{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K3XWJSBV6RD5YP5JIALC62QDXT","short_pith_number":"pith:K3XWJSBV","canonical_record":{"source":{"id":"2505.12822","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T08:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"f75324cc6e5d262bec79a14aedb1df9a7a364a30150784e2a23b4d346aaa76e5","abstract_canon_sha256":"409a892c9ae6a44b2b2bba22b9e9a57facec956710fe4307cd3c383689a4a62c"},"schema_version":"1.0"},"canonical_sha256":"56ef64c835f447dc3fa940162f6a03bccc0a1084a4b360617d5e6f264471c3ea","source":{"kind":"arxiv","id":"2505.12822","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12822","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12822v2","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12822","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"K3XWJSBV6RD5","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"K3XWJSBV6RD5YP5J","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"K3XWJSBV","created_at":"2026-07-05T11:07:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K3XWJSBV6RD5YP5JIALC62QDXT","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12822","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T08:05:13Z","cross_cats_sorted":[],"title_canon_sha256":"f75324cc6e5d262bec79a14aedb1df9a7a364a30150784e2a23b4d346aaa76e5","abstract_canon_sha256":"409a892c9ae6a44b2b2bba22b9e9a57facec956710fe4307cd3c383689a4a62c"},"schema_version":"1.0"},"canonical_sha256":"56ef64c835f447dc3fa940162f6a03bccc0a1084a4b360617d5e6f264471c3ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:24.952871Z","signature_b64":"yl8GzfaYy+63VsDd9cEijOyl3ARr2RNCa8XT07UhN8qJg/0xQqNW4KNe18HByVZSI5PMSdr99iC8gvKa0UwnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ef64c835f447dc3fa940162f6a03bccc0a1084a4b360617d5e6f264471c3ea","last_reissued_at":"2026-07-05T11:07:24.952331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:24.952331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12822","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"607qsdq8uvvO9uL33cN2LaT3XfvdG6EFq8s086lsRWtJby5Tk0pXXbkBGnGwNWeLtb2NRMpKITej40diqZtsBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:46:52.065902Z"},"content_sha256":"2334eb06afdcc7df5fa9d84a8414c95742e78fa2c149a8566e3dd7192e565c2d","schema_version":"1.0","event_id":"sha256:2334eb06afdcc7df5fa9d84a8414c95742e78fa2c149a8566e3dd7192e565c2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K3XWJSBV6RD5YP5JIALC62QDXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emergent Specialization: Rare Token Neurons in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haozheng Wang, Jing Liu, Yueheng Li","submitted_at":"2025-05-19T08:05:13Z","abstract_excerpt":"Large language models struggle with representing and generating rare tokens despite their importance in specialized domains. In this study, we identify neuron structures with exceptionally strong influence on language model's prediction of rare tokens, termed as rare token neurons, and investigate the mechanism for their emergence and behavior. These neurons exhibit a characteristic three-phase organization (plateau, power-law, and rapid decay) that emerges dynamically during training, evolving from a homogeneous initial state to a functionally differentiated architecture. In the activation sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12822","kind":"arxiv","version":2},"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/2505.12822/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":"2026-07-05T11:07:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PE7HiKcDEPh7zX5B/RUkOOiCCahbstb7srcazpyGKarzj5jUB+QxthyVwn9l2jF0Bt9R54cngJfbcp8V2TKhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:46:52.066287Z"},"content_sha256":"c4f6d15cf0b131baea1daf1e761f0f880c79bd7b6aca8cee11479d4db852f522","schema_version":"1.0","event_id":"sha256:c4f6d15cf0b131baea1daf1e761f0f880c79bd7b6aca8cee11479d4db852f522"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K3XWJSBV6RD5YP5JIALC62QDXT/bundle.json","state_url":"https://pith.science/pith/K3XWJSBV6RD5YP5JIALC62QDXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K3XWJSBV6RD5YP5JIALC62QDXT/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":"2026-08-19T17:46:52Z","links":{"resolver":"https://pith.science/pith/K3XWJSBV6RD5YP5JIALC62QDXT","bundle":"https://pith.science/pith/K3XWJSBV6RD5YP5JIALC62QDXT/bundle.json","state":"https://pith.science/pith/K3XWJSBV6RD5YP5JIALC62QDXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K3XWJSBV6RD5YP5JIALC62QDXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K3XWJSBV6RD5YP5JIALC62QDXT","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":"409a892c9ae6a44b2b2bba22b9e9a57facec956710fe4307cd3c383689a4a62c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T08:05:13Z","title_canon_sha256":"f75324cc6e5d262bec79a14aedb1df9a7a364a30150784e2a23b4d346aaa76e5"},"schema_version":"1.0","source":{"id":"2505.12822","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12822","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12822v2","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12822","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"K3XWJSBV6RD5","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"K3XWJSBV6RD5YP5J","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"K3XWJSBV","created_at":"2026-07-05T11:07:24Z"}],"graph_snapshots":[{"event_id":"sha256:c4f6d15cf0b131baea1daf1e761f0f880c79bd7b6aca8cee11479d4db852f522","target":"graph","created_at":"2026-07-05T11:07:24Z","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/2505.12822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models struggle with representing and generating rare tokens despite their importance in specialized domains. In this study, we identify neuron structures with exceptionally strong influence on language model's prediction of rare tokens, termed as rare token neurons, and investigate the mechanism for their emergence and behavior. These neurons exhibit a characteristic three-phase organization (plateau, power-law, and rapid decay) that emerges dynamically during training, evolving from a homogeneous initial state to a functionally differentiated architecture. In the activation sp","authors_text":"Haozheng Wang, Jing Liu, Yueheng Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T08:05:13Z","title":"Emergent Specialization: Rare Token Neurons in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12822","kind":"arxiv","version":2},"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":"sha256:2334eb06afdcc7df5fa9d84a8414c95742e78fa2c149a8566e3dd7192e565c2d","target":"record","created_at":"2026-07-05T11:07:24Z","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":"409a892c9ae6a44b2b2bba22b9e9a57facec956710fe4307cd3c383689a4a62c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T08:05:13Z","title_canon_sha256":"f75324cc6e5d262bec79a14aedb1df9a7a364a30150784e2a23b4d346aaa76e5"},"schema_version":"1.0","source":{"id":"2505.12822","kind":"arxiv","version":2}},"canonical_sha256":"56ef64c835f447dc3fa940162f6a03bccc0a1084a4b360617d5e6f264471c3ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56ef64c835f447dc3fa940162f6a03bccc0a1084a4b360617d5e6f264471c3ea","first_computed_at":"2026-07-05T11:07:24.952331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:24.952331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yl8GzfaYy+63VsDd9cEijOyl3ARr2RNCa8XT07UhN8qJg/0xQqNW4KNe18HByVZSI5PMSdr99iC8gvKa0UwnAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:24.952871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12822","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2334eb06afdcc7df5fa9d84a8414c95742e78fa2c149a8566e3dd7192e565c2d","sha256:c4f6d15cf0b131baea1daf1e761f0f880c79bd7b6aca8cee11479d4db852f522"],"state_sha256":"dbe0b2dcdffdd3b2948bbf9c5bf3e0a04f7255172c8e5e404a9a447e3a2c7612"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SG8ltfd3MmzEWmp5bFXpfpLs/TzbuJIfAmohIcwcLXDMX4Z5MMJIYLTYX1dwtoyB94/w3AlUoKctdGjiUlRRCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:46:52.069613Z","bundle_sha256":"64ae7338880613b7c8f8014198a012ae69fc1e12f1fadfe88e894af7846a664a"}}