{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3RBXO5D3CANZT33BAUYL5ZTZGX","short_pith_number":"pith:3RBXO5D3","canonical_record":{"source":{"id":"2310.10226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T09:35:42Z","cross_cats_sorted":[],"title_canon_sha256":"96bb2479267d6d8e7a88a3f5fc3291a3612e1ca4695264bbcd1831216c3b8c48","abstract_canon_sha256":"3217b8132085b4bf4caeda7e01479d2f510db6f36f982450dd6b0a827a275d5a"},"schema_version":"1.0"},"canonical_sha256":"dc4377747b101b99ef610530bee67935f10e064ad3215f64dd014f7e6e5611da","source":{"kind":"arxiv","id":"2310.10226","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10226","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10226v1","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10226","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"3RBXO5D3CANZ","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"pith_short_16","alias_value":"3RBXO5D3CANZT33B","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"pith_short_8","alias_value":"3RBXO5D3","created_at":"2026-07-05T07:01:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3RBXO5D3CANZT33BAUYL5ZTZGX","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T09:35:42Z","cross_cats_sorted":[],"title_canon_sha256":"96bb2479267d6d8e7a88a3f5fc3291a3612e1ca4695264bbcd1831216c3b8c48","abstract_canon_sha256":"3217b8132085b4bf4caeda7e01479d2f510db6f36f982450dd6b0a827a275d5a"},"schema_version":"1.0"},"canonical_sha256":"dc4377747b101b99ef610530bee67935f10e064ad3215f64dd014f7e6e5611da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:17.359101Z","signature_b64":"r372VfU2dPoaW/rxnyaRrD1zKzQDtE5xbnxf08IIXnHptJ50nBc5oGMiwuLYwIAwSmMF3QTQEVZofxOU33S1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc4377747b101b99ef610530bee67935f10e064ad3215f64dd014f7e6e5611da","last_reissued_at":"2026-07-05T07:01:17.358598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:17.358598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10226","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":"2026-07-05T07:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nWqr4X4/VeU2iklmSvEEvxUbWWU/2rUjBecCzjntI/bsPORHjupSqPUb0V94He+YBshmHGnbSjommt7GdiPdDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:23:19.475600Z"},"content_sha256":"9131e033abecb1aa4d83d2ebbd0ec4ac902e4c3c78aa3cfffc450b21dd0224ad","schema_version":"1.0","event_id":"sha256:9131e033abecb1aa4d83d2ebbd0ec4ac902e4c3c78aa3cfffc450b21dd0224ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3RBXO5D3CANZT33BAUYL5ZTZGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deng Cai, Huayang Li, Lemao Liu, Nigel Collier, Taro Watanabe, Tian Lan, Yixuan Su, Zihao Fu","submitted_at":"2023-10-16T09:35:42Z","abstract_excerpt":"There are a number of diverging hypotheses about the neural text degeneration problem, i.e., generating repetitive and dull loops, which makes this problem both interesting and confusing. In this work, we aim to advance our understanding by presenting a straightforward and fundamental explanation from the data perspective. Our preliminary investigation reveals a strong correlation between the degeneration issue and the presence of repetitions in training data. Subsequent experiments also demonstrate that by selectively dropping out the attention to repetitive words in training data, degenerati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10226","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/2310.10226/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":"2026-07-05T07:01:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kpKYwk0aeKzj/qgqUA0HdLXd626kBBoX4K6DcVDwaJvqpvCoUyTff9fRDu/IqZkhb2lOcqC1tS7KSuLkbPgPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T09:23:19.476131Z"},"content_sha256":"91c16221fd5eb2cf8145cac035a21c78a001d63d89ed976568dbda930f9c5f5c","schema_version":"1.0","event_id":"sha256:91c16221fd5eb2cf8145cac035a21c78a001d63d89ed976568dbda930f9c5f5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RBXO5D3CANZT33BAUYL5ZTZGX/bundle.json","state_url":"https://pith.science/pith/3RBXO5D3CANZT33BAUYL5ZTZGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RBXO5D3CANZT33BAUYL5ZTZGX/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":"2026-08-11T09:23:19Z","links":{"resolver":"https://pith.science/pith/3RBXO5D3CANZT33BAUYL5ZTZGX","bundle":"https://pith.science/pith/3RBXO5D3CANZT33BAUYL5ZTZGX/bundle.json","state":"https://pith.science/pith/3RBXO5D3CANZT33BAUYL5ZTZGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RBXO5D3CANZT33BAUYL5ZTZGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3RBXO5D3CANZT33BAUYL5ZTZGX","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":"3217b8132085b4bf4caeda7e01479d2f510db6f36f982450dd6b0a827a275d5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T09:35:42Z","title_canon_sha256":"96bb2479267d6d8e7a88a3f5fc3291a3612e1ca4695264bbcd1831216c3b8c48"},"schema_version":"1.0","source":{"id":"2310.10226","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10226","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10226v1","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10226","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"3RBXO5D3CANZ","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"pith_short_16","alias_value":"3RBXO5D3CANZT33B","created_at":"2026-07-05T07:01:17Z"},{"alias_kind":"pith_short_8","alias_value":"3RBXO5D3","created_at":"2026-07-05T07:01:17Z"}],"graph_snapshots":[{"event_id":"sha256:91c16221fd5eb2cf8145cac035a21c78a001d63d89ed976568dbda930f9c5f5c","target":"graph","created_at":"2026-07-05T07:01:17Z","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/2310.10226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are a number of diverging hypotheses about the neural text degeneration problem, i.e., generating repetitive and dull loops, which makes this problem both interesting and confusing. In this work, we aim to advance our understanding by presenting a straightforward and fundamental explanation from the data perspective. Our preliminary investigation reveals a strong correlation between the degeneration issue and the presence of repetitions in training data. Subsequent experiments also demonstrate that by selectively dropping out the attention to repetitive words in training data, degenerati","authors_text":"Deng Cai, Huayang Li, Lemao Liu, Nigel Collier, Taro Watanabe, Tian Lan, Yixuan Su, Zihao Fu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T09:35:42Z","title":"Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10226","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":"sha256:9131e033abecb1aa4d83d2ebbd0ec4ac902e4c3c78aa3cfffc450b21dd0224ad","target":"record","created_at":"2026-07-05T07:01:17Z","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":"3217b8132085b4bf4caeda7e01479d2f510db6f36f982450dd6b0a827a275d5a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-16T09:35:42Z","title_canon_sha256":"96bb2479267d6d8e7a88a3f5fc3291a3612e1ca4695264bbcd1831216c3b8c48"},"schema_version":"1.0","source":{"id":"2310.10226","kind":"arxiv","version":1}},"canonical_sha256":"dc4377747b101b99ef610530bee67935f10e064ad3215f64dd014f7e6e5611da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc4377747b101b99ef610530bee67935f10e064ad3215f64dd014f7e6e5611da","first_computed_at":"2026-07-05T07:01:17.358598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:17.358598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r372VfU2dPoaW/rxnyaRrD1zKzQDtE5xbnxf08IIXnHptJ50nBc5oGMiwuLYwIAwSmMF3QTQEVZofxOU33S1Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:17.359101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10226","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9131e033abecb1aa4d83d2ebbd0ec4ac902e4c3c78aa3cfffc450b21dd0224ad","sha256:91c16221fd5eb2cf8145cac035a21c78a001d63d89ed976568dbda930f9c5f5c"],"state_sha256":"851d427b8cde8cc8d20a6230467a151d6d5d28711023c67c46c3a68c796fb316"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwrJP0xt76A2ALkEIPRA8IcGsBGEG973D1otR10beCxNjqo3T5zpXRZSsv3uqCZ5iemBVfxXuustJ4HfTSkqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T09:23:19.483261Z","bundle_sha256":"c6a94a8d1453f471fb023dc5b657368d8dd9aa5d1d453856b57062c51c317e6f"}}