{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SHYHXLDUVG3TLR6H6V3FSU2C2A","short_pith_number":"pith:SHYHXLDU","canonical_record":{"source":{"id":"2505.01706","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-03T05:59:13Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a366a7e5c61f2e0bf5fe4b7bfc9efea4954cdd17f0f62a828a4879ae5f4c366f","abstract_canon_sha256":"5c6653dea2fa2dbeaf27567357e179df1dcf8693fcf6452a32ddaaf78a9785c0"},"schema_version":"1.0"},"canonical_sha256":"91f07bac74a9b735c7c7f576595342d0244e380b8cb31ebcf19070731272db7c","source":{"kind":"arxiv","id":"2505.01706","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01706","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01706v1","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01706","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"pith_short_12","alias_value":"SHYHXLDUVG3T","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"pith_short_16","alias_value":"SHYHXLDUVG3TLR6H","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"pith_short_8","alias_value":"SHYHXLDU","created_at":"2026-07-05T10:58:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SHYHXLDUVG3TLR6H6V3FSU2C2A","target":"record","payload":{"canonical_record":{"source":{"id":"2505.01706","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-03T05:59:13Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a366a7e5c61f2e0bf5fe4b7bfc9efea4954cdd17f0f62a828a4879ae5f4c366f","abstract_canon_sha256":"5c6653dea2fa2dbeaf27567357e179df1dcf8693fcf6452a32ddaaf78a9785c0"},"schema_version":"1.0"},"canonical_sha256":"91f07bac74a9b735c7c7f576595342d0244e380b8cb31ebcf19070731272db7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:02.511151Z","signature_b64":"wvx2MZMOwIEUcHagfQNNk8JRha5lYgzIqHmlq4R0yxX3JNDHlqKx2cMMc8builozqU1ZjgCN/n7tTP60oekhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91f07bac74a9b735c7c7f576595342d0244e380b8cb31ebcf19070731272db7c","last_reissued_at":"2026-07-05T10:58:02.510600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:02.510600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.01706","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":"2026-07-05T10:58:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C3IzBhNBvl7Urr5MzwV7T4/HV3Oxwba8bBHy1J137P/yeIMBxjZKk1LMhDwTjdWYWrQ8jMHBFUxgxipvZcmICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:03:01.512181Z"},"content_sha256":"da97f4b5daf6800e75156c29d0f3bf6295d1884285224daf739c543202f8b310","schema_version":"1.0","event_id":"sha256:da97f4b5daf6800e75156c29d0f3bf6295d1884285224daf739c543202f8b310"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SHYHXLDUVG3TLR6H6V3FSU2C2A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inducing Robustness in a 2 Dimensional Direct Preference Optimization Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ganesh Ramakrishnan, Nachiketa Patil, Ritik, Sarvesh Shashidhar, Suraj Racha","submitted_at":"2025-05-03T05:59:13Z","abstract_excerpt":"Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative to approaches that use Reinforcement learning via Human Feedback. In this work, we investigate the performance of DPO using open-source preference datasets. One of the major drawbacks of DPO is that it doesn't induce granular scoring and treats all the segments of the responses with equal propensity. However, this is not practically true for human preferences since even \"good\" responses have segments that may not be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01706","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/2505.01706/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":"2026-07-05T10:58:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jk6DIckVrHROZrGrXB3uIOrRNALpM7mvjjnCFjIne+wJSkFwZtZg0e6fqKvdwK8/KrNXxTZamsIrOZcrlFuxCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:03:01.512689Z"},"content_sha256":"82e6760489f8b2deebec76bfb7a6eb7573df4ba8ecec149aca21f48621d3a2c9","schema_version":"1.0","event_id":"sha256:82e6760489f8b2deebec76bfb7a6eb7573df4ba8ecec149aca21f48621d3a2c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHYHXLDUVG3TLR6H6V3FSU2C2A/bundle.json","state_url":"https://pith.science/pith/SHYHXLDUVG3TLR6H6V3FSU2C2A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHYHXLDUVG3TLR6H6V3FSU2C2A/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":"2026-08-16T22:03:01Z","links":{"resolver":"https://pith.science/pith/SHYHXLDUVG3TLR6H6V3FSU2C2A","bundle":"https://pith.science/pith/SHYHXLDUVG3TLR6H6V3FSU2C2A/bundle.json","state":"https://pith.science/pith/SHYHXLDUVG3TLR6H6V3FSU2C2A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHYHXLDUVG3TLR6H6V3FSU2C2A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SHYHXLDUVG3TLR6H6V3FSU2C2A","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":"5c6653dea2fa2dbeaf27567357e179df1dcf8693fcf6452a32ddaaf78a9785c0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-03T05:59:13Z","title_canon_sha256":"a366a7e5c61f2e0bf5fe4b7bfc9efea4954cdd17f0f62a828a4879ae5f4c366f"},"schema_version":"1.0","source":{"id":"2505.01706","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01706","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01706v1","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01706","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"pith_short_12","alias_value":"SHYHXLDUVG3T","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"pith_short_16","alias_value":"SHYHXLDUVG3TLR6H","created_at":"2026-07-05T10:58:02Z"},{"alias_kind":"pith_short_8","alias_value":"SHYHXLDU","created_at":"2026-07-05T10:58:02Z"}],"graph_snapshots":[{"event_id":"sha256:82e6760489f8b2deebec76bfb7a6eb7573df4ba8ecec149aca21f48621d3a2c9","target":"graph","created_at":"2026-07-05T10:58:02Z","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/2505.01706/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative to approaches that use Reinforcement learning via Human Feedback. In this work, we investigate the performance of DPO using open-source preference datasets. One of the major drawbacks of DPO is that it doesn't induce granular scoring and treats all the segments of the responses with equal propensity. However, this is not practically true for human preferences since even \"good\" responses have segments that may not be ","authors_text":"Ganesh Ramakrishnan, Nachiketa Patil, Ritik, Sarvesh Shashidhar, Suraj Racha","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-03T05:59:13Z","title":"Inducing Robustness in a 2 Dimensional Direct Preference Optimization Paradigm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01706","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:da97f4b5daf6800e75156c29d0f3bf6295d1884285224daf739c543202f8b310","target":"record","created_at":"2026-07-05T10:58:02Z","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":"5c6653dea2fa2dbeaf27567357e179df1dcf8693fcf6452a32ddaaf78a9785c0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-03T05:59:13Z","title_canon_sha256":"a366a7e5c61f2e0bf5fe4b7bfc9efea4954cdd17f0f62a828a4879ae5f4c366f"},"schema_version":"1.0","source":{"id":"2505.01706","kind":"arxiv","version":1}},"canonical_sha256":"91f07bac74a9b735c7c7f576595342d0244e380b8cb31ebcf19070731272db7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91f07bac74a9b735c7c7f576595342d0244e380b8cb31ebcf19070731272db7c","first_computed_at":"2026-07-05T10:58:02.510600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:02.510600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wvx2MZMOwIEUcHagfQNNk8JRha5lYgzIqHmlq4R0yxX3JNDHlqKx2cMMc8builozqU1ZjgCN/n7tTP60oekhCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:02.511151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01706","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da97f4b5daf6800e75156c29d0f3bf6295d1884285224daf739c543202f8b310","sha256:82e6760489f8b2deebec76bfb7a6eb7573df4ba8ecec149aca21f48621d3a2c9"],"state_sha256":"9217b9ddf1af0fcaa34c0624aedceac838458f1d0aa0b77cbb8626b7074448c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1RAjW5U+ovkkqHKdMACmM3anu5r1uISjk0tL8XiWtlNKNznrPF1dGM54LIGVkDFFJ8in6ZA2oK0gMgTLhrCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:03:01.516129Z","bundle_sha256":"24e9ddc072d7e4ab0c651ad683edf6320b6fe4d1996562a28a83af13ae2e5a8c"}}