{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H364XADWCAYDBLXCCD3HQH6KBK","short_pith_number":"pith:H364XADW","canonical_record":{"source":{"id":"2302.14233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T01:32:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"496620dcfd66a9f37077b4dc5008bab24740653b5f11b6808a316a1fedc59841","abstract_canon_sha256":"4903193eb5e0cf80911b17167d8c82df866a63c1d9cd36e612c9af0df212987f"},"schema_version":"1.0"},"canonical_sha256":"3efdcb8076103030aee210f6781fca0a811a98eddd08dbb68e83954cc25011f7","source":{"kind":"arxiv","id":"2302.14233","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14233","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14233v2","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14233","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"H364XADWCAYD","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"H364XADWCAYDBLXC","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"H364XADW","created_at":"2026-07-05T07:04:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H364XADWCAYDBLXCCD3HQH6KBK","target":"record","payload":{"canonical_record":{"source":{"id":"2302.14233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T01:32:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"496620dcfd66a9f37077b4dc5008bab24740653b5f11b6808a316a1fedc59841","abstract_canon_sha256":"4903193eb5e0cf80911b17167d8c82df866a63c1d9cd36e612c9af0df212987f"},"schema_version":"1.0"},"canonical_sha256":"3efdcb8076103030aee210f6781fca0a811a98eddd08dbb68e83954cc25011f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:45.432707Z","signature_b64":"eARpTPU9Cz5RX1CnhtnLrRgl2EIeUX6mG/kzL9VWZgDLGd+oxhw3XIe31T0v/d4gYaeZFx2HHqrsj5uNv8qkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3efdcb8076103030aee210f6781fca0a811a98eddd08dbb68e83954cc25011f7","last_reissued_at":"2026-07-05T07:04:45.432238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:45.432238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.14233","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kF4uypN7lzvPdomwUvEPl9FqsJj8cP3Ia+kBj574f2fV7Get2sMq4IYsMWKTWi07GLmCg/k0hk5MQY2gMvEkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:25:01.893099Z"},"content_sha256":"5735ac700a48a88f12bb9867e3af5d0b85b9f51a989ebf5b3d1c486fb21834f3","schema_version":"1.0","event_id":"sha256:5735ac700a48a88f12bb9867e3af5d0b85b9f51a989ebf5b3d1c486fb21834f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H364XADWCAYDBLXCCD3HQH6KBK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Goal Driven Discovery of Distributional Differences via Language Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Klein, Jacob Steinhardt, Jinwoo Ahn, Peter Zhang, Ruiqi Zhong, Steve Li","submitted_at":"2023-02-28T01:32:32Z","abstract_excerpt":"Mining large corpora can generate useful discoveries but is time-consuming for humans. We formulate a new task, D5, that automatically discovers differences between two large corpora in a goal-driven way. The task input is a problem comprising a research goal \"$\\textit{comparing the side effects of drug A and drug B}$\" and a corpus pair (two large collections of patients' self-reported reactions after taking each drug). The output is a language description (discovery) of how these corpora differ (patients taking drug A \"$\\textit{mention feelings of paranoia}$\" more often). We build a D5 system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14233","kind":"arxiv","version":2},"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/2302.14233/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":"2026-07-05T07:04:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rc2EnzNXaAgXFx3SlcpgERbf1mhe9fF5f8WZMfhwwEE/qUJ3rnhJsnCuJvli080PyI3S/+czbtjGgBmcOtjUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:25:01.893622Z"},"content_sha256":"95ed861ed8a7124536762b26dfd20737af2fb40c8a1fcc90f1136113076962b0","schema_version":"1.0","event_id":"sha256:95ed861ed8a7124536762b26dfd20737af2fb40c8a1fcc90f1136113076962b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/bundle.json","state_url":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H364XADWCAYDBLXCCD3HQH6KBK/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":"2026-08-06T13:25:01Z","links":{"resolver":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK","bundle":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/bundle.json","state":"https://pith.science/pith/H364XADWCAYDBLXCCD3HQH6KBK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H364XADWCAYDBLXCCD3HQH6KBK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H364XADWCAYDBLXCCD3HQH6KBK","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":"4903193eb5e0cf80911b17167d8c82df866a63c1d9cd36e612c9af0df212987f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T01:32:32Z","title_canon_sha256":"496620dcfd66a9f37077b4dc5008bab24740653b5f11b6808a316a1fedc59841"},"schema_version":"1.0","source":{"id":"2302.14233","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14233","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14233v2","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14233","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"H364XADWCAYD","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"H364XADWCAYDBLXC","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"H364XADW","created_at":"2026-07-05T07:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:95ed861ed8a7124536762b26dfd20737af2fb40c8a1fcc90f1136113076962b0","target":"graph","created_at":"2026-07-05T07:04:45Z","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/2302.14233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mining large corpora can generate useful discoveries but is time-consuming for humans. We formulate a new task, D5, that automatically discovers differences between two large corpora in a goal-driven way. The task input is a problem comprising a research goal \"$\\textit{comparing the side effects of drug A and drug B}$\" and a corpus pair (two large collections of patients' self-reported reactions after taking each drug). The output is a language description (discovery) of how these corpora differ (patients taking drug A \"$\\textit{mention feelings of paranoia}$\" more often). We build a D5 system","authors_text":"Dan Klein, Jacob Steinhardt, Jinwoo Ahn, Peter Zhang, Ruiqi Zhong, Steve Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T01:32:32Z","title":"Goal Driven Discovery of Distributional Differences via Language Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14233","kind":"arxiv","version":2},"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":"sha256:5735ac700a48a88f12bb9867e3af5d0b85b9f51a989ebf5b3d1c486fb21834f3","target":"record","created_at":"2026-07-05T07:04:45Z","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":"4903193eb5e0cf80911b17167d8c82df866a63c1d9cd36e612c9af0df212987f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-28T01:32:32Z","title_canon_sha256":"496620dcfd66a9f37077b4dc5008bab24740653b5f11b6808a316a1fedc59841"},"schema_version":"1.0","source":{"id":"2302.14233","kind":"arxiv","version":2}},"canonical_sha256":"3efdcb8076103030aee210f6781fca0a811a98eddd08dbb68e83954cc25011f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3efdcb8076103030aee210f6781fca0a811a98eddd08dbb68e83954cc25011f7","first_computed_at":"2026-07-05T07:04:45.432238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:45.432238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eARpTPU9Cz5RX1CnhtnLrRgl2EIeUX6mG/kzL9VWZgDLGd+oxhw3XIe31T0v/d4gYaeZFx2HHqrsj5uNv8qkCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:45.432707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.14233","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5735ac700a48a88f12bb9867e3af5d0b85b9f51a989ebf5b3d1c486fb21834f3","sha256:95ed861ed8a7124536762b26dfd20737af2fb40c8a1fcc90f1136113076962b0"],"state_sha256":"7dfcc345275e195c86fc18e0847ceb4ac89b23ab15f2c9f91f7b412394801257"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"669c7Mu1e8eN8QgDdVvGA+e2ogYS647A/YLxgZ69NFBWDAaCW2kl1/nzmR4d/CLi8tWlnA9KGEuhHR8R82EvDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:25:01.898001Z","bundle_sha256":"44d20deeecc6aeb558178f4029c1fd09f9995ad8e0123073079075edce2304a9"}}