{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:W232XZTJTPCE4ALB2ED335PD76","short_pith_number":"pith:W232XZTJ","canonical_record":{"source":{"id":"2506.00152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T18:44:09Z","cross_cats_sorted":["econ.EM","stat.ML"],"title_canon_sha256":"dfe73ba24731b24500dda21a82e05dc36cd7d70c050f6fb9575a65c432015049","abstract_canon_sha256":"2b21e45d7733083035f140ddedc0f48f0de3cea46db60f376fd7dcc22a425d15"},"schema_version":"1.0"},"canonical_sha256":"b6b7abe6699bc44e0161d107bdf5e3ffae9e431d7792fa21d5f06e45701b533c","source":{"kind":"arxiv","id":"2506.00152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00152","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00152v1","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00152","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"W232XZTJTPCE","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"W232XZTJTPCE4ALB","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"W232XZTJ","created_at":"2026-07-05T11:13:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:W232XZTJTPCE4ALB2ED335PD76","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T18:44:09Z","cross_cats_sorted":["econ.EM","stat.ML"],"title_canon_sha256":"dfe73ba24731b24500dda21a82e05dc36cd7d70c050f6fb9575a65c432015049","abstract_canon_sha256":"2b21e45d7733083035f140ddedc0f48f0de3cea46db60f376fd7dcc22a425d15"},"schema_version":"1.0"},"canonical_sha256":"b6b7abe6699bc44e0161d107bdf5e3ffae9e431d7792fa21d5f06e45701b533c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:29.859778Z","signature_b64":"SQFSovFBjR+SNNsF4GxUTzkP8mGVq8HPBRAlpIweQPqwWD5fsTOLV2RA8J27o0ZyesZ/m362SlRZyggh85NzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6b7abe6699bc44e0161d107bdf5e3ffae9e431d7792fa21d5f06e45701b533c","last_reissued_at":"2026-07-05T11:13:29.859347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:29.859347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00152","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":"2026-07-05T11:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VrkPFn46kVyfWLoaJQpRmQbv6YYrDE7TMYvDCnNODuvYMvoAAcxSiIU4BLntOY+/fqSEwtCPZIAZMy7mpXedAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:36:43.824833Z"},"content_sha256":"0cbb5f30ddd3c526927369f1b507a427efc0c4f71583e18e4db3e58090fa839a","schema_version":"1.0","event_id":"sha256:0cbb5f30ddd3c526927369f1b507a427efc0c4f71583e18e4db3e58090fa839a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:W232XZTJTPCE4ALB2ED335PD76","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["econ.EM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Erfan Loghmani","submitted_at":"2025-05-30T18:44:09Z","abstract_excerpt":"Large language models are being widely used across industries to generate content that contributes directly to key performance metrics, such as conversion rates. Pretrained models, however, often fall short when it comes to aligning with human preferences or optimizing for business objectives. As a result, fine-tuning with good-quality labeled data is essential to guide models to generate content that achieves better results. Controlled experiments, like A/B tests, can provide such data, but they are often expensive and come with significant engineering and logistical challenges. Meanwhile, co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00152","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/2506.00152/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":"2026-07-05T11:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZqZGC9+nMT2dq5+djF+47LrsWo7vcjOO5/q0Ajz/NJIEwZxyuweTLQUGKXingI0AeQjBwIx+mjjNpYp5Uxx4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:36:43.825387Z"},"content_sha256":"a54ec20061d77389a7f2a315f8769d0f1f695858d94f935f82234832f963a5d2","schema_version":"1.0","event_id":"sha256:a54ec20061d77389a7f2a315f8769d0f1f695858d94f935f82234832f963a5d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W232XZTJTPCE4ALB2ED335PD76/bundle.json","state_url":"https://pith.science/pith/W232XZTJTPCE4ALB2ED335PD76/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W232XZTJTPCE4ALB2ED335PD76/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":"2026-08-08T00:36:43Z","links":{"resolver":"https://pith.science/pith/W232XZTJTPCE4ALB2ED335PD76","bundle":"https://pith.science/pith/W232XZTJTPCE4ALB2ED335PD76/bundle.json","state":"https://pith.science/pith/W232XZTJTPCE4ALB2ED335PD76/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W232XZTJTPCE4ALB2ED335PD76/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W232XZTJTPCE4ALB2ED335PD76","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":"2b21e45d7733083035f140ddedc0f48f0de3cea46db60f376fd7dcc22a425d15","cross_cats_sorted":["econ.EM","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T18:44:09Z","title_canon_sha256":"dfe73ba24731b24500dda21a82e05dc36cd7d70c050f6fb9575a65c432015049"},"schema_version":"1.0","source":{"id":"2506.00152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00152","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00152v1","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00152","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"W232XZTJTPCE","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"W232XZTJTPCE4ALB","created_at":"2026-07-05T11:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"W232XZTJ","created_at":"2026-07-05T11:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:a54ec20061d77389a7f2a315f8769d0f1f695858d94f935f82234832f963a5d2","target":"graph","created_at":"2026-07-05T11:13:29Z","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/2506.00152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models are being widely used across industries to generate content that contributes directly to key performance metrics, such as conversion rates. Pretrained models, however, often fall short when it comes to aligning with human preferences or optimizing for business objectives. As a result, fine-tuning with good-quality labeled data is essential to guide models to generate content that achieves better results. Controlled experiments, like A/B tests, can provide such data, but they are often expensive and come with significant engineering and logistical challenges. Meanwhile, co","authors_text":"Erfan Loghmani","cross_cats":["econ.EM","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T18:44:09Z","title":"Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00152","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":"sha256:0cbb5f30ddd3c526927369f1b507a427efc0c4f71583e18e4db3e58090fa839a","target":"record","created_at":"2026-07-05T11:13:29Z","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":"2b21e45d7733083035f140ddedc0f48f0de3cea46db60f376fd7dcc22a425d15","cross_cats_sorted":["econ.EM","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T18:44:09Z","title_canon_sha256":"dfe73ba24731b24500dda21a82e05dc36cd7d70c050f6fb9575a65c432015049"},"schema_version":"1.0","source":{"id":"2506.00152","kind":"arxiv","version":1}},"canonical_sha256":"b6b7abe6699bc44e0161d107bdf5e3ffae9e431d7792fa21d5f06e45701b533c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6b7abe6699bc44e0161d107bdf5e3ffae9e431d7792fa21d5f06e45701b533c","first_computed_at":"2026-07-05T11:13:29.859347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:29.859347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SQFSovFBjR+SNNsF4GxUTzkP8mGVq8HPBRAlpIweQPqwWD5fsTOLV2RA8J27o0ZyesZ/m362SlRZyggh85NzCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:29.859778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cbb5f30ddd3c526927369f1b507a427efc0c4f71583e18e4db3e58090fa839a","sha256:a54ec20061d77389a7f2a315f8769d0f1f695858d94f935f82234832f963a5d2"],"state_sha256":"eeea9d622f56beed7dd034303dc7dc5bd46845270166994bdb3e5dc1fd1c1d8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOcJ2YMG9Qk94nJ3auDARBzWeVMJBRzMMDTrvwAAYKIuHJtPTJ3mYYRSUBSldwplMHSsHD0msNg5anQDaVzCDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:36:43.828292Z","bundle_sha256":"7760f2dd5a415717ff9235bbb1d86ab674c4cf69c3114a44832a2f2df290976c"}}