{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DBMLSCO4KWZG3U535XQUCRZUL5","short_pith_number":"pith:DBMLSCO4","canonical_record":{"source":{"id":"2606.10375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T03:36:31Z","cross_cats_sorted":[],"title_canon_sha256":"54bbfc47fa2a795b9f3350f13b5eec5175f091061f1202e1428d2b87512147c0","abstract_canon_sha256":"6bfd1a8bbf7ae54be5614afa9438612b65b218928eca9e30a17d67b2cdf8047f"},"schema_version":"1.0"},"canonical_sha256":"1858b909dc55b26dd3bbede14147345f465920a44a4dc685b4dcf64d52ff1d39","source":{"kind":"arxiv","id":"2606.10375","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10375","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10375v1","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10375","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"DBMLSCO4KWZG","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_16","alias_value":"DBMLSCO4KWZG3U53","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_8","alias_value":"DBMLSCO4","created_at":"2026-06-10T01:10:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DBMLSCO4KWZG3U535XQUCRZUL5","target":"record","payload":{"canonical_record":{"source":{"id":"2606.10375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T03:36:31Z","cross_cats_sorted":[],"title_canon_sha256":"54bbfc47fa2a795b9f3350f13b5eec5175f091061f1202e1428d2b87512147c0","abstract_canon_sha256":"6bfd1a8bbf7ae54be5614afa9438612b65b218928eca9e30a17d67b2cdf8047f"},"schema_version":"1.0"},"canonical_sha256":"1858b909dc55b26dd3bbede14147345f465920a44a4dc685b4dcf64d52ff1d39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:14.566759Z","signature_b64":"uq93J6WCr0RRXoBLPXJ3c9qY4ondZgbRSSZ/rSGmEKc57UlTupyP7RPDHPKjBrELS4lXhk/NdCBvgU5tH38ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1858b909dc55b26dd3bbede14147345f465920a44a4dc685b4dcf64d52ff1d39","last_reissued_at":"2026-06-10T01:10:14.566341Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:14.566341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.10375","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":"2026-06-10T01:10:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBJyYKWrO5gjdK5nyg9ei4P3dAG8Oc7C5TU7J2Tzc7HRw+KD/N6VFU+N6cqCyydga4xfc9UHxvB8M5UiC0nHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T23:59:35.982458Z"},"content_sha256":"243a471c66535ac389bbab8e1ab333fae2b9e15eb744a7f0a677038d686f8075","schema_version":"1.0","event_id":"sha256:243a471c66535ac389bbab8e1ab333fae2b9e15eb744a7f0a677038d686f8075"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DBMLSCO4KWZG3U535XQUCRZUL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Heng Chang, Huijie Qin, Jiandong Ding, Tianying Liu","submitted_at":"2026-06-09T03:36:31Z","abstract_excerpt":"Semantic-ID (\\sid) tokenizers are increasingly reused as standalone artifacts in generative recommendation: an exported item-to-code mapping becomes the address space that a later sequence generator must use. These mappings rarely come with a common inspection interface, so coverage gaps, full-code aliasing, behaviorally weak prefixes, tail compression, and prefix fan-out are often found only after downstream training. We present \\tool, a mapping-first diagnostic resource for \\sid tokenizer artifacts. \\tool defines a small adapter contract over item mappings, metadata, interactions, and option"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10375","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/2606.10375/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":"2026-06-10T01:10:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3jb35P2JBPGElUYcOUP2YPx0esrbhbc9pAnWN5rGyyXCtPmyvq1E2TmdKDoXVqkoIzufs7IsvK7RYSLEcZ+FCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T23:59:35.982815Z"},"content_sha256":"801c65d27e570344863a956ae2e0c9583597ea4b8c49fde99cbb92087d08c87a","schema_version":"1.0","event_id":"sha256:801c65d27e570344863a956ae2e0c9583597ea4b8c49fde99cbb92087d08c87a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBMLSCO4KWZG3U535XQUCRZUL5/bundle.json","state_url":"https://pith.science/pith/DBMLSCO4KWZG3U535XQUCRZUL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBMLSCO4KWZG3U535XQUCRZUL5/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":"2026-06-27T23:59:35Z","links":{"resolver":"https://pith.science/pith/DBMLSCO4KWZG3U535XQUCRZUL5","bundle":"https://pith.science/pith/DBMLSCO4KWZG3U535XQUCRZUL5/bundle.json","state":"https://pith.science/pith/DBMLSCO4KWZG3U535XQUCRZUL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBMLSCO4KWZG3U535XQUCRZUL5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DBMLSCO4KWZG3U535XQUCRZUL5","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":"6bfd1a8bbf7ae54be5614afa9438612b65b218928eca9e30a17d67b2cdf8047f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T03:36:31Z","title_canon_sha256":"54bbfc47fa2a795b9f3350f13b5eec5175f091061f1202e1428d2b87512147c0"},"schema_version":"1.0","source":{"id":"2606.10375","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10375","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10375v1","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10375","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"DBMLSCO4KWZG","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_16","alias_value":"DBMLSCO4KWZG3U53","created_at":"2026-06-10T01:10:14Z"},{"alias_kind":"pith_short_8","alias_value":"DBMLSCO4","created_at":"2026-06-10T01:10:14Z"}],"graph_snapshots":[{"event_id":"sha256:801c65d27e570344863a956ae2e0c9583597ea4b8c49fde99cbb92087d08c87a","target":"graph","created_at":"2026-06-10T01:10:14Z","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/2606.10375/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic-ID (\\sid) tokenizers are increasingly reused as standalone artifacts in generative recommendation: an exported item-to-code mapping becomes the address space that a later sequence generator must use. These mappings rarely come with a common inspection interface, so coverage gaps, full-code aliasing, behaviorally weak prefixes, tail compression, and prefix fan-out are often found only after downstream training. We present \\tool, a mapping-first diagnostic resource for \\sid tokenizer artifacts. \\tool defines a small adapter contract over item mappings, metadata, interactions, and option","authors_text":"Heng Chang, Huijie Qin, Jiandong Ding, Tianying Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T03:36:31Z","title":"SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10375","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":"sha256:243a471c66535ac389bbab8e1ab333fae2b9e15eb744a7f0a677038d686f8075","target":"record","created_at":"2026-06-10T01:10:14Z","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":"6bfd1a8bbf7ae54be5614afa9438612b65b218928eca9e30a17d67b2cdf8047f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-09T03:36:31Z","title_canon_sha256":"54bbfc47fa2a795b9f3350f13b5eec5175f091061f1202e1428d2b87512147c0"},"schema_version":"1.0","source":{"id":"2606.10375","kind":"arxiv","version":1}},"canonical_sha256":"1858b909dc55b26dd3bbede14147345f465920a44a4dc685b4dcf64d52ff1d39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1858b909dc55b26dd3bbede14147345f465920a44a4dc685b4dcf64d52ff1d39","first_computed_at":"2026-06-10T01:10:14.566341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:14.566341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uq93J6WCr0RRXoBLPXJ3c9qY4ondZgbRSSZ/rSGmEKc57UlTupyP7RPDHPKjBrELS4lXhk/NdCBvgU5tH38ABA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:14.566759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10375","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243a471c66535ac389bbab8e1ab333fae2b9e15eb744a7f0a677038d686f8075","sha256:801c65d27e570344863a956ae2e0c9583597ea4b8c49fde99cbb92087d08c87a"],"state_sha256":"760aac6c4eb322b343b50bc570c0fa49fcbb42418094d9003836817518e2899c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vauw/FcK1c0OGxcnZzo2ZzFkRV9izUM4uyV9H7LfHkvPxbEfS7uCi+J2BAA5SEiKaQLIuG32NkcJw6r5dk9NBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T23:59:35.984701Z","bundle_sha256":"35788da30ea960a695db4e2bfb100991ce4cc2bc1066dd0029ed2782cb5da4ab"}}