{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WZAEYRPH3BIWJXX3VFT5IIL37X","short_pith_number":"pith:WZAEYRPH","canonical_record":{"source":{"id":"2310.15829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T13:32:20Z","cross_cats_sorted":[],"title_canon_sha256":"9c605ef22a31c0dcdf782f98ccfdf80ed43189efff1bc6cb373df9970293829b","abstract_canon_sha256":"cada058f1726f64376edb56fe58d7ae656f344a64632d99a97d422bf4f0c1e43"},"schema_version":"1.0"},"canonical_sha256":"b6404c45e7d85164defba967d4217bfddcf91302c5c3f839f8f3c78306788c35","source":{"kind":"arxiv","id":"2310.15829","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15829","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15829v1","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15829","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"WZAEYRPH3BIW","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"WZAEYRPH3BIWJXX3","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"WZAEYRPH","created_at":"2026-07-05T07:04:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WZAEYRPH3BIWJXX3VFT5IIL37X","target":"record","payload":{"canonical_record":{"source":{"id":"2310.15829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T13:32:20Z","cross_cats_sorted":[],"title_canon_sha256":"9c605ef22a31c0dcdf782f98ccfdf80ed43189efff1bc6cb373df9970293829b","abstract_canon_sha256":"cada058f1726f64376edb56fe58d7ae656f344a64632d99a97d422bf4f0c1e43"},"schema_version":"1.0"},"canonical_sha256":"b6404c45e7d85164defba967d4217bfddcf91302c5c3f839f8f3c78306788c35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:31.499255Z","signature_b64":"qRszkKwrjVwHxPmRkmZzPv8bKCdEGuz9VeGeL9la74tQD3qh3ikpBIF4cakfQehwhWQ8oyndYlvw7FT+LtoUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6404c45e7d85164defba967d4217bfddcf91302c5c3f839f8f3c78306788c35","last_reissued_at":"2026-07-05T07:04:31.498706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:31.498706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.15829","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":"2026-07-05T07:04:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvB4otO+uj0PvjI0fpnwFXXFpKhcRRrHDadMw//iBfv3rgCliqBVftPibH2VAyof/4rI4iEj6rgS3UvVGBEOBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:25:58.629580Z"},"content_sha256":"f1aa0fa16357e76ab828b3c3e8dd86d513667f54b9ac0ec842afae66ce861a59","schema_version":"1.0","event_id":"sha256:f1aa0fa16357e76ab828b3c3e8dd86d513667f54b9ac0ec842afae66ce861a59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WZAEYRPH3BIWJXX3VFT5IIL37X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unnatural language processing: How do language models handle machine-generated prompts?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Corentin Kervadec, Francesca Franzon, Marco Baroni","submitted_at":"2023-10-24T13:32:20Z","abstract_excerpt":"Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are routinely outperformed by automatically generated token sequences with no apparent meaning or syntactic structure, including sequences of vectors from a model's embedding space. We use machine-generated prompts to probe how models respond to input that is not composed of natural language expressions. We study the behavior of models of different sizes in multiple semantic tasks in response to both continuous and discrete machine-generated prompts, and compare it to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15829","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/2310.15829/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":"2026-07-05T07:04:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y1h9KDm4DpHIWZpO/4Qqveh6hoepsfoo/wY7LxDXgaJNlWLBfCeyio2ikZQTHTaQE+/MyCgyu4tZCLoeidiwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:25:58.630275Z"},"content_sha256":"e70a69eb3a65a4f854c0a97b83194345e124e6a55e9ac0a7ef44dc73c848276f","schema_version":"1.0","event_id":"sha256:e70a69eb3a65a4f854c0a97b83194345e124e6a55e9ac0a7ef44dc73c848276f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZAEYRPH3BIWJXX3VFT5IIL37X/bundle.json","state_url":"https://pith.science/pith/WZAEYRPH3BIWJXX3VFT5IIL37X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZAEYRPH3BIWJXX3VFT5IIL37X/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":"2026-08-04T20:25:58Z","links":{"resolver":"https://pith.science/pith/WZAEYRPH3BIWJXX3VFT5IIL37X","bundle":"https://pith.science/pith/WZAEYRPH3BIWJXX3VFT5IIL37X/bundle.json","state":"https://pith.science/pith/WZAEYRPH3BIWJXX3VFT5IIL37X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZAEYRPH3BIWJXX3VFT5IIL37X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WZAEYRPH3BIWJXX3VFT5IIL37X","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":"cada058f1726f64376edb56fe58d7ae656f344a64632d99a97d422bf4f0c1e43","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T13:32:20Z","title_canon_sha256":"9c605ef22a31c0dcdf782f98ccfdf80ed43189efff1bc6cb373df9970293829b"},"schema_version":"1.0","source":{"id":"2310.15829","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15829","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15829v1","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15829","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"WZAEYRPH3BIW","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"WZAEYRPH3BIWJXX3","created_at":"2026-07-05T07:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"WZAEYRPH","created_at":"2026-07-05T07:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:e70a69eb3a65a4f854c0a97b83194345e124e6a55e9ac0a7ef44dc73c848276f","target":"graph","created_at":"2026-07-05T07:04:31Z","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/2310.15829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model prompt optimization research has shown that semantically and grammatically well-formed manually crafted prompts are routinely outperformed by automatically generated token sequences with no apparent meaning or syntactic structure, including sequences of vectors from a model's embedding space. We use machine-generated prompts to probe how models respond to input that is not composed of natural language expressions. We study the behavior of models of different sizes in multiple semantic tasks in response to both continuous and discrete machine-generated prompts, and compare it to ","authors_text":"Corentin Kervadec, Francesca Franzon, Marco Baroni","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T13:32:20Z","title":"Unnatural language processing: How do language models handle machine-generated prompts?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15829","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:f1aa0fa16357e76ab828b3c3e8dd86d513667f54b9ac0ec842afae66ce861a59","target":"record","created_at":"2026-07-05T07:04:31Z","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":"cada058f1726f64376edb56fe58d7ae656f344a64632d99a97d422bf4f0c1e43","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T13:32:20Z","title_canon_sha256":"9c605ef22a31c0dcdf782f98ccfdf80ed43189efff1bc6cb373df9970293829b"},"schema_version":"1.0","source":{"id":"2310.15829","kind":"arxiv","version":1}},"canonical_sha256":"b6404c45e7d85164defba967d4217bfddcf91302c5c3f839f8f3c78306788c35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6404c45e7d85164defba967d4217bfddcf91302c5c3f839f8f3c78306788c35","first_computed_at":"2026-07-05T07:04:31.498706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:31.498706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qRszkKwrjVwHxPmRkmZzPv8bKCdEGuz9VeGeL9la74tQD3qh3ikpBIF4cakfQehwhWQ8oyndYlvw7FT+LtoUAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:31.499255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15829","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1aa0fa16357e76ab828b3c3e8dd86d513667f54b9ac0ec842afae66ce861a59","sha256:e70a69eb3a65a4f854c0a97b83194345e124e6a55e9ac0a7ef44dc73c848276f"],"state_sha256":"3afd99e1d406554dac1101d27c1390ae05e1663df83d59dbf72caee90f197ca7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xWTuZ9824aaOWcg61wV+Dp1fdtGZXYq9plHtlPjSvmRcii7to0lK1JmSoqaICBjwWLR2jf4Nwglpvg6nIF2gBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:25:58.636898Z","bundle_sha256":"e2f14cbc01b8e2ba9fe586ba243266f9a9dde5355eab748c4dcf8edb4d5a7023"}}