{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GC4LIP5NH66NKL4BA4RTHUPIAC","short_pith_number":"pith:GC4LIP5N","canonical_record":{"source":{"id":"2510.14331","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-16T06:10:11Z","cross_cats_sorted":[],"title_canon_sha256":"e2f4f6a346271267c5ef888849d66f0b65e2cc0f0e4fcf6c48d7636343384b45","abstract_canon_sha256":"88f3f119194e350de8ad4ac9c6c7b5db2403897c60d916e2b5bbc6a3ae3a1f84"},"schema_version":"1.0"},"canonical_sha256":"30b8b43fad3fbcd52f81072333d1e8008afac58d9b9d374e984f9a1e84e7bafd","source":{"kind":"arxiv","id":"2510.14331","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14331","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14331v3","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14331","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"GC4LIP5NH66N","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"GC4LIP5NH66NKL4B","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"GC4LIP5N","created_at":"2026-07-03T01:17:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GC4LIP5NH66NKL4BA4RTHUPIAC","target":"record","payload":{"canonical_record":{"source":{"id":"2510.14331","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-16T06:10:11Z","cross_cats_sorted":[],"title_canon_sha256":"e2f4f6a346271267c5ef888849d66f0b65e2cc0f0e4fcf6c48d7636343384b45","abstract_canon_sha256":"88f3f119194e350de8ad4ac9c6c7b5db2403897c60d916e2b5bbc6a3ae3a1f84"},"schema_version":"1.0"},"canonical_sha256":"30b8b43fad3fbcd52f81072333d1e8008afac58d9b9d374e984f9a1e84e7bafd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:13.718699Z","signature_b64":"j8NDvpdhEQa1M2sPLFgyWFzTpSQ/EBSFLTrgkviZMnhhpdLwQG2i1/KWMe7AO8uwg/hJMhVkF8wlP1JP71aaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30b8b43fad3fbcd52f81072333d1e8008afac58d9b9d374e984f9a1e84e7bafd","last_reissued_at":"2026-07-03T01:17:13.718174Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:13.718174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.14331","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":"2026-07-03T01:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bl/2CogrGNTITRGtc80W7DQ4hgCKtsyBnTg+1gztuCTn/i+GvZedGvKTkF6sxDkbunUxeFYjgyqU7Unoi+akCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T04:06:49.554785Z"},"content_sha256":"5af19c63476e56cff5c5cb9791be548701bd46a983e353870ec04251067ab61b","schema_version":"1.0","event_id":"sha256:5af19c63476e56cff5c5cb9791be548701bd46a983e353870ec04251067ab61b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GC4LIP5NH66NKL4BA4RTHUPIAC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM Priors for ERM over Programs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eran Malach, Priyadarsi Mishra, Shivam Singhal, Tomer Galanti","submitted_at":"2025-10-16T06:10:11Z","abstract_excerpt":"We study program-learning methods that are efficient in both samples and computation. Classical learning theory suggests that when the target admits a short program description, for example a short piece of ``Python code'', it can be learned from few examples by ERM over the program class. However, this approach relies on enumerating candidate programs, which is typically exponential in the description length; gradient-based training avoids this explicit search but, for some families of short programs, can require exponentially many samples to succeed. We propose \\textsc{LLM-PV}, a propose-and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14331","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/2510.14331/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":"2026-07-03T01:17:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yY5fjplsyyEN8ZOrLHbac0opTOOKZmDbxy5zNOLLuwXOqK5oLgVW8MiUDf78hUoy1jsBYE5fMWMqurHxE8aDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T04:06:49.555074Z"},"content_sha256":"d71d87ff0061e4a852cf2e6a1cf1169d9b68bbf715949b9ecb79d4ad52487faa","schema_version":"1.0","event_id":"sha256:d71d87ff0061e4a852cf2e6a1cf1169d9b68bbf715949b9ecb79d4ad52487faa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GC4LIP5NH66NKL4BA4RTHUPIAC/bundle.json","state_url":"https://pith.science/pith/GC4LIP5NH66NKL4BA4RTHUPIAC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GC4LIP5NH66NKL4BA4RTHUPIAC/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":"2026-08-02T04:06:49Z","links":{"resolver":"https://pith.science/pith/GC4LIP5NH66NKL4BA4RTHUPIAC","bundle":"https://pith.science/pith/GC4LIP5NH66NKL4BA4RTHUPIAC/bundle.json","state":"https://pith.science/pith/GC4LIP5NH66NKL4BA4RTHUPIAC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GC4LIP5NH66NKL4BA4RTHUPIAC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GC4LIP5NH66NKL4BA4RTHUPIAC","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":"88f3f119194e350de8ad4ac9c6c7b5db2403897c60d916e2b5bbc6a3ae3a1f84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-16T06:10:11Z","title_canon_sha256":"e2f4f6a346271267c5ef888849d66f0b65e2cc0f0e4fcf6c48d7636343384b45"},"schema_version":"1.0","source":{"id":"2510.14331","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14331","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14331v3","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14331","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"GC4LIP5NH66N","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"GC4LIP5NH66NKL4B","created_at":"2026-07-03T01:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"GC4LIP5N","created_at":"2026-07-03T01:17:13Z"}],"graph_snapshots":[{"event_id":"sha256:d71d87ff0061e4a852cf2e6a1cf1169d9b68bbf715949b9ecb79d4ad52487faa","target":"graph","created_at":"2026-07-03T01:17:13Z","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/2510.14331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study program-learning methods that are efficient in both samples and computation. Classical learning theory suggests that when the target admits a short program description, for example a short piece of ``Python code'', it can be learned from few examples by ERM over the program class. However, this approach relies on enumerating candidate programs, which is typically exponential in the description length; gradient-based training avoids this explicit search but, for some families of short programs, can require exponentially many samples to succeed. We propose \\textsc{LLM-PV}, a propose-and","authors_text":"Eran Malach, Priyadarsi Mishra, Shivam Singhal, Tomer Galanti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-16T06:10:11Z","title":"LLM Priors for ERM over Programs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14331","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":"sha256:5af19c63476e56cff5c5cb9791be548701bd46a983e353870ec04251067ab61b","target":"record","created_at":"2026-07-03T01:17:13Z","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":"88f3f119194e350de8ad4ac9c6c7b5db2403897c60d916e2b5bbc6a3ae3a1f84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-16T06:10:11Z","title_canon_sha256":"e2f4f6a346271267c5ef888849d66f0b65e2cc0f0e4fcf6c48d7636343384b45"},"schema_version":"1.0","source":{"id":"2510.14331","kind":"arxiv","version":3}},"canonical_sha256":"30b8b43fad3fbcd52f81072333d1e8008afac58d9b9d374e984f9a1e84e7bafd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30b8b43fad3fbcd52f81072333d1e8008afac58d9b9d374e984f9a1e84e7bafd","first_computed_at":"2026-07-03T01:17:13.718174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:13.718174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j8NDvpdhEQa1M2sPLFgyWFzTpSQ/EBSFLTrgkviZMnhhpdLwQG2i1/KWMe7AO8uwg/hJMhVkF8wlP1JP71aaDQ==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:13.718699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.14331","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5af19c63476e56cff5c5cb9791be548701bd46a983e353870ec04251067ab61b","sha256:d71d87ff0061e4a852cf2e6a1cf1169d9b68bbf715949b9ecb79d4ad52487faa"],"state_sha256":"d8135e97f13d0d174c1339e80886ebad0af857e3de79adb863ce3793e65a14d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6lNd5VP5EjgoSC+GAFfECjazhStRYB6zxN2dVSmV2bMVLnSU5Ge9ECa/FN9rFwkJdFcS0Xgk5flsstJsvP9cDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T04:06:49.557314Z","bundle_sha256":"b08010c21b0c50e3f4d39c92de5ad4bfd824d0ac0a411acc4d37fe004b092203"}}