{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BL232D7UC4QNZVHH4SGSBLFY2B","short_pith_number":"pith:BL232D7U","canonical_record":{"source":{"id":"2512.15765","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-12T10:13:54Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"e1636424fe004fdb8305b81909f27ed522b635d1262fa69d0009b50bcb5afe90","abstract_canon_sha256":"65c54d1d9780e3cfeb00fff415bef803b8975d401a8494779031dcfe56197205"},"schema_version":"1.0"},"canonical_sha256":"0af5bd0ff41720dcd4e7e48d20acb8d0678d2b759161f806bc18f90355b39b6d","source":{"kind":"arxiv","id":"2512.15765","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.15765","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"2512.15765v3","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.15765","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"BL232D7UC4QN","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"pith_short_16","alias_value":"BL232D7UC4QNZVHH","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"pith_short_8","alias_value":"BL232D7U","created_at":"2026-07-07T02:17:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BL232D7UC4QNZVHH4SGSBLFY2B","target":"record","payload":{"canonical_record":{"source":{"id":"2512.15765","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-12T10:13:54Z","cross_cats_sorted":["cs.GT","stat.ML"],"title_canon_sha256":"e1636424fe004fdb8305b81909f27ed522b635d1262fa69d0009b50bcb5afe90","abstract_canon_sha256":"65c54d1d9780e3cfeb00fff415bef803b8975d401a8494779031dcfe56197205"},"schema_version":"1.0"},"canonical_sha256":"0af5bd0ff41720dcd4e7e48d20acb8d0678d2b759161f806bc18f90355b39b6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:15.435759Z","signature_b64":"WnIf8aC2MJ8bHxqUTbim3iLt9ysVhvtU++WqiY9alO2iICMtFABP6YCPHhoSZ3O8StIYT3Qcp9BpLeu6NRRTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0af5bd0ff41720dcd4e7e48d20acb8d0678d2b759161f806bc18f90355b39b6d","last_reissued_at":"2026-07-07T02:17:15.434839Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:15.434839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.15765","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2octl1JClFo9AQfMHjoCCTruts86sHirtdWBE3d3YUiccsrQVhT7Wg3Ne4bmFnxhjbdVT37Hbl1iBWlHBVEYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:14:03.495084Z"},"content_sha256":"4180c4737a2e1928d298a8b3078583073fd11983f9aa6cb3b5f16f2d999f6a90","schema_version":"1.0","event_id":"sha256:4180c4737a2e1928d298a8b3078583073fd11983f9aa6cb3b5f16f2d999f6a90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BL232D7UC4QNZVHH4SGSBLFY2B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Heymann, Maxime Vono, M\\'elissa Tamine, Otmane Sakhi, Patrick Loiseau","submitted_at":"2025-12-12T10:13:54Z","abstract_excerpt":"Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources. The standard game-theoretic approach assigns each dataset a contribution score via the Shapley value. In practice, however, Shapley-based valuation is computationally prohibitive because it requires fine-tuning a separate model for every possible coalition of preference datasets, i.e., an exponential number of alignments. We address this challenge for a broad family of preference-optimization objectives, including DPO and IPO, that lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.15765","kind":"arxiv","version":3},"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/2512.15765/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":"2026-07-07T02:17:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4aLYqDkicizLdBY5SN1RBKzybi71sXz3BWu+mWe98P0Q8usXCr8gDRW3BLaTAbeezu1KsdWvp+lxx9DJPh/iDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:14:03.495588Z"},"content_sha256":"5867ffcff319d9b96dbfa7ec3a2fcce39f61ec74802d06507264d609244f78f7","schema_version":"1.0","event_id":"sha256:5867ffcff319d9b96dbfa7ec3a2fcce39f61ec74802d06507264d609244f78f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BL232D7UC4QNZVHH4SGSBLFY2B/bundle.json","state_url":"https://pith.science/pith/BL232D7UC4QNZVHH4SGSBLFY2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BL232D7UC4QNZVHH4SGSBLFY2B/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":"2026-08-04T16:14:03Z","links":{"resolver":"https://pith.science/pith/BL232D7UC4QNZVHH4SGSBLFY2B","bundle":"https://pith.science/pith/BL232D7UC4QNZVHH4SGSBLFY2B/bundle.json","state":"https://pith.science/pith/BL232D7UC4QNZVHH4SGSBLFY2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BL232D7UC4QNZVHH4SGSBLFY2B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BL232D7UC4QNZVHH4SGSBLFY2B","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":"65c54d1d9780e3cfeb00fff415bef803b8975d401a8494779031dcfe56197205","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-12T10:13:54Z","title_canon_sha256":"e1636424fe004fdb8305b81909f27ed522b635d1262fa69d0009b50bcb5afe90"},"schema_version":"1.0","source":{"id":"2512.15765","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.15765","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"2512.15765v3","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.15765","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"BL232D7UC4QN","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"pith_short_16","alias_value":"BL232D7UC4QNZVHH","created_at":"2026-07-07T02:17:15Z"},{"alias_kind":"pith_short_8","alias_value":"BL232D7U","created_at":"2026-07-07T02:17:15Z"}],"graph_snapshots":[{"event_id":"sha256:5867ffcff319d9b96dbfa7ec3a2fcce39f61ec74802d06507264d609244f78f7","target":"graph","created_at":"2026-07-07T02:17:15Z","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/2512.15765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data valuation is a natural framework for understanding which preference datasets matter most when aligning a Large Language Model (LLM) using multiple sources. The standard game-theoretic approach assigns each dataset a contribution score via the Shapley value. In practice, however, Shapley-based valuation is computationally prohibitive because it requires fine-tuning a separate model for every possible coalition of preference datasets, i.e., an exponential number of alignments. We address this challenge for a broad family of preference-optimization objectives, including DPO and IPO, that lea","authors_text":"Benjamin Heymann, Maxime Vono, M\\'elissa Tamine, Otmane Sakhi, Patrick Loiseau","cross_cats":["cs.GT","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-12T10:13:54Z","title":"Shapley-based Data Valuation for LLM Alignment via Sequential Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.15765","kind":"arxiv","version":3},"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":"sha256:4180c4737a2e1928d298a8b3078583073fd11983f9aa6cb3b5f16f2d999f6a90","target":"record","created_at":"2026-07-07T02:17:15Z","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":"65c54d1d9780e3cfeb00fff415bef803b8975d401a8494779031dcfe56197205","cross_cats_sorted":["cs.GT","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-12T10:13:54Z","title_canon_sha256":"e1636424fe004fdb8305b81909f27ed522b635d1262fa69d0009b50bcb5afe90"},"schema_version":"1.0","source":{"id":"2512.15765","kind":"arxiv","version":3}},"canonical_sha256":"0af5bd0ff41720dcd4e7e48d20acb8d0678d2b759161f806bc18f90355b39b6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0af5bd0ff41720dcd4e7e48d20acb8d0678d2b759161f806bc18f90355b39b6d","first_computed_at":"2026-07-07T02:17:15.434839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:17:15.434839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WnIf8aC2MJ8bHxqUTbim3iLt9ysVhvtU++WqiY9alO2iICMtFABP6YCPHhoSZ3O8StIYT3Qcp9BpLeu6NRRTDQ==","signature_status":"signed_v1","signed_at":"2026-07-07T02:17:15.435759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.15765","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4180c4737a2e1928d298a8b3078583073fd11983f9aa6cb3b5f16f2d999f6a90","sha256:5867ffcff319d9b96dbfa7ec3a2fcce39f61ec74802d06507264d609244f78f7"],"state_sha256":"4571ca88832995f8f255f9e859f293d9ae177665db97b562f586f05ce4918de6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKkLdfUiaUh9jkw2D7D53DboGuJJ2He99VlUq+m3q1ZMTwOIXBMmmSsgu2XRkLYczmjDbpECQYf92QDk1q9kAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:14:03.499380Z","bundle_sha256":"b39df792d45239848417342407282e82201ae5d08126280901b03263feee4b27"}}