{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AMPZEUNNTS2P24ABPSN7VORVEM","short_pith_number":"pith:AMPZEUNN","canonical_record":{"source":{"id":"2305.03029","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T17:53:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b73f27caf7a1ea76de7ae66c4d8a0445ff8f721dc727fbe48f9ee31975a144a1","abstract_canon_sha256":"0035a028b9d3d4f4bbae844879bf16d70a2b5ad09041bed2d4e65fcf31459e01"},"schema_version":"1.0"},"canonical_sha256":"031f9251ad9cb4fd70017c9bfaba3523324b45251ad5f579fd0b7af3d73fda4a","source":{"kind":"arxiv","id":"2305.03029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03029","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03029v1","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03029","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"AMPZEUNNTS2P","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"AMPZEUNNTS2P24AB","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"AMPZEUNN","created_at":"2026-07-05T06:07:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AMPZEUNNTS2P24ABPSN7VORVEM","target":"record","payload":{"canonical_record":{"source":{"id":"2305.03029","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T17:53:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b73f27caf7a1ea76de7ae66c4d8a0445ff8f721dc727fbe48f9ee31975a144a1","abstract_canon_sha256":"0035a028b9d3d4f4bbae844879bf16d70a2b5ad09041bed2d4e65fcf31459e01"},"schema_version":"1.0"},"canonical_sha256":"031f9251ad9cb4fd70017c9bfaba3523324b45251ad5f579fd0b7af3d73fda4a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:07.424703Z","signature_b64":"ljgBmTxKy4wf9liWnfehIpEyrRKd86R2cj5wwypEHKKwtxUhYz6kPz94ttMhqNJ2gnagxhLkPgk+uOvamRD6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"031f9251ad9cb4fd70017c9bfaba3523324b45251ad5f579fd0b7af3d73fda4a","last_reissued_at":"2026-07-05T06:07:07.424259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:07.424259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.03029","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":"2026-07-05T06:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Boa+H2Ar71B/GhLFDHTILw9yLeW46MCRWFV/JKPeyZ9SyCcsDn/UpXkMTAsTGI1/fqAEKoDqPU97cXk81UDcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T10:33:20.712939Z"},"content_sha256":"9582f22c5de0a99f18af7b304f8a0c28f7d36c716904a033868f9e5d4d6e7737","schema_version":"1.0","event_id":"sha256:9582f22c5de0a99f18af7b304f8a0c28f7d36c716904a033868f9e5d4d6e7737"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AMPZEUNNTS2P24ABPSN7VORVEM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What changes when you randomly choose BPE merge operations? Not much","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Jonne S\\\"alev\\\"a","submitted_at":"2023-05-04T17:53:27Z","abstract_excerpt":"We introduce three simple randomized variants of byte pair encoding (BPE) and explore whether randomizing the selection of merge operations substantially affects a downstream machine translation task. We focus on translation into morphologically rich languages, hypothesizing that this task may show sensitivity to the method of choosing subwords. Analysis using a Bayesian linear model indicates that two of the variants perform nearly indistinguishably compared to standard BPE while the other degrades performance less than we anticipated. We conclude that although standard BPE is widely used, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03029","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/2305.03029/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":"2026-07-05T06:07:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RxINFCK3HB+ImZg5XsvO62mAE5mSsowjPMQXjYIr+uuUO5NHBR9ALCzGzksL79qefpYsLHFVY3NyV/6zL1/mCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T10:33:20.713333Z"},"content_sha256":"5f55287cb1fde0c082c8b89f0e6326765bd2be7d850907fe8f4882b4c4437096","schema_version":"1.0","event_id":"sha256:5f55287cb1fde0c082c8b89f0e6326765bd2be7d850907fe8f4882b4c4437096"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMPZEUNNTS2P24ABPSN7VORVEM/bundle.json","state_url":"https://pith.science/pith/AMPZEUNNTS2P24ABPSN7VORVEM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMPZEUNNTS2P24ABPSN7VORVEM/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":"2026-07-13T10:33:20Z","links":{"resolver":"https://pith.science/pith/AMPZEUNNTS2P24ABPSN7VORVEM","bundle":"https://pith.science/pith/AMPZEUNNTS2P24ABPSN7VORVEM/bundle.json","state":"https://pith.science/pith/AMPZEUNNTS2P24ABPSN7VORVEM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMPZEUNNTS2P24ABPSN7VORVEM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AMPZEUNNTS2P24ABPSN7VORVEM","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":"0035a028b9d3d4f4bbae844879bf16d70a2b5ad09041bed2d4e65fcf31459e01","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T17:53:27Z","title_canon_sha256":"b73f27caf7a1ea76de7ae66c4d8a0445ff8f721dc727fbe48f9ee31975a144a1"},"schema_version":"1.0","source":{"id":"2305.03029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.03029","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"arxiv_version","alias_value":"2305.03029v1","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.03029","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"pith_short_12","alias_value":"AMPZEUNNTS2P","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"pith_short_16","alias_value":"AMPZEUNNTS2P24AB","created_at":"2026-07-05T06:07:07Z"},{"alias_kind":"pith_short_8","alias_value":"AMPZEUNN","created_at":"2026-07-05T06:07:07Z"}],"graph_snapshots":[{"event_id":"sha256:5f55287cb1fde0c082c8b89f0e6326765bd2be7d850907fe8f4882b4c4437096","target":"graph","created_at":"2026-07-05T06:07:07Z","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/2305.03029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce three simple randomized variants of byte pair encoding (BPE) and explore whether randomizing the selection of merge operations substantially affects a downstream machine translation task. We focus on translation into morphologically rich languages, hypothesizing that this task may show sensitivity to the method of choosing subwords. Analysis using a Bayesian linear model indicates that two of the variants perform nearly indistinguishably compared to standard BPE while the other degrades performance less than we anticipated. We conclude that although standard BPE is widely used, th","authors_text":"Constantine Lignos, Jonne S\\\"alev\\\"a","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T17:53:27Z","title":"What changes when you randomly choose BPE merge operations? Not much"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.03029","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":"sha256:9582f22c5de0a99f18af7b304f8a0c28f7d36c716904a033868f9e5d4d6e7737","target":"record","created_at":"2026-07-05T06:07:07Z","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":"0035a028b9d3d4f4bbae844879bf16d70a2b5ad09041bed2d4e65fcf31459e01","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T17:53:27Z","title_canon_sha256":"b73f27caf7a1ea76de7ae66c4d8a0445ff8f721dc727fbe48f9ee31975a144a1"},"schema_version":"1.0","source":{"id":"2305.03029","kind":"arxiv","version":1}},"canonical_sha256":"031f9251ad9cb4fd70017c9bfaba3523324b45251ad5f579fd0b7af3d73fda4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"031f9251ad9cb4fd70017c9bfaba3523324b45251ad5f579fd0b7af3d73fda4a","first_computed_at":"2026-07-05T06:07:07.424259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:07.424259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ljgBmTxKy4wf9liWnfehIpEyrRKd86R2cj5wwypEHKKwtxUhYz6kPz94ttMhqNJ2gnagxhLkPgk+uOvamRD6BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:07.424703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.03029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9582f22c5de0a99f18af7b304f8a0c28f7d36c716904a033868f9e5d4d6e7737","sha256:5f55287cb1fde0c082c8b89f0e6326765bd2be7d850907fe8f4882b4c4437096"],"state_sha256":"37dff35d08d88ff493612578a93cbbcf80320ffd9c71f3a0d17d5463887625a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V5AX1rZ8pV0zudZu15FFzTy6i2NHPTf/hLyMn3+8kcpHAKzluEl6sgx3jtQdmFycb6v/8mJIFlHe0lGyu/m1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T10:33:20.715506Z","bundle_sha256":"5c3250486ce553b1276054f67ce9101d6e794955e353c52b5724b5d5851715bd"}}