{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KJITCPSE6JZMK5D2BQ4LZOZ7U5","short_pith_number":"pith:KJITCPSE","canonical_record":{"source":{"id":"2606.09856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T15:40:02Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"d3611994170bfd7b823dbc31cb0f82b661a555608d8d550e12603543ec87a326","abstract_canon_sha256":"de113c10888572af9dcb2f6f5ae415c86f9cebe33fce92034a1b24b25a4e1d65"},"schema_version":"1.0"},"canonical_sha256":"5251313e44f272c5747a0c38bcbb3fa774337b9bbfaae902896ba7938b58dfa5","source":{"kind":"arxiv","id":"2606.09856","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09856","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09856v1","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09856","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"KJITCPSE6JZM","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"KJITCPSE6JZMK5D2","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"KJITCPSE","created_at":"2026-06-10T00:08:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KJITCPSE6JZMK5D2BQ4LZOZ7U5","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09856","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T15:40:02Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"d3611994170bfd7b823dbc31cb0f82b661a555608d8d550e12603543ec87a326","abstract_canon_sha256":"de113c10888572af9dcb2f6f5ae415c86f9cebe33fce92034a1b24b25a4e1d65"},"schema_version":"1.0"},"canonical_sha256":"5251313e44f272c5747a0c38bcbb3fa774337b9bbfaae902896ba7938b58dfa5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T00:08:28.802716Z","signature_b64":"rtsqJ4ZO9ddw9jUBKbzN6ZnaYgTtLJ62MmfgbjPAN5q2ECB3MbhsZGCMaIyEC2TnWQHX3nmPpb0VJTlqWkyVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5251313e44f272c5747a0c38bcbb3fa774337b9bbfaae902896ba7938b58dfa5","last_reissued_at":"2026-06-10T00:08:28.801815Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T00:08:28.801815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09856","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":"2026-06-10T00:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wlk1TEEEiMZvSVt2V+qvySUSUXPbYRv0ooDKTK//IKmU/loulZsYm4/+/d6O6WGFus9MUNg4A1Xrsi7GjpxCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T20:34:39.803845Z"},"content_sha256":"dbd2a0b664f88fb5a6f1449c380bba99df6ea625d098dba9b8a323c9d374cd4b","schema_version":"1.0","event_id":"sha256:dbd2a0b664f88fb5a6f1449c380bba99df6ea625d098dba9b8a323c9d374cd4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KJITCPSE6JZMK5D2BQ4LZOZ7U5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Akshay K. Jagadish, Brenden M. Lake, Liyi Zhang, Thomas L. Griffiths","submitted_at":"2026-05-26T15:40:02Z","abstract_excerpt":"Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable. Yet, many real-world reasoning problems are inductive: agents must infer uncertain beliefs from sparse, ambiguous observations. There are challenges to using standard fine-tuning methods for inductive reasoning, including difficulties in curating large-scale, high-quality labeled datasets and in handling targets that are inherently distributional. In this work, we introduce a novel approach, called Program-based Posterior Training (PPT), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09856","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/2606.09856/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":"2026-06-10T00:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B5brbp0miQCb3EVR5yK8jKlGBENfokJ7oDHrUCxWqUAey9hRPg0Nh0DieKvqtrtQaTx1of2f5ryxjc7kvU6aCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T20:34:39.804214Z"},"content_sha256":"2f312db401ad48c210310b3be6598160d1d8314a4ba7b864456d63f5260b1ae3","schema_version":"1.0","event_id":"sha256:2f312db401ad48c210310b3be6598160d1d8314a4ba7b864456d63f5260b1ae3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJITCPSE6JZMK5D2BQ4LZOZ7U5/bundle.json","state_url":"https://pith.science/pith/KJITCPSE6JZMK5D2BQ4LZOZ7U5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJITCPSE6JZMK5D2BQ4LZOZ7U5/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":"2026-06-26T20:34:39Z","links":{"resolver":"https://pith.science/pith/KJITCPSE6JZMK5D2BQ4LZOZ7U5","bundle":"https://pith.science/pith/KJITCPSE6JZMK5D2BQ4LZOZ7U5/bundle.json","state":"https://pith.science/pith/KJITCPSE6JZMK5D2BQ4LZOZ7U5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJITCPSE6JZMK5D2BQ4LZOZ7U5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KJITCPSE6JZMK5D2BQ4LZOZ7U5","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":"de113c10888572af9dcb2f6f5ae415c86f9cebe33fce92034a1b24b25a4e1d65","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T15:40:02Z","title_canon_sha256":"d3611994170bfd7b823dbc31cb0f82b661a555608d8d550e12603543ec87a326"},"schema_version":"1.0","source":{"id":"2606.09856","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09856","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09856v1","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09856","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"KJITCPSE6JZM","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"pith_short_16","alias_value":"KJITCPSE6JZMK5D2","created_at":"2026-06-10T00:08:28Z"},{"alias_kind":"pith_short_8","alias_value":"KJITCPSE","created_at":"2026-06-10T00:08:28Z"}],"graph_snapshots":[{"event_id":"sha256:2f312db401ad48c210310b3be6598160d1d8314a4ba7b864456d63f5260b1ae3","target":"graph","created_at":"2026-06-10T00:08:28Z","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/2606.09856/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable. Yet, many real-world reasoning problems are inductive: agents must infer uncertain beliefs from sparse, ambiguous observations. There are challenges to using standard fine-tuning methods for inductive reasoning, including difficulties in curating large-scale, high-quality labeled datasets and in handling targets that are inherently distributional. In this work, we introduce a novel approach, called Program-based Posterior Training (PPT), ","authors_text":"Akshay K. Jagadish, Brenden M. Lake, Liyi Zhang, Thomas L. Griffiths","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T15:40:02Z","title":"Using Probabilistic Programs to Train Inductive Reasoning in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09856","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:dbd2a0b664f88fb5a6f1449c380bba99df6ea625d098dba9b8a323c9d374cd4b","target":"record","created_at":"2026-06-10T00:08:28Z","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":"de113c10888572af9dcb2f6f5ae415c86f9cebe33fce92034a1b24b25a4e1d65","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T15:40:02Z","title_canon_sha256":"d3611994170bfd7b823dbc31cb0f82b661a555608d8d550e12603543ec87a326"},"schema_version":"1.0","source":{"id":"2606.09856","kind":"arxiv","version":1}},"canonical_sha256":"5251313e44f272c5747a0c38bcbb3fa774337b9bbfaae902896ba7938b58dfa5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5251313e44f272c5747a0c38bcbb3fa774337b9bbfaae902896ba7938b58dfa5","first_computed_at":"2026-06-10T00:08:28.801815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:28.801815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rtsqJ4ZO9ddw9jUBKbzN6ZnaYgTtLJ62MmfgbjPAN5q2ECB3MbhsZGCMaIyEC2TnWQHX3nmPpb0VJTlqWkyVAg==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:28.802716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09856","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbd2a0b664f88fb5a6f1449c380bba99df6ea625d098dba9b8a323c9d374cd4b","sha256:2f312db401ad48c210310b3be6598160d1d8314a4ba7b864456d63f5260b1ae3"],"state_sha256":"a2bf65da153dc6c6b9dc98fdf5fd50c4a2614611dc783b34ae94c2c7c34b77e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xpsOEgXVIg7D2Y4VuoPYEXcbqYveFbuSIZWp2t5vrZ8luJzGQ1dbAe2X15icfd5ms+0DoAW0Mt5PYETcLcPLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T20:34:39.806140Z","bundle_sha256":"015e8a0646d29a45ec16ac0ce2d3cb70c10ac87ea09e2cde3be4727e4347082b"}}