{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2CSB7O6IWES22YSJUWKXDCPNJB","short_pith_number":"pith:2CSB7O6I","canonical_record":{"source":{"id":"2507.05179","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T16:34:28Z","cross_cats_sorted":[],"title_canon_sha256":"e8e211bb97abb76101deceae85f109d6b2239878e707477a9b6a5d2fb3352731","abstract_canon_sha256":"59d034c78160c82208f495a329f2f4e154783f7dd697c756e283b817d6eabdf2"},"schema_version":"1.0"},"canonical_sha256":"d0a41fbbc8b125ad6249a5957189ed4860ee135f4fafd789158d3e51fa8e0cfa","source":{"kind":"arxiv","id":"2507.05179","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05179","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05179v6","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05179","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"2CSB7O6IWES2","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"2CSB7O6IWES22YSJ","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"2CSB7O6I","created_at":"2026-06-02T01:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2CSB7O6IWES22YSJUWKXDCPNJB","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05179","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T16:34:28Z","cross_cats_sorted":[],"title_canon_sha256":"e8e211bb97abb76101deceae85f109d6b2239878e707477a9b6a5d2fb3352731","abstract_canon_sha256":"59d034c78160c82208f495a329f2f4e154783f7dd697c756e283b817d6eabdf2"},"schema_version":"1.0"},"canonical_sha256":"d0a41fbbc8b125ad6249a5957189ed4860ee135f4fafd789158d3e51fa8e0cfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:14.826187Z","signature_b64":"TzXtAzPDKjJeLhm7kN40/fWw2FELuj676+8RjmpZjBcfUfSCD+YEiTbbPTf+uSq4Z76esl9zTJGr+G+77aUJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0a41fbbc8b125ad6249a5957189ed4860ee135f4fafd789158d3e51fa8e0cfa","last_reissued_at":"2026-06-02T01:04:14.825707Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:14.825707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05179","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2SCDgqnbcHcv4WfUEKsVE6TACKdXwQhYwwVjyQonlYKj09yWnbU1jMUhS2uC1GuXmJKQFm1wLIF3vlIvRdbMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:08:13.942075Z"},"content_sha256":"e28391e4fac4f5dbb4361b478da48c0d3e8122ebe1f71c3cb9e870440b9632c3","schema_version":"1.0","event_id":"sha256:e28391e4fac4f5dbb4361b478da48c0d3e8122ebe1f71c3cb9e870440b9632c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2CSB7O6IWES22YSJUWKXDCPNJB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A curriculum-driven DPO framework generates reliable Hindi news veracity explanations by preferring fact-checked sources.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Jatowt, Pulkit Bansal, Raghvendra Kumar, Shakti Singh, Sriparna Saha","submitted_at":"2025-07-07T16:34:28Z","abstract_excerpt":"In an era of rampant misinformation, generating reliable news explanations is vital, especially for under-represented languages like Hindi. Lacking robust automated tools, Hindi faces challenges in scaling misinformation detection. To bridge this gap, we propose a novel framework integrating Direct Preference Optimization (DPO) with curriculum learning to align machine-generated explanations with human reasoning. Fact-checked explanations from credible sources serve as preferred responses, while LLM outputs highlight system limitations and serve as non-preferred responses. To refine task-speci"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments with LLMs (Mistral, Llama, Gemma) and PLMs (mBART, mT5) confirm the framework's effectiveness in generating coherent, contextually relevant explanations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That fact-checked explanations from credible sources can reliably serve as preferred responses while LLM outputs serve as non-preferred responses, and that adding the Actuality and Finesse parameters to the DPO loss will produce measurable improvements in explanation quality without introducing new biases or inconsistencies.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A DPO framework augmented with curriculum learning and two new loss parameters generates veracity explanations for Hindi news using LLMs and PLMs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A curriculum-driven DPO framework generates reliable Hindi news veracity explanations by preferring fact-checked sources.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9223b97f260b554eca0cbb36ee18200db00605ddb6e852a8b26544a2b50d6c62"},"source":{"id":"2507.05179","kind":"arxiv","version":6},"verdict":{"id":"2ce27f78-c6e8-44ec-8fc4-003038fbf60c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T06:04:03.724054Z","strongest_claim":"Experiments with LLMs (Mistral, Llama, Gemma) and PLMs (mBART, mT5) confirm the framework's effectiveness in generating coherent, contextually relevant explanations.","one_line_summary":"A DPO framework augmented with curriculum learning and two new loss parameters generates veracity explanations for Hindi news using LLMs and PLMs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That fact-checked explanations from credible sources can reliably serve as preferred responses while LLM outputs serve as non-preferred responses, and that adding the Actuality and Finesse parameters to the DPO loss will produce measurable improvements in explanation quality without introducing new biases or inconsistencies.","pith_extraction_headline":"A curriculum-driven DPO framework generates reliable Hindi news veracity explanations by preferring fact-checked sources."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.05179/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":1,"snapshot_sha256":"48a212deabcf3159a1b8e2f3a7419ec5b21e20f66ccd7d1731cbee01a61a6932"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2ce27f78-c6e8-44ec-8fc4-003038fbf60c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dgRH3lENi/gGTc2pV+V4BCclxdurXvRR6lvD3Ud7ubJt8SkYTeaE+APo26zcUTQ/kK3Rp6LqM5ewyzcHYgDRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:08:13.943138Z"},"content_sha256":"55ff934d1e1baefc0140b4e6816c37b2166316070258492b5e4f6cff9ba3bbdb","schema_version":"1.0","event_id":"sha256:55ff934d1e1baefc0140b4e6816c37b2166316070258492b5e4f6cff9ba3bbdb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CSB7O6IWES22YSJUWKXDCPNJB/bundle.json","state_url":"https://pith.science/pith/2CSB7O6IWES22YSJUWKXDCPNJB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CSB7O6IWES22YSJUWKXDCPNJB/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":"2026-06-05T20:08:13Z","links":{"resolver":"https://pith.science/pith/2CSB7O6IWES22YSJUWKXDCPNJB","bundle":"https://pith.science/pith/2CSB7O6IWES22YSJUWKXDCPNJB/bundle.json","state":"https://pith.science/pith/2CSB7O6IWES22YSJUWKXDCPNJB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CSB7O6IWES22YSJUWKXDCPNJB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2CSB7O6IWES22YSJUWKXDCPNJB","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":"59d034c78160c82208f495a329f2f4e154783f7dd697c756e283b817d6eabdf2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T16:34:28Z","title_canon_sha256":"e8e211bb97abb76101deceae85f109d6b2239878e707477a9b6a5d2fb3352731"},"schema_version":"1.0","source":{"id":"2507.05179","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05179","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05179v6","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05179","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"2CSB7O6IWES2","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"2CSB7O6IWES22YSJ","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"2CSB7O6I","created_at":"2026-06-02T01:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:55ff934d1e1baefc0140b4e6816c37b2166316070258492b5e4f6cff9ba3bbdb","target":"graph","created_at":"2026-06-02T01:04:14Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments with LLMs (Mistral, Llama, Gemma) and PLMs (mBART, mT5) confirm the framework's effectiveness in generating coherent, contextually relevant explanations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That fact-checked explanations from credible sources can reliably serve as preferred responses while LLM outputs serve as non-preferred responses, and that adding the Actuality and Finesse parameters to the DPO loss will produce measurable improvements in explanation quality without introducing new biases or inconsistencies."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A DPO framework augmented with curriculum learning and two new loss parameters generates veracity explanations for Hindi news using LLMs and PLMs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A curriculum-driven DPO framework generates reliable Hindi news veracity explanations by preferring fact-checked sources."}],"snapshot_sha256":"9223b97f260b554eca0cbb36ee18200db00605ddb6e852a8b26544a2b50d6c62"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"48a212deabcf3159a1b8e2f3a7419ec5b21e20f66ccd7d1731cbee01a61a6932"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.05179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In an era of rampant misinformation, generating reliable news explanations is vital, especially for under-represented languages like Hindi. Lacking robust automated tools, Hindi faces challenges in scaling misinformation detection. To bridge this gap, we propose a novel framework integrating Direct Preference Optimization (DPO) with curriculum learning to align machine-generated explanations with human reasoning. Fact-checked explanations from credible sources serve as preferred responses, while LLM outputs highlight system limitations and serve as non-preferred responses. To refine task-speci","authors_text":"Adam Jatowt, Pulkit Bansal, Raghvendra Kumar, Shakti Singh, Sriparna Saha","cross_cats":[],"headline":"A curriculum-driven DPO framework generates reliable Hindi news veracity explanations by preferring fact-checked sources.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T16:34:28Z","title":"From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05179","kind":"arxiv","version":6},"verdict":{"created_at":"2026-05-19T06:04:03.724054Z","id":"2ce27f78-c6e8-44ec-8fc4-003038fbf60c","model_set":{"reader":"grok-4.3"},"one_line_summary":"A DPO framework augmented with curriculum learning and two new loss parameters generates veracity explanations for Hindi news using LLMs and PLMs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A curriculum-driven DPO framework generates reliable Hindi news veracity explanations by preferring fact-checked sources.","strongest_claim":"Experiments with LLMs (Mistral, Llama, Gemma) and PLMs (mBART, mT5) confirm the framework's effectiveness in generating coherent, contextually relevant explanations.","weakest_assumption":"That fact-checked explanations from credible sources can reliably serve as preferred responses while LLM outputs serve as non-preferred responses, and that adding the Actuality and Finesse parameters to the DPO loss will produce measurable improvements in explanation quality without introducing new biases or inconsistencies."}},"verdict_id":"2ce27f78-c6e8-44ec-8fc4-003038fbf60c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e28391e4fac4f5dbb4361b478da48c0d3e8122ebe1f71c3cb9e870440b9632c3","target":"record","created_at":"2026-06-02T01:04:14Z","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":"59d034c78160c82208f495a329f2f4e154783f7dd697c756e283b817d6eabdf2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T16:34:28Z","title_canon_sha256":"e8e211bb97abb76101deceae85f109d6b2239878e707477a9b6a5d2fb3352731"},"schema_version":"1.0","source":{"id":"2507.05179","kind":"arxiv","version":6}},"canonical_sha256":"d0a41fbbc8b125ad6249a5957189ed4860ee135f4fafd789158d3e51fa8e0cfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0a41fbbc8b125ad6249a5957189ed4860ee135f4fafd789158d3e51fa8e0cfa","first_computed_at":"2026-06-02T01:04:14.825707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:14.825707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TzXtAzPDKjJeLhm7kN40/fWw2FELuj676+8RjmpZjBcfUfSCD+YEiTbbPTf+uSq4Z76esl9zTJGr+G+77aUJAg==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:14.826187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05179","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e28391e4fac4f5dbb4361b478da48c0d3e8122ebe1f71c3cb9e870440b9632c3","sha256:55ff934d1e1baefc0140b4e6816c37b2166316070258492b5e4f6cff9ba3bbdb"],"state_sha256":"05714554d2133afbabd86fb9cdcf1a0c125a38daa78fcbae765dc4929954b459"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMzPzYLvuCxLdZIaJm9OBKxSDZF9iVDk+UTsNeZP2OIHajhYTxcoP7aJjBJQ01Jvfq+EFp+gtp3jxifmVafMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T20:08:13.948642Z","bundle_sha256":"56cbf7944b2a9287b4d6ffa392e6608a77ea1e6e79bbf6d3fb9594d7d8f17274"}}