{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XRQACSIDCF5EX4YKLFIRJDDIGI","short_pith_number":"pith:XRQACSID","canonical_record":{"source":{"id":"2605.16608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T20:17:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e05b263cd6a098d69c689be231fd365beee6dbb73692541a56ab2a67714693c3","abstract_canon_sha256":"470c0c1e38bc9aa0c28c3be64a3d2ea51a6b022a2e6ab04a56a41a8ff42d626b"},"schema_version":"1.0"},"canonical_sha256":"bc60014903117a4bf30a5951148c683239c9056263afe73edbe2c1e9e4376cf9","source":{"kind":"arxiv","id":"2605.16608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16608","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16608v1","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16608","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"XRQACSIDCF5E","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"XRQACSIDCF5EX4YK","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"XRQACSID","created_at":"2026-05-20T00:02:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XRQACSIDCF5EX4YKLFIRJDDIGI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T20:17:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e05b263cd6a098d69c689be231fd365beee6dbb73692541a56ab2a67714693c3","abstract_canon_sha256":"470c0c1e38bc9aa0c28c3be64a3d2ea51a6b022a2e6ab04a56a41a8ff42d626b"},"schema_version":"1.0"},"canonical_sha256":"bc60014903117a4bf30a5951148c683239c9056263afe73edbe2c1e9e4376cf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:32.279449Z","signature_b64":"rdEPWvEGqjIW4t8dyLNq5pFLXJgH5CbJfmvNRjgLuJQoJawSrCfu22YuC7jRmh1cAeTKY7dEgaUPE7+tOLjDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc60014903117a4bf30a5951148c683239c9056263afe73edbe2c1e9e4376cf9","last_reissued_at":"2026-05-20T00:02:32.278539Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:32.278539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16608","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":"2026-05-20T00:02:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWOsF9o3ret/E1E+sN76JGNB9T95qkS9/UI2Md19MC1qw7ivGZikJwdn5BiNbBFqXjCFnj4OtbGYcSsmeXwcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:44:45.526485Z"},"content_sha256":"7376c2524b0b4b5ebb2cf501542b483db9ec64626e4dd54ad9fb5f179f3cc41e","schema_version":"1.0","event_id":"sha256:7376c2524b0b4b5ebb2cf501542b483db9ec64626e4dd54ad9fb5f179f3cc41e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XRQACSIDCF5EX4YKLFIRJDDIGI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Embeddings, Except In Heavy Truncation Scenarios","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Daniel Ruffinelli, Simone Paolo Ponzetto, Sotaro Takeshita, Yurina Takeshita","submitted_at":"2026-05-15T20:17:34Z","abstract_excerpt":"Matryoshka Representation Learning (MRL) is a widely adopted approach for training text encoders so they provide useful text representations at various sizes, available by simply truncating the resulting vectors at sizes pre-determined at training time. Recent works have shown that randomly truncating text embeddings has minimal impact in downstream performance unless vectors are reduced in size by at least 70%, suggesting that embeddings are already robust to truncation without the use of MRL. However, no prior work has compared random truncation to MRL, so it is unclear how the two methods c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16608","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/2605.16608/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T19:21:56.795392Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.596234Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"bbf7ae18c0d74537f9d8c32fe72d92a12aaabdf954327ebf775168dcbb1bdc9a"},"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":"2026-05-20T00:02:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DfdRS0iUvuxu+IZ3tfjWAb8g3FdSPOfAiA0RkM7QyfNuQ8dBggMjezco/UJFQ4cc+4cDQ6mMNiH5NB6R1jKhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:44:45.527352Z"},"content_sha256":"638f7bbbd8294a1eb78153e964e60bb5018b36e9f989e4f543502f9d68288d91","schema_version":"1.0","event_id":"sha256:638f7bbbd8294a1eb78153e964e60bb5018b36e9f989e4f543502f9d68288d91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XRQACSIDCF5EX4YKLFIRJDDIGI/bundle.json","state_url":"https://pith.science/pith/XRQACSIDCF5EX4YKLFIRJDDIGI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XRQACSIDCF5EX4YKLFIRJDDIGI/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":"2026-05-25T09:44:45Z","links":{"resolver":"https://pith.science/pith/XRQACSIDCF5EX4YKLFIRJDDIGI","bundle":"https://pith.science/pith/XRQACSIDCF5EX4YKLFIRJDDIGI/bundle.json","state":"https://pith.science/pith/XRQACSIDCF5EX4YKLFIRJDDIGI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XRQACSIDCF5EX4YKLFIRJDDIGI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XRQACSIDCF5EX4YKLFIRJDDIGI","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":"470c0c1e38bc9aa0c28c3be64a3d2ea51a6b022a2e6ab04a56a41a8ff42d626b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T20:17:34Z","title_canon_sha256":"e05b263cd6a098d69c689be231fd365beee6dbb73692541a56ab2a67714693c3"},"schema_version":"1.0","source":{"id":"2605.16608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16608","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16608v1","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16608","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"XRQACSIDCF5E","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"XRQACSIDCF5EX4YK","created_at":"2026-05-20T00:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"XRQACSID","created_at":"2026-05-20T00:02:32Z"}],"graph_snapshots":[{"event_id":"sha256:638f7bbbd8294a1eb78153e964e60bb5018b36e9f989e4f543502f9d68288d91","target":"graph","created_at":"2026-05-20T00:02:32Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:21:56.795392Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.596234Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16608/integrity.json","findings":[],"snapshot_sha256":"bbf7ae18c0d74537f9d8c32fe72d92a12aaabdf954327ebf775168dcbb1bdc9a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Matryoshka Representation Learning (MRL) is a widely adopted approach for training text encoders so they provide useful text representations at various sizes, available by simply truncating the resulting vectors at sizes pre-determined at training time. Recent works have shown that randomly truncating text embeddings has minimal impact in downstream performance unless vectors are reduced in size by at least 70%, suggesting that embeddings are already robust to truncation without the use of MRL. However, no prior work has compared random truncation to MRL, so it is unclear how the two methods c","authors_text":"Daniel Ruffinelli, Simone Paolo Ponzetto, Sotaro Takeshita, Yurina Takeshita","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T20:17:34Z","title":"To MRL or not to MRL: Text Embeddings are Robust to Truncation Without Matryoshka Embeddings, Except In Heavy Truncation Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16608","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":"sha256:7376c2524b0b4b5ebb2cf501542b483db9ec64626e4dd54ad9fb5f179f3cc41e","target":"record","created_at":"2026-05-20T00:02:32Z","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":"470c0c1e38bc9aa0c28c3be64a3d2ea51a6b022a2e6ab04a56a41a8ff42d626b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T20:17:34Z","title_canon_sha256":"e05b263cd6a098d69c689be231fd365beee6dbb73692541a56ab2a67714693c3"},"schema_version":"1.0","source":{"id":"2605.16608","kind":"arxiv","version":1}},"canonical_sha256":"bc60014903117a4bf30a5951148c683239c9056263afe73edbe2c1e9e4376cf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc60014903117a4bf30a5951148c683239c9056263afe73edbe2c1e9e4376cf9","first_computed_at":"2026-05-20T00:02:32.278539Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:32.278539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rdEPWvEGqjIW4t8dyLNq5pFLXJgH5CbJfmvNRjgLuJQoJawSrCfu22YuC7jRmh1cAeTKY7dEgaUPE7+tOLjDAw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:32.279449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7376c2524b0b4b5ebb2cf501542b483db9ec64626e4dd54ad9fb5f179f3cc41e","sha256:638f7bbbd8294a1eb78153e964e60bb5018b36e9f989e4f543502f9d68288d91"],"state_sha256":"c38bc8bb5c10fe5179471d3b0c634df82e7601335cf5ff0d26a9de54bbaa0910"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBAhoGkjUJTB9Ty9WlLGimZl7yKq7ZfYEkZZ88wWCB9y6TdsGm9PgfrF1Y61qnRJuqs3EbQ7HgxJod1eL5rSBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T09:44:45.531188Z","bundle_sha256":"3305c4b43d0546c016ff7f2ef654e3f7235a1e23ed60ab43538b398f12a5b26f"}}