{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YPQAQ2DR5KCDNLSRA7SQQYSNRC","short_pith_number":"pith:YPQAQ2DR","canonical_record":{"source":{"id":"2501.15754","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T03:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"63c0f955c74172b8e13d39aef4c38ca849d78ccbbc1aa376accdcd4ec39dd927","abstract_canon_sha256":"f699439a38640a9a99754229bc96d6a91de532e21e102beb3edfaedf28e1ab58"},"schema_version":"1.0"},"canonical_sha256":"c3e0086871ea8436ae5107e508624d88843dc8ed84372ac4602f6b54c2c12693","source":{"kind":"arxiv","id":"2501.15754","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15754","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15754v3","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15754","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"pith_short_12","alias_value":"YPQAQ2DR5KCD","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"pith_short_16","alias_value":"YPQAQ2DR5KCDNLSR","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"pith_short_8","alias_value":"YPQAQ2DR","created_at":"2026-07-05T10:11:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YPQAQ2DR5KCDNLSRA7SQQYSNRC","target":"record","payload":{"canonical_record":{"source":{"id":"2501.15754","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T03:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"63c0f955c74172b8e13d39aef4c38ca849d78ccbbc1aa376accdcd4ec39dd927","abstract_canon_sha256":"f699439a38640a9a99754229bc96d6a91de532e21e102beb3edfaedf28e1ab58"},"schema_version":"1.0"},"canonical_sha256":"c3e0086871ea8436ae5107e508624d88843dc8ed84372ac4602f6b54c2c12693","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:32.304785Z","signature_b64":"8WBzVgiA7PtHQIp4xf9Y9A2UnPEIt+8dAvyxubzYQ067FnSkiewe4R/sGYj175KnJWOVabtqaRSMZR/Sd4TECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e0086871ea8436ae5107e508624d88843dc8ed84372ac4602f6b54c2c12693","last_reissued_at":"2026-07-05T10:11:32.304278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:32.304278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.15754","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:11:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pCWGsqdqOezfsvlQi5Uf/9GK4oKmCkTIzOoRht2034nhGl4Y7MME8pFv3Szrd/V5lMb4v7XLNOxw4U+42KfsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:54:29.714667Z"},"content_sha256":"85ec02b0382e8d9eae64a5a264e5e17b985c28e223b0159a1e82ca4dacc52fec","schema_version":"1.0","event_id":"sha256:85ec02b0382e8d9eae64a5a264e5e17b985c28e223b0159a1e82ca4dacc52fec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YPQAQ2DR5KCDNLSRA7SQQYSNRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Heinzerling, Go kamoda, Keisuke Sakaguchi, Keito Kudo, Kentaro Inui, Tatsuro Inaba","submitted_at":"2025-01-27T03:45:29Z","abstract_excerpt":"According to the stages-of-inference hypothesis, early layers of language models map their subword-tokenized input, which does not necessarily correspond to a linguistically meaningful segmentation, to more meaningful representations that form the model's \"inner vocabulary\". Prior analysis of this detokenization stage has predominantly relied on probing and interventions such as path patching, which involve selecting particular inputs, choosing a subset of components that will be patched, and then observing changes in model behavior. Here, we show that several important aspects of the detokeni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15754","kind":"arxiv","version":3},"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/2501.15754/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":"2026-07-05T10:11:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wZI9n8sD1Wb7NdzKJ9t/UcRSOs89kHJ7Z+EXtM+01ycnKFYUyv7emFrSOLDwYbejHElSJp1bUn5y9ptN83rFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:54:29.715176Z"},"content_sha256":"f5f774b897c4c8f72c2794d89a18a3e61b0f8fc3282681c791fcc552d74ce53e","schema_version":"1.0","event_id":"sha256:f5f774b897c4c8f72c2794d89a18a3e61b0f8fc3282681c791fcc552d74ce53e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YPQAQ2DR5KCDNLSRA7SQQYSNRC/bundle.json","state_url":"https://pith.science/pith/YPQAQ2DR5KCDNLSRA7SQQYSNRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YPQAQ2DR5KCDNLSRA7SQQYSNRC/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":"2026-08-11T02:54:29Z","links":{"resolver":"https://pith.science/pith/YPQAQ2DR5KCDNLSRA7SQQYSNRC","bundle":"https://pith.science/pith/YPQAQ2DR5KCDNLSRA7SQQYSNRC/bundle.json","state":"https://pith.science/pith/YPQAQ2DR5KCDNLSRA7SQQYSNRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YPQAQ2DR5KCDNLSRA7SQQYSNRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YPQAQ2DR5KCDNLSRA7SQQYSNRC","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":"f699439a38640a9a99754229bc96d6a91de532e21e102beb3edfaedf28e1ab58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T03:45:29Z","title_canon_sha256":"63c0f955c74172b8e13d39aef4c38ca849d78ccbbc1aa376accdcd4ec39dd927"},"schema_version":"1.0","source":{"id":"2501.15754","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15754","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15754v3","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15754","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"pith_short_12","alias_value":"YPQAQ2DR5KCD","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"pith_short_16","alias_value":"YPQAQ2DR5KCDNLSR","created_at":"2026-07-05T10:11:32Z"},{"alias_kind":"pith_short_8","alias_value":"YPQAQ2DR","created_at":"2026-07-05T10:11:32Z"}],"graph_snapshots":[{"event_id":"sha256:f5f774b897c4c8f72c2794d89a18a3e61b0f8fc3282681c791fcc552d74ce53e","target":"graph","created_at":"2026-07-05T10:11:32Z","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":[],"endpoint":"/pith/2501.15754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"According to the stages-of-inference hypothesis, early layers of language models map their subword-tokenized input, which does not necessarily correspond to a linguistically meaningful segmentation, to more meaningful representations that form the model's \"inner vocabulary\". Prior analysis of this detokenization stage has predominantly relied on probing and interventions such as path patching, which involve selecting particular inputs, choosing a subset of components that will be patched, and then observing changes in model behavior. Here, we show that several important aspects of the detokeni","authors_text":"Benjamin Heinzerling, Go kamoda, Keisuke Sakaguchi, Keito Kudo, Kentaro Inui, Tatsuro Inaba","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T03:45:29Z","title":"Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15754","kind":"arxiv","version":3},"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":"sha256:85ec02b0382e8d9eae64a5a264e5e17b985c28e223b0159a1e82ca4dacc52fec","target":"record","created_at":"2026-07-05T10:11:32Z","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":"f699439a38640a9a99754229bc96d6a91de532e21e102beb3edfaedf28e1ab58","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T03:45:29Z","title_canon_sha256":"63c0f955c74172b8e13d39aef4c38ca849d78ccbbc1aa376accdcd4ec39dd927"},"schema_version":"1.0","source":{"id":"2501.15754","kind":"arxiv","version":3}},"canonical_sha256":"c3e0086871ea8436ae5107e508624d88843dc8ed84372ac4602f6b54c2c12693","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3e0086871ea8436ae5107e508624d88843dc8ed84372ac4602f6b54c2c12693","first_computed_at":"2026-07-05T10:11:32.304278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:32.304278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8WBzVgiA7PtHQIp4xf9Y9A2UnPEIt+8dAvyxubzYQ067FnSkiewe4R/sGYj175KnJWOVabtqaRSMZR/Sd4TECg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:32.304785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15754","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85ec02b0382e8d9eae64a5a264e5e17b985c28e223b0159a1e82ca4dacc52fec","sha256:f5f774b897c4c8f72c2794d89a18a3e61b0f8fc3282681c791fcc552d74ce53e"],"state_sha256":"a4de8410f68caf2da2e9344bd39298ebd5ec6b9aff0c1bf24953f5dbca62c083"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ACfeOC/iYRBUiIyho6x75QcYxbaczA09uQ52EN34phF13Yuxk5PF0xv1azHQM148RVoAFq82T7Hw6fS/MC8JDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:54:29.721158Z","bundle_sha256":"b3130401ff8b7950f744a562e76aeb3ea877e8cc56fd552149ebbe87eaa63889"}}