{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NTGWAWUKTPFQDJAM4WWGLQFIUY","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":"856b412c1504acca0d7140841cff81de710a0f5959a896dc787d92f3026b6314","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T09:12:20Z","title_canon_sha256":"f2652a3b2e4927057d96fc61e8f09276f6c6add5bb1d5e08018506beecc0a6f7"},"schema_version":"1.0","source":{"id":"2405.12617","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12617","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12617v2","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12617","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_12","alias_value":"NTGWAWUKTPFQ","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_16","alias_value":"NTGWAWUKTPFQDJAM","created_at":"2026-07-05T09:50:47Z"},{"alias_kind":"pith_short_8","alias_value":"NTGWAWUK","created_at":"2026-07-05T09:50:47Z"}],"graph_snapshots":[{"event_id":"sha256:8af865ce360411627fa6561ade9b2afe9caa2522bf64941bb81767aa61bb22a4","target":"graph","created_at":"2026-07-05T09:50:47Z","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/2405.12617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are widely recognized for their exceptional capacity to capture semantics meaning. Yet, there remains no established metric to quantify this capability. In this work, we introduce a quantitative metric, Information Emergence (IE), designed to measure LLMs' ability to extract semantics from input tokens. We formalize ``semantics'' as the meaningful information abstracted from a sequence of tokens and quantify this by comparing the entropy reduction observed for a sequence of tokens (macro-level) and individual tokens (micro-level). To achieve this, we design a light","authors_text":"Hang Chen, Jiaying Zhu, Wenya Wang, Xinyu Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T09:12:20Z","title":"Quantifying Semantic Emergence in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12617","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:bad2a95d17e844fc2d24469fd3546f85a49ed2e04504d643e95d8b2bb8c76cbc","target":"record","created_at":"2026-07-05T09:50:47Z","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":"856b412c1504acca0d7140841cff81de710a0f5959a896dc787d92f3026b6314","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T09:12:20Z","title_canon_sha256":"f2652a3b2e4927057d96fc61e8f09276f6c6add5bb1d5e08018506beecc0a6f7"},"schema_version":"1.0","source":{"id":"2405.12617","kind":"arxiv","version":2}},"canonical_sha256":"6ccd605a8a9bcb01a40ce5ac65c0a8a61bedb70cc1d9ab141241dce075c14aa9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ccd605a8a9bcb01a40ce5ac65c0a8a61bedb70cc1d9ab141241dce075c14aa9","first_computed_at":"2026-07-05T09:50:47.529074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:47.529074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RBE1rg3VOOAvK6ot6PAJDmETjc1e2W1a29zYybmHn+TxL3vuHDNg37OrfTwqqUX9PknwRtFvLWs4VfRvRDVBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:47.529633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12617","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bad2a95d17e844fc2d24469fd3546f85a49ed2e04504d643e95d8b2bb8c76cbc","sha256:8af865ce360411627fa6561ade9b2afe9caa2522bf64941bb81767aa61bb22a4"],"state_sha256":"f2cc7db9496dd96e6a659380b50c600ed1d7e82e6035be10015c5701c1e6c464"}