{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RUXGNLKLUBICZL3KAEJK73YENE","short_pith_number":"pith:RUXGNLKL","canonical_record":{"source":{"id":"2305.16349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T19:10:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"042edaf26ecab6307e86ff824ef9a1fa85ac4202790ae73b513b52ac84d26f77","abstract_canon_sha256":"81edf1b99bd6e1278991f3d37cd2e49a0280a93bf8446d6a76c0089c5e29397e"},"schema_version":"1.0"},"canonical_sha256":"8d2e66ad4ba0502caf6a0112afef046910826ecefea3902e5b2ca5def35ce41c","source":{"kind":"arxiv","id":"2305.16349","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16349","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16349v1","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16349","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"pith_short_12","alias_value":"RUXGNLKLUBIC","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"pith_short_16","alias_value":"RUXGNLKLUBICZL3K","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"pith_short_8","alias_value":"RUXGNLKL","created_at":"2026-07-05T06:14:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RUXGNLKLUBICZL3KAEJK73YENE","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T19:10:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"042edaf26ecab6307e86ff824ef9a1fa85ac4202790ae73b513b52ac84d26f77","abstract_canon_sha256":"81edf1b99bd6e1278991f3d37cd2e49a0280a93bf8446d6a76c0089c5e29397e"},"schema_version":"1.0"},"canonical_sha256":"8d2e66ad4ba0502caf6a0112afef046910826ecefea3902e5b2ca5def35ce41c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:12.117532Z","signature_b64":"NJxpRp1nKiqjdwygY9R/mtbsW03QsFyRhI1v3GWi08y/1v0qySl8kh2GXcVDPpEZ96/rxdvAAAIxle3BuzhICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d2e66ad4ba0502caf6a0112afef046910826ecefea3902e5b2ca5def35ce41c","last_reissued_at":"2026-07-05T06:14:12.117200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:12.117200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16349","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":"2026-07-05T06:14:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ys2CgD4iAMyxSJrP/By41yw7kIb1KzMGPdNaketyX/AtiE8R+87l9dqYNGYg61Hbk5N7qovI/Hg48f28DUl4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:16:09.499821Z"},"content_sha256":"c90beae73f721ff72f97c5800351f61a14f6e4c418966bb9c083926bf14f5e3e","schema_version":"1.0","event_id":"sha256:c90beae73f721ff72f97c5800351f61a14f6e4c418966bb9c083926bf14f5e3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RUXGNLKLUBICZL3KAEJK73YENE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lexinvariant Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eric Zelikman, Gregory Valiant, Percy Liang, Qian Huang, Sarah Li Chen, Yuhuai Wu","submitted_at":"2023-05-24T19:10:46Z","abstract_excerpt":"Token embeddings, a mapping from discrete lexical symbols to continuous vectors, are at the heart of any language model (LM). However, lexical symbol meanings can also be determined and even redefined by their structural role in a long context. In this paper, we ask: is it possible for a language model to be performant without \\emph{any} fixed token embeddings? Such a language model would have to rely entirely on the co-occurence and repetition of tokens in the context rather than the \\textit{a priori} identity of any token. To answer this, we study \\textit{lexinvariant}language models that ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16349","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/2305.16349/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":"2026-07-05T06:14:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dKH0Gh3LArCrpB8TsNdnPSnvZlzqBDUqFyHlmJwc2VyVYXm02lFUW07spwcMs6Gz8XjEg/PzewJbnz/J2us/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:16:09.500412Z"},"content_sha256":"12229de94dc621797d9bb45cd5cb319c2b6ac8ef0f61108926d65d27bab06951","schema_version":"1.0","event_id":"sha256:12229de94dc621797d9bb45cd5cb319c2b6ac8ef0f61108926d65d27bab06951"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUXGNLKLUBICZL3KAEJK73YENE/bundle.json","state_url":"https://pith.science/pith/RUXGNLKLUBICZL3KAEJK73YENE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUXGNLKLUBICZL3KAEJK73YENE/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":"2026-08-12T11:16:09Z","links":{"resolver":"https://pith.science/pith/RUXGNLKLUBICZL3KAEJK73YENE","bundle":"https://pith.science/pith/RUXGNLKLUBICZL3KAEJK73YENE/bundle.json","state":"https://pith.science/pith/RUXGNLKLUBICZL3KAEJK73YENE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUXGNLKLUBICZL3KAEJK73YENE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RUXGNLKLUBICZL3KAEJK73YENE","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":"81edf1b99bd6e1278991f3d37cd2e49a0280a93bf8446d6a76c0089c5e29397e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T19:10:46Z","title_canon_sha256":"042edaf26ecab6307e86ff824ef9a1fa85ac4202790ae73b513b52ac84d26f77"},"schema_version":"1.0","source":{"id":"2305.16349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16349","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16349v1","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16349","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"pith_short_12","alias_value":"RUXGNLKLUBIC","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"pith_short_16","alias_value":"RUXGNLKLUBICZL3K","created_at":"2026-07-05T06:14:12Z"},{"alias_kind":"pith_short_8","alias_value":"RUXGNLKL","created_at":"2026-07-05T06:14:12Z"}],"graph_snapshots":[{"event_id":"sha256:12229de94dc621797d9bb45cd5cb319c2b6ac8ef0f61108926d65d27bab06951","target":"graph","created_at":"2026-07-05T06:14:12Z","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/2305.16349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Token embeddings, a mapping from discrete lexical symbols to continuous vectors, are at the heart of any language model (LM). However, lexical symbol meanings can also be determined and even redefined by their structural role in a long context. In this paper, we ask: is it possible for a language model to be performant without \\emph{any} fixed token embeddings? Such a language model would have to rely entirely on the co-occurence and repetition of tokens in the context rather than the \\textit{a priori} identity of any token. To answer this, we study \\textit{lexinvariant}language models that ar","authors_text":"Eric Zelikman, Gregory Valiant, Percy Liang, Qian Huang, Sarah Li Chen, Yuhuai Wu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T19:10:46Z","title":"Lexinvariant Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16349","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:c90beae73f721ff72f97c5800351f61a14f6e4c418966bb9c083926bf14f5e3e","target":"record","created_at":"2026-07-05T06:14:12Z","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":"81edf1b99bd6e1278991f3d37cd2e49a0280a93bf8446d6a76c0089c5e29397e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T19:10:46Z","title_canon_sha256":"042edaf26ecab6307e86ff824ef9a1fa85ac4202790ae73b513b52ac84d26f77"},"schema_version":"1.0","source":{"id":"2305.16349","kind":"arxiv","version":1}},"canonical_sha256":"8d2e66ad4ba0502caf6a0112afef046910826ecefea3902e5b2ca5def35ce41c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d2e66ad4ba0502caf6a0112afef046910826ecefea3902e5b2ca5def35ce41c","first_computed_at":"2026-07-05T06:14:12.117200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:12.117200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NJxpRp1nKiqjdwygY9R/mtbsW03QsFyRhI1v3GWi08y/1v0qySl8kh2GXcVDPpEZ96/rxdvAAAIxle3BuzhICg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:12.117532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c90beae73f721ff72f97c5800351f61a14f6e4c418966bb9c083926bf14f5e3e","sha256:12229de94dc621797d9bb45cd5cb319c2b6ac8ef0f61108926d65d27bab06951"],"state_sha256":"23a101fa70c7462f18e383909d70322f832bb992d3a4d2678e3f4bc08eed6d0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tC0kUxX6GP9eTspHj53/G2b+LhrIejNfhagwPo6mGbVrJxIdde+CNkBRoMyECzwOrAmMbm9jcv+igNDjqd3TBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T11:16:09.505623Z","bundle_sha256":"691d92318fe9d588810b25fafbee615a6d17be3e85a9fa9d0da246293ff322d9"}}