{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ETQXKHTFE54BEP5PZRQPWBUYHF","short_pith_number":"pith:ETQXKHTF","schema_version":"1.0","canonical_sha256":"24e1751e652778123fafcc60fb0698396b022bc2cc8f708fb8f72601383cd92c","source":{"kind":"arxiv","id":"2501.03486","version":1},"attestation_state":"computed","paper":{"title":"Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amrit Singh Bedi, Avinash Reddy, George K. Atia, Prashant Trivedi, Souradip Chakraborty, Vaneet Aggarwal","submitted_at":"2025-01-07T03:14:39Z","abstract_excerpt":"The alignment of large language models (LLMs) with human values is critical as these models become increasingly integrated into various societal and decision-making processes. Traditional methods, such as reinforcement learning from human feedback (RLHF), achieve alignment by fine-tuning model parameters, but these approaches are often computationally expensive and impractical when models are frozen or inaccessible for parameter modification. In contrast, prompt optimization is a viable alternative to RLHF for LLM alignment. While the existing literature has shown empirical promise of prompt o"},"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":"2501.03486","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-07T03:14:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1657b8a85903e810d5e2739ebbd907877cae6bd098e7e4d13ac971f4b1ae580e","abstract_canon_sha256":"a01247b3a7fd9483936ac9386580d4ed51efd103b766feb220d51e666e47e716"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:55.526952Z","signature_b64":"mGVxQAiUWcAhilpkFQbk4VjZ7cclMmRm+BLgkAZoLbXdZP5P//Ia1CQV2zdwKubyvT1hnyI5b9nQbVGklfSvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24e1751e652778123fafcc60fb0698396b022bc2cc8f708fb8f72601383cd92c","last_reissued_at":"2026-07-05T09:57:55.526465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:55.526465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amrit Singh Bedi, Avinash Reddy, George K. Atia, Prashant Trivedi, Souradip Chakraborty, Vaneet Aggarwal","submitted_at":"2025-01-07T03:14:39Z","abstract_excerpt":"The alignment of large language models (LLMs) with human values is critical as these models become increasingly integrated into various societal and decision-making processes. Traditional methods, such as reinforcement learning from human feedback (RLHF), achieve alignment by fine-tuning model parameters, but these approaches are often computationally expensive and impractical when models are frozen or inaccessible for parameter modification. In contrast, prompt optimization is a viable alternative to RLHF for LLM alignment. While the existing literature has shown empirical promise of prompt o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03486","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/2501.03486/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":"2501.03486","created_at":"2026-07-05T09:57:55.526524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03486v1","created_at":"2026-07-05T09:57:55.526524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03486","created_at":"2026-07-05T09:57:55.526524+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETQXKHTFE54B","created_at":"2026-07-05T09:57:55.526524+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETQXKHTFE54BEP5P","created_at":"2026-07-05T09:57:55.526524+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETQXKHTF","created_at":"2026-07-05T09:57:55.526524+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17735","citing_title":"SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF","json":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF.json","graph_json":"https://pith.science/api/pith-number/ETQXKHTFE54BEP5PZRQPWBUYHF/graph.json","events_json":"https://pith.science/api/pith-number/ETQXKHTFE54BEP5PZRQPWBUYHF/events.json","paper":"https://pith.science/paper/ETQXKHTF"},"agent_actions":{"view_html":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF","download_json":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF.json","view_paper":"https://pith.science/paper/ETQXKHTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03486&json=true","fetch_graph":"https://pith.science/api/pith-number/ETQXKHTFE54BEP5PZRQPWBUYHF/graph.json","fetch_events":"https://pith.science/api/pith-number/ETQXKHTFE54BEP5PZRQPWBUYHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF/action/storage_attestation","attest_author":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF/action/author_attestation","sign_citation":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF/action/citation_signature","submit_replication":"https://pith.science/pith/ETQXKHTFE54BEP5PZRQPWBUYHF/action/replication_record"}},"created_at":"2026-07-05T09:57:55.526524+00:00","updated_at":"2026-07-05T09:57:55.526524+00:00"}