{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PWMHEGTUBP4FRAP7JJCWL3ZABI","short_pith_number":"pith:PWMHEGTU","canonical_record":{"source":{"id":"2605.20602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T01:44:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c2b92730954f699c17986f2306f189c4b470b12ee51577df062b2bbfe8917877","abstract_canon_sha256":"42b0487437fa7b483d7e700031afde1dd6fe1082f777a1452429c9abf4871392"},"schema_version":"1.0"},"canonical_sha256":"7d98721a740bf85881ff4a4565ef200a05979dae5fbd643f0571bca49a7f77d2","source":{"kind":"arxiv","id":"2605.20602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20602","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20602v1","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20602","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"PWMHEGTUBP4F","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"PWMHEGTUBP4FRAP7","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"PWMHEGTU","created_at":"2026-05-21T01:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PWMHEGTUBP4FRAP7JJCWL3ZABI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20602","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T01:44:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c2b92730954f699c17986f2306f189c4b470b12ee51577df062b2bbfe8917877","abstract_canon_sha256":"42b0487437fa7b483d7e700031afde1dd6fe1082f777a1452429c9abf4871392"},"schema_version":"1.0"},"canonical_sha256":"7d98721a740bf85881ff4a4565ef200a05979dae5fbd643f0571bca49a7f77d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:44.118097Z","signature_b64":"hNfNlMmhNKBicm+2AN79+Aa2FtkPPry4Z8ogGpRKp7t3qLL/oW+Myss8n+MMi0pTtDs9lZJ5OddF/WiNjYrCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d98721a740bf85881ff4a4565ef200a05979dae5fbd643f0571bca49a7f77d2","last_reissued_at":"2026-05-21T01:04:44.117490Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:44.117490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20602","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":"2026-05-21T01:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yD/cGGzfx9wf1NkZWvybdyXIN19gUTmSk8WxE/Weqvnj2SiznFPhBUu35CDatei5erpFRt/EEw/WSyOqhIjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:31:19.262124Z"},"content_sha256":"4b54e100bb501d2256f3e6575ba18e6f2356a03f620e6eeb4b25083b42093613","schema_version":"1.0","event_id":"sha256:4b54e100bb501d2256f3e6575ba18e6f2356a03f620e6eeb4b25083b42093613"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PWMHEGTUBP4FRAP7JJCWL3ZABI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ming Liu","submitted_at":"2026-05-20T01:44:47Z","abstract_excerpt":"Successive self-training on a language model's own outputs is widely characterized as a process of flattening: diversity drops, distributions narrow, and the text becomes \"more like itself.\" We provide evidence that this characterization is incomplete. Across eleven generations of self-training on five models (GPT-2 124M, Pythia-410M, Pythia-1.4B, OPT-1.3B, Pythia-2.8B), language is not flattened uniformly -- it is restructured. Surface markers (discourse connectives, hedges, em-dashes) rise, while mid- and deep-syntactic structures (questions, parentheticals, passives, subjunctives) collapse."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20602","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/2605.20602/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":"2026-05-21T01:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B7NtYrn5tFocjmqvm187PMhbfPNTh+M6mwJTNSCRMTT6mOgk829WpRE7Yqd/pEGpWmSCieDQnNbiRcCVRUpnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:31:19.262940Z"},"content_sha256":"3305e2915ef719f973a0df0cf90ee1e01be21a2dc35cb52a40c12f862b42e867","schema_version":"1.0","event_id":"sha256:3305e2915ef719f973a0df0cf90ee1e01be21a2dc35cb52a40c12f862b42e867"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PWMHEGTUBP4FRAP7JJCWL3ZABI/bundle.json","state_url":"https://pith.science/pith/PWMHEGTUBP4FRAP7JJCWL3ZABI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PWMHEGTUBP4FRAP7JJCWL3ZABI/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":"2026-05-22T23:31:19Z","links":{"resolver":"https://pith.science/pith/PWMHEGTUBP4FRAP7JJCWL3ZABI","bundle":"https://pith.science/pith/PWMHEGTUBP4FRAP7JJCWL3ZABI/bundle.json","state":"https://pith.science/pith/PWMHEGTUBP4FRAP7JJCWL3ZABI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PWMHEGTUBP4FRAP7JJCWL3ZABI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PWMHEGTUBP4FRAP7JJCWL3ZABI","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":"42b0487437fa7b483d7e700031afde1dd6fe1082f777a1452429c9abf4871392","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T01:44:47Z","title_canon_sha256":"c2b92730954f699c17986f2306f189c4b470b12ee51577df062b2bbfe8917877"},"schema_version":"1.0","source":{"id":"2605.20602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20602","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20602v1","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20602","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"PWMHEGTUBP4F","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"PWMHEGTUBP4FRAP7","created_at":"2026-05-21T01:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"PWMHEGTU","created_at":"2026-05-21T01:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:3305e2915ef719f973a0df0cf90ee1e01be21a2dc35cb52a40c12f862b42e867","target":"graph","created_at":"2026-05-21T01:04:44Z","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/2605.20602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Successive self-training on a language model's own outputs is widely characterized as a process of flattening: diversity drops, distributions narrow, and the text becomes \"more like itself.\" We provide evidence that this characterization is incomplete. Across eleven generations of self-training on five models (GPT-2 124M, Pythia-410M, Pythia-1.4B, OPT-1.3B, Pythia-2.8B), language is not flattened uniformly -- it is restructured. Surface markers (discourse connectives, hedges, em-dashes) rise, while mid- and deep-syntactic structures (questions, parentheticals, passives, subjunctives) collapse.","authors_text":"Ming Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T01:44:47Z","title":"Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20602","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":"sha256:4b54e100bb501d2256f3e6575ba18e6f2356a03f620e6eeb4b25083b42093613","target":"record","created_at":"2026-05-21T01:04:44Z","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":"42b0487437fa7b483d7e700031afde1dd6fe1082f777a1452429c9abf4871392","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T01:44:47Z","title_canon_sha256":"c2b92730954f699c17986f2306f189c4b470b12ee51577df062b2bbfe8917877"},"schema_version":"1.0","source":{"id":"2605.20602","kind":"arxiv","version":1}},"canonical_sha256":"7d98721a740bf85881ff4a4565ef200a05979dae5fbd643f0571bca49a7f77d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d98721a740bf85881ff4a4565ef200a05979dae5fbd643f0571bca49a7f77d2","first_computed_at":"2026-05-21T01:04:44.117490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:44.117490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hNfNlMmhNKBicm+2AN79+Aa2FtkPPry4Z8ogGpRKp7t3qLL/oW+Myss8n+MMi0pTtDs9lZJ5OddF/WiNjYrCDQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:44.118097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b54e100bb501d2256f3e6575ba18e6f2356a03f620e6eeb4b25083b42093613","sha256:3305e2915ef719f973a0df0cf90ee1e01be21a2dc35cb52a40c12f862b42e867"],"state_sha256":"3bf4d4d04612e7f012d6cf86e09ec21d8a394e5f85b51c299d1e64bdc5d2c2ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/eJR18oIi8T5obUe+2vTBF7HuElS1MC8zMn1KqJmP2/bH9qJis12h23saFD4AWtjlWA1QP5uWgqHpqZMCdM8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T23:31:19.267932Z","bundle_sha256":"59af53fa737e00b6ed51245edaf36d55dfee47ff7badd963933402872169890e"}}