{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FPPWUYI7KNNXYUH5VC2OPWESOG","short_pith_number":"pith:FPPWUYI7","schema_version":"1.0","canonical_sha256":"2bdf6a611f535b7c50fda8b4e7d892719593a4cfc0a8d30e3d331f5e58dad347","source":{"kind":"arxiv","id":"2508.09937","version":1},"attestation_state":"computed","paper":{"title":"A Comprehensive Evaluation framework of Alignment Techniques for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aminat Adebiyi, Heloisa Caroline de Souza Pereira Candello, Luan Soares de Souza, Marcelo Carpinette Grave, Maysa Malfiza Garcia de Macedo, Momin Abbas, Muneeza Azmat, Raya Horesh, Rebecka Nordenlow, Rogerio A de Paula, Tiago Machado, Yixin Chen","submitted_at":"2025-08-13T16:42:01Z","abstract_excerpt":"As Large Language Models (LLMs) become increasingly integrated into real-world applications, ensuring their outputs align with human values and safety standards has become critical. The field has developed diverse alignment approaches including traditional fine-tuning methods (RLHF, instruction tuning), post-hoc correction systems, and inference-time interventions, each with distinct advantages and limitations. However, the lack of unified evaluation frameworks makes it difficult to systematically compare these paradigms and guide deployment decisions. This paper introduces a multi-dimensional"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.09937","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-13T16:42:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"523ed50e1f1846dd139880adb9648226e4ade446f49dd3560ec27bdcdaad8b4d","abstract_canon_sha256":"59127177fd5b7eaaa8979cde165580555a442af1ae930d4406821f10dd8878f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:51.479811Z","signature_b64":"abjQ7TL5PPEjb/uCWM0VKjj3G+V/PoQq7X7Pl7peC6YwuVEWjlgu/EEi9Izgy10pQsVLNnH8a4prhZlMoFT9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bdf6a611f535b7c50fda8b4e7d892719593a4cfc0a8d30e3d331f5e58dad347","last_reissued_at":"2026-07-05T11:53:51.479390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:51.479390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comprehensive Evaluation framework of Alignment Techniques for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aminat Adebiyi, Heloisa Caroline de Souza Pereira Candello, Luan Soares de Souza, Marcelo Carpinette Grave, Maysa Malfiza Garcia de Macedo, Momin Abbas, Muneeza Azmat, Raya Horesh, Rebecka Nordenlow, Rogerio A de Paula, Tiago Machado, Yixin Chen","submitted_at":"2025-08-13T16:42:01Z","abstract_excerpt":"As Large Language Models (LLMs) become increasingly integrated into real-world applications, ensuring their outputs align with human values and safety standards has become critical. The field has developed diverse alignment approaches including traditional fine-tuning methods (RLHF, instruction tuning), post-hoc correction systems, and inference-time interventions, each with distinct advantages and limitations. However, the lack of unified evaluation frameworks makes it difficult to systematically compare these paradigms and guide deployment decisions. This paper introduces a multi-dimensional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09937","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/2508.09937/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.09937","created_at":"2026-07-05T11:53:51.479446+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09937v1","created_at":"2026-07-05T11:53:51.479446+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09937","created_at":"2026-07-05T11:53:51.479446+00:00"},{"alias_kind":"pith_short_12","alias_value":"FPPWUYI7KNNX","created_at":"2026-07-05T11:53:51.479446+00:00"},{"alias_kind":"pith_short_16","alias_value":"FPPWUYI7KNNXYUH5","created_at":"2026-07-05T11:53:51.479446+00:00"},{"alias_kind":"pith_short_8","alias_value":"FPPWUYI7","created_at":"2026-07-05T11:53:51.479446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG","json":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG.json","graph_json":"https://pith.science/api/pith-number/FPPWUYI7KNNXYUH5VC2OPWESOG/graph.json","events_json":"https://pith.science/api/pith-number/FPPWUYI7KNNXYUH5VC2OPWESOG/events.json","paper":"https://pith.science/paper/FPPWUYI7"},"agent_actions":{"view_html":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG","download_json":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG.json","view_paper":"https://pith.science/paper/FPPWUYI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09937&json=true","fetch_graph":"https://pith.science/api/pith-number/FPPWUYI7KNNXYUH5VC2OPWESOG/graph.json","fetch_events":"https://pith.science/api/pith-number/FPPWUYI7KNNXYUH5VC2OPWESOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG/action/storage_attestation","attest_author":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG/action/author_attestation","sign_citation":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG/action/citation_signature","submit_replication":"https://pith.science/pith/FPPWUYI7KNNXYUH5VC2OPWESOG/action/replication_record"}},"created_at":"2026-07-05T11:53:51.479446+00:00","updated_at":"2026-07-05T11:53:51.479446+00:00"}