith/MMGY7HECG3DGK6YOEK4KK4XKCI","bundle":"https://pith.science/pith/MMGY7HECG3DGK6YOEK4KK4XKCI/bundle.json","state":"https://pith.science/pith/MMGY7HECG3DGK6YOEK4KK4XKCI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMGY7HECG3DGK6YOEK4KK4XKCI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MMGY7HECG3DGK6YOEK4KK4XKCI","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":"c7dfd12261cdb02aee525751faca7770858328a8db7ece478ed0fb96b5c0750f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T14:16:14Z","title_canon_sha256":"6d7cf29e6f1fb4f4b5c8e7d9cbfc6c60f5b80b4d68d8aaf4e4056dcd37a1363b"},"schema_version":"1.0","source":{"id":"2406.07288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07288","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07288v1","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07288","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_12","alias_value":"MMGY7HECG3DG","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_16","alias_value":"MMGY7HECG3DGK6YO","created_at":"2026-07-05T08:30:21Z"},{"alias_kind":"pith_short_8","alias_value":"MMGY7HEC","created_at":"2026-07-05T08:30:21Z"}],"graph_snapshots":[{"event_id":"sha256:10e5fb96d0a2305bc77b5b29dd2fa695f7e4d4e1faec432be57cf98a9bb668b2","target":"graph","created_at":"2026-07-05T08:30:21Z","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/2406.07288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic methods for generating and gathering linguistic data have proven effective for fine-tuning Language Models (LMs) in languages less resourced than English. Still, while there has been emphasis on data quantity, less attention has been given to its quality. In this work, we investigate the impact of human intervention on machine-generated data when fine-tuning dialogical models. In particular, we study (1) whether post-edited dialogues exhibit higher perceived quality compared to the originals that were automatically generated; (2) whether fine-tuning with post-edited dialogues results","authors_text":"Daniela Occhipinti, Felice Dell'Orletta, Huiyuan Lai, Irene Mondella, Malvina Nissim, Marco Guerini, Michele Marchi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T14:16:14Z","title":"Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07288","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":"sha256:3ea795645135c489c8d39857608e5f7606669939771b4437330715432c2f2511","target":"record","created_at":"2026-07-05T08:30:21Z","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":"c7dfd12261cdb02aee525751faca7770858328a8db7ece478ed0fb96b5c0750f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-11T14:16:14Z","title_canon_sha256":"6d7cf29e6f1fb4f4b5c8e7d9cbfc6c60f5b80b4d68d8aaf4e4056dcd37a1363b"},"schema_version":"1.0","source":{"id":"2406.07288","kind":"arxiv","version":1}},"canonical_sha256":"630d8f9c8236c6657b0e22b8a572ea1232db0f55a1f2a4abcb0a3f53a7c0b7c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"630d8f9c8236c6657b0e22b8a572ea1232db0f55a1f2a4abcb0a3f53a7c0b7c0","first_computed_at":"2026-07-05T08:30:21.164143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:21.164143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KBI+59hPdaXWzBduvQnQuUWGM+lLRvNPuKIzPC1DFJff++mxXIE2uvYw8DQv1yE8ZwTImhWopF8OqUMXGVS5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:21.164617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ea795645135c489c8d39857608e5f7606669939771b4437330715432c2f2511","sha256:10e5fb96d0a2305bc77b5b29dd2fa695f7e4d4e1faec432be57cf98a9bb668b2"],"state_sha256":"5120451560e6c94b1855b9bc94fc369faea0f4641206890c1a364f7aa1b092e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UhvXT1YZkIZi6uYhanQ/DMyyCXJ5uzsh4/MDEBDat6v3Cctu1tURJryC04N0wBG4AYC/NJAg57ZzPtXZBw0DBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:45:08.992548Z","bundle_sha256":"048babfc7c93e742744ca4346495c75416b28a7e41101ede8f0e8d938ffd813c"}}