{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SB6SWXTSWPUI75XP5NSDGPNQMY","short_pith_number":"pith:SB6SWXTS","canonical_record":{"source":{"id":"2606.08562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T10:36:20Z","cross_cats_sorted":[],"title_canon_sha256":"d3a8526042700cec6e919bbdae79f2feda50f4cea0d228feefb19b8e32190856","abstract_canon_sha256":"bec15d190a8e67a33b721d596bbb9270011ef1cf2010cfc2b74bbcecd32c2eba"},"schema_version":"1.0"},"canonical_sha256":"907d2b5e72b3e88ff6efeb64333db066358f571575ccac76d09f98336e46f9f6","source":{"kind":"arxiv","id":"2606.08562","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08562","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08562v1","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08562","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"SB6SWXTSWPUI","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"SB6SWXTSWPUI75XP","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"SB6SWXTS","created_at":"2026-06-09T01:05:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SB6SWXTSWPUI75XP5NSDGPNQMY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T10:36:20Z","cross_cats_sorted":[],"title_canon_sha256":"d3a8526042700cec6e919bbdae79f2feda50f4cea0d228feefb19b8e32190856","abstract_canon_sha256":"bec15d190a8e67a33b721d596bbb9270011ef1cf2010cfc2b74bbcecd32c2eba"},"schema_version":"1.0"},"canonical_sha256":"907d2b5e72b3e88ff6efeb64333db066358f571575ccac76d09f98336e46f9f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:40.200572Z","signature_b64":"s0nlyd4D+4X+veAGhYXv+OvcSNSgRCW0N7qDS2wVp5G8K/dR49TeQInjWMxWDdyNoxBxBxByyaaWOg8/RpNGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"907d2b5e72b3e88ff6efeb64333db066358f571575ccac76d09f98336e46f9f6","last_reissued_at":"2026-06-09T01:05:40.200146Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:40.200146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08562","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":"2026-06-09T01:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UBrBjOwe5l/cm1BZryhetIrQWZqfM4uUVnMy6SJQzeAOsncZH7tAFQ+/KcWIxKQveRiscbQJ2GOsevDwHtyOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T12:00:41.121926Z"},"content_sha256":"4578136fdd803fdbf338708138632e60fa9e2781112fea6cc302f9dfe7198590","schema_version":"1.0","event_id":"sha256:4578136fdd803fdbf338708138632e60fa9e2781112fea6cc302f9dfe7198590"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SB6SWXTSWPUI75XP5NSDGPNQMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inside the LLM Word Factory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benzi Busigin, Yuval Pinter","submitted_at":"2026-06-07T10:36:20Z","abstract_excerpt":"Transformer language models process input provided as subword fragments, but natural language semantics usually rely on word-level concepts. Detokenization is the process where models reconcile these two facts, aggregating subwords into word-level representations through their computation. Prior work has found that this takes place mostly in early-to-middle layers, but so far the exact mechanics of the process have not been pinned down. We venture deep into detokenization using activation patching in controlled paired experiments that isolate the contribution of different model components, loc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08562","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/2606.08562/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":"2026-06-09T01:05:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8QLLLK+t2V8JLidrQ+ln1npazN0xpd2WgpsL8D61y/2UPCIN7XXZ00deX72PWKJ1cji+VofZXi4UwZb/xyjABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T12:00:41.122296Z"},"content_sha256":"7752834ab54fe085eee9d7eba01d20791871abe5adcb29c3860441a0178f14dd","schema_version":"1.0","event_id":"sha256:7752834ab54fe085eee9d7eba01d20791871abe5adcb29c3860441a0178f14dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SB6SWXTSWPUI75XP5NSDGPNQMY/bundle.json","state_url":"https://pith.science/pith/SB6SWXTSWPUI75XP5NSDGPNQMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SB6SWXTSWPUI75XP5NSDGPNQMY/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":"2026-06-29T12:00:41Z","links":{"resolver":"https://pith.science/pith/SB6SWXTSWPUI75XP5NSDGPNQMY","bundle":"https://pith.science/pith/SB6SWXTSWPUI75XP5NSDGPNQMY/bundle.json","state":"https://pith.science/pith/SB6SWXTSWPUI75XP5NSDGPNQMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SB6SWXTSWPUI75XP5NSDGPNQMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SB6SWXTSWPUI75XP5NSDGPNQMY","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":"bec15d190a8e67a33b721d596bbb9270011ef1cf2010cfc2b74bbcecd32c2eba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T10:36:20Z","title_canon_sha256":"d3a8526042700cec6e919bbdae79f2feda50f4cea0d228feefb19b8e32190856"},"schema_version":"1.0","source":{"id":"2606.08562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08562","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08562v1","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08562","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_12","alias_value":"SB6SWXTSWPUI","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_16","alias_value":"SB6SWXTSWPUI75XP","created_at":"2026-06-09T01:05:40Z"},{"alias_kind":"pith_short_8","alias_value":"SB6SWXTS","created_at":"2026-06-09T01:05:40Z"}],"graph_snapshots":[{"event_id":"sha256:7752834ab54fe085eee9d7eba01d20791871abe5adcb29c3860441a0178f14dd","target":"graph","created_at":"2026-06-09T01:05:40Z","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/2606.08562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer language models process input provided as subword fragments, but natural language semantics usually rely on word-level concepts. Detokenization is the process where models reconcile these two facts, aggregating subwords into word-level representations through their computation. Prior work has found that this takes place mostly in early-to-middle layers, but so far the exact mechanics of the process have not been pinned down. We venture deep into detokenization using activation patching in controlled paired experiments that isolate the contribution of different model components, loc","authors_text":"Benzi Busigin, Yuval Pinter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T10:36:20Z","title":"Inside the LLM Word Factory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08562","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":"sha256:4578136fdd803fdbf338708138632e60fa9e2781112fea6cc302f9dfe7198590","target":"record","created_at":"2026-06-09T01:05:40Z","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":"bec15d190a8e67a33b721d596bbb9270011ef1cf2010cfc2b74bbcecd32c2eba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T10:36:20Z","title_canon_sha256":"d3a8526042700cec6e919bbdae79f2feda50f4cea0d228feefb19b8e32190856"},"schema_version":"1.0","source":{"id":"2606.08562","kind":"arxiv","version":1}},"canonical_sha256":"907d2b5e72b3e88ff6efeb64333db066358f571575ccac76d09f98336e46f9f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"907d2b5e72b3e88ff6efeb64333db066358f571575ccac76d09f98336e46f9f6","first_computed_at":"2026-06-09T01:05:40.200146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:40.200146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s0nlyd4D+4X+veAGhYXv+OvcSNSgRCW0N7qDS2wVp5G8K/dR49TeQInjWMxWDdyNoxBxBxByyaaWOg8/RpNGDw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:40.200572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4578136fdd803fdbf338708138632e60fa9e2781112fea6cc302f9dfe7198590","sha256:7752834ab54fe085eee9d7eba01d20791871abe5adcb29c3860441a0178f14dd"],"state_sha256":"a1fc8f0ad2a47ce981995c674b044b727638eee92cb4b17ff01b42b2a842dcf6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sdzo9Y/b62H/01ENj1UrywhO6nGUyaZXP01nHVMHQPzFQT2O0DgmNQ288XhaRudJXW0vAAczwdfMn7CiyJfHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T12:00:41.124449Z","bundle_sha256":"ca638ffa05d5e341aea057de6bfbbdeda159e652fae817e78cd2bba152507966"}}