{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NTGWAWUKTPFQDJAM4WWGLQFIUY","short_pith_number":"pith:NTGWAWUK","canonical_record":{"source":{"id":"2405.12617","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T09:12:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f2652a3b2e4927057d96fc61e8f09276f6c6add5bb1d5e08018506beecc0a6f7","abstract_canon_sha256":"856b412c1504acca0d7140841cff81de710a0f5959a896dc787d92f3026b6314"},"schema_version":"1.0"},"canonical_sha256":"6ccd605a8a9bcb01a40ce5ac65c0a8a61bedb70cc1d9ab141241dce075c14aa9","source":{"kind":"arxiv","id":"2405.12617","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NTGWAWUKTPFQDJAM4WWGLQFIUY","target":"record","payload":{"canonical_record":{"source":{"id":"2405.12617","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-21T09:12:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f2652a3b2e4927057d96fc61e8f09276f6c6add5bb1d5e08018506beecc0a6f7","abstract_canon_sha256":"856b412c1504acca0d7140841cff81de710a0f5959a896dc787d92f3026b6314"},"schema_version":"1.0"},"canonical_sha256":"6ccd605a8a9bcb01a40ce5ac65c0a8a61bedb70cc1d9ab141241dce075c14aa9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:47.529633Z","signature_b64":"RBE1rg3VOOAvK6ot6PAJDmETjc1e2W1a29zYybmHn+TxL3vuHDNg37OrfTwqqUX9PknwRtFvLWs4VfRvRDVBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ccd605a8a9bcb01a40ce5ac65c0a8a61bedb70cc1d9ab141241dce075c14aa9","last_reissued_at":"2026-07-05T09:50:47.529074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:47.529074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.12617","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":"2026-07-05T09:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KfT131lZzI0D8nLaRS41UGWk5Scz/kTQjsRAD6K2RjXPaFOg80D5pdAZ8Bh2UXK13MadwjKwqE07tHWpRbGgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:38:35.023520Z"},"content_sha256":"bad2a95d17e844fc2d24469fd3546f85a49ed2e04504d643e95d8b2bb8c76cbc","schema_version":"1.0","event_id":"sha256:bad2a95d17e844fc2d24469fd3546f85a49ed2e04504d643e95d8b2bb8c76cbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NTGWAWUKTPFQDJAM4WWGLQFIUY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying Semantic Emergence in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hang Chen, Jiaying Zhu, Wenya Wang, Xinyu Yang","submitted_at":"2024-05-21T09:12:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12617","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/2405.12617/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":"2026-07-05T09:50:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iRj8iYWzwzlqhsDVyWGyivqf/EY2frybqunO1ytte28WKs8pYTshFryQz4Q7rujzWxVkRqZXoeJ7OEKf4dEWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:38:35.024019Z"},"content_sha256":"8af865ce360411627fa6561ade9b2afe9caa2522bf64941bb81767aa61bb22a4","schema_version":"1.0","event_id":"sha256:8af865ce360411627fa6561ade9b2afe9caa2522bf64941bb81767aa61bb22a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NTGWAWUKTPFQDJAM4WWGLQFIUY/bundle.json","state_url":"https://pith.science/pith/NTGWAWUKTPFQDJAM4WWGLQFIUY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NTGWAWUKTPFQDJAM4WWGLQFIUY/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":"2026-08-08T09:38:35Z","links":{"resolver":"https://pith.science/pith/NTGWAWUKTPFQDJAM4WWGLQFIUY","bundle":"https://pith.science/pith/NTGWAWUKTPFQDJAM4WWGLQFIUY/bundle.json","state":"https://pith.science/pith/NTGWAWUKTPFQDJAM4WWGLQFIUY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NTGWAWUKTPFQDJAM4WWGLQFIUY/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AG37+0KiLzJ0oPhsnrtkkV5nX9vxfreVkMU2ecy3N28RTRtiYlynC0y3hjsPsHkcFxG64w9AyhfqZKcPS0e9Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:38:35.028510Z","bundle_sha256":"ef7549facd109179cd5bcc34058114071f787e62384cb494056419068be9e2b9"}}