{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VRLTH6YKRQHEUJ7J5JH5QHJSGX","short_pith_number":"pith:VRLTH6YK","canonical_record":{"source":{"id":"2608.08139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T13:56:39Z","cross_cats_sorted":[],"title_canon_sha256":"7e8085b6331c4a03a06eb0708ad6d0aeb7c20bf271e5a1aeaf27a4c119208803","abstract_canon_sha256":"8c685bb8ca6f80027c4ffff8971a631bcc5b1b0752a2170c1b00b19ec9f7f94c"},"schema_version":"1.0"},"canonical_sha256":"ac5733fb0a8c0e4a27e9ea4fd81d3235f585149e7e9562e435559dc8eaf3fee0","source":{"kind":"arxiv","id":"2608.08139","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08139","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08139v1","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08139","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"pith_short_12","alias_value":"VRLTH6YKRQHE","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"pith_short_16","alias_value":"VRLTH6YKRQHEUJ7J","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"pith_short_8","alias_value":"VRLTH6YK","created_at":"2026-08-11T01:21:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VRLTH6YKRQHEUJ7J5JH5QHJSGX","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T13:56:39Z","cross_cats_sorted":[],"title_canon_sha256":"7e8085b6331c4a03a06eb0708ad6d0aeb7c20bf271e5a1aeaf27a4c119208803","abstract_canon_sha256":"8c685bb8ca6f80027c4ffff8971a631bcc5b1b0752a2170c1b00b19ec9f7f94c"},"schema_version":"1.0"},"canonical_sha256":"ac5733fb0a8c0e4a27e9ea4fd81d3235f585149e7e9562e435559dc8eaf3fee0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:21:48.065658Z","signature_b64":"9iDgYcsVi4F6elzq7f7F2IDG7ofnehBbay6QF/R99ZOvyaYaw5/C0bDLZ8v9RFKw04DSrY6hRm/feHOgMIngCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac5733fb0a8c0e4a27e9ea4fd81d3235f585149e7e9562e435559dc8eaf3fee0","last_reissued_at":"2026-08-11T01:21:48.062889Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:21:48.062889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08139","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":"2026-08-11T01:21:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lm54hMbI/gGySZ7vmnqaIiMvatMBt2pyWvN/XSXEKO/Mj7t0qri1ZIDNwFdkqyNGX6836tIfW5t2STNoVsLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:02:14.394881Z"},"content_sha256":"1e2daa526ff04b5629806d4a8ccff7957347ecab5a5851d61d86c8d5a3ac18ba","schema_version":"1.0","event_id":"sha256:1e2daa526ff04b5629806d4a8ccff7957347ecab5a5851d61d86c8d5a3ac18ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VRLTH6YKRQHEUJ7J5JH5QHJSGX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Chen, Shengming Zhao, Yuqi Wu","submitted_at":"2026-08-08T13:56:39Z","abstract_excerpt":"Establishing the provenance of a language model---including its base checkpoint and possible overlap in training distributions---is a governance challenge that metadata alone cannot resolve. We introduce a training-free fingerprint based on the top-$k$ vocabulary projections of late hidden states elicited by 250 fixed knowledge probes, compared using Jaccard overlap over decoded token strings. We evaluate the method on 32 open-weight models from nine families (0.6B--32B) with documented relationships. (1)~A \\emph{similarity ladder} broadly follows model relatedness: independently trained model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08139","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/2608.08139/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":"2026-08-11T01:21:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PCB9Bx/luqtOTHRSK4B5s06VC8j0ynmJny3cU4TLZsRnL6lH9TpXtZqcj9uvXkeoB2l6tYch7STxhXMEuhbtCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:02:14.395815Z"},"content_sha256":"17208d7b6f9d5c9017372da7962cc1144d03f5caa9a7b5f5bce3ee16b1a4d928","schema_version":"1.0","event_id":"sha256:17208d7b6f9d5c9017372da7962cc1144d03f5caa9a7b5f5bce3ee16b1a4d928"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VRLTH6YKRQHEUJ7J5JH5QHJSGX/bundle.json","state_url":"https://pith.science/pith/VRLTH6YKRQHEUJ7J5JH5QHJSGX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VRLTH6YKRQHEUJ7J5JH5QHJSGX/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":"2026-08-17T05:02:14Z","links":{"resolver":"https://pith.science/pith/VRLTH6YKRQHEUJ7J5JH5QHJSGX","bundle":"https://pith.science/pith/VRLTH6YKRQHEUJ7J5JH5QHJSGX/bundle.json","state":"https://pith.science/pith/VRLTH6YKRQHEUJ7J5JH5QHJSGX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VRLTH6YKRQHEUJ7J5JH5QHJSGX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VRLTH6YKRQHEUJ7J5JH5QHJSGX","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":"8c685bb8ca6f80027c4ffff8971a631bcc5b1b0752a2170c1b00b19ec9f7f94c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T13:56:39Z","title_canon_sha256":"7e8085b6331c4a03a06eb0708ad6d0aeb7c20bf271e5a1aeaf27a4c119208803"},"schema_version":"1.0","source":{"id":"2608.08139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08139","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08139v1","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08139","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"pith_short_12","alias_value":"VRLTH6YKRQHE","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"pith_short_16","alias_value":"VRLTH6YKRQHEUJ7J","created_at":"2026-08-11T01:21:48Z"},{"alias_kind":"pith_short_8","alias_value":"VRLTH6YK","created_at":"2026-08-11T01:21:48Z"}],"graph_snapshots":[{"event_id":"sha256:17208d7b6f9d5c9017372da7962cc1144d03f5caa9a7b5f5bce3ee16b1a4d928","target":"graph","created_at":"2026-08-11T01:21:48Z","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/2608.08139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Establishing the provenance of a language model---including its base checkpoint and possible overlap in training distributions---is a governance challenge that metadata alone cannot resolve. We introduce a training-free fingerprint based on the top-$k$ vocabulary projections of late hidden states elicited by 250 fixed knowledge probes, compared using Jaccard overlap over decoded token strings. We evaluate the method on 32 open-weight models from nine families (0.6B--32B) with documented relationships. (1)~A \\emph{similarity ladder} broadly follows model relatedness: independently trained model","authors_text":"Jie Chen, Shengming Zhao, Yuqi Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T13:56:39Z","title":"TokenPrint: A Calibrated Token-Space Fingerprint for Language-Model Provenance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08139","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":"sha256:1e2daa526ff04b5629806d4a8ccff7957347ecab5a5851d61d86c8d5a3ac18ba","target":"record","created_at":"2026-08-11T01:21:48Z","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":"8c685bb8ca6f80027c4ffff8971a631bcc5b1b0752a2170c1b00b19ec9f7f94c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T13:56:39Z","title_canon_sha256":"7e8085b6331c4a03a06eb0708ad6d0aeb7c20bf271e5a1aeaf27a4c119208803"},"schema_version":"1.0","source":{"id":"2608.08139","kind":"arxiv","version":1}},"canonical_sha256":"ac5733fb0a8c0e4a27e9ea4fd81d3235f585149e7e9562e435559dc8eaf3fee0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac5733fb0a8c0e4a27e9ea4fd81d3235f585149e7e9562e435559dc8eaf3fee0","first_computed_at":"2026-08-11T01:21:48.062889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:21:48.062889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9iDgYcsVi4F6elzq7f7F2IDG7ofnehBbay6QF/R99ZOvyaYaw5/C0bDLZ8v9RFKw04DSrY6hRm/feHOgMIngCw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:21:48.065658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e2daa526ff04b5629806d4a8ccff7957347ecab5a5851d61d86c8d5a3ac18ba","sha256:17208d7b6f9d5c9017372da7962cc1144d03f5caa9a7b5f5bce3ee16b1a4d928"],"state_sha256":"57a10e4b61c96be2450b92f525a3bb6b38835926af555e66bf9f7844eaf14dd7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMAm6Id+9dHPMiQac89caKRfrDvBzbH/2by8hIhWfBtcp788Oyp2O37mE+Fa3v6ErKP7YWqo41MTUXDwzIUaCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T05:02:14.400979Z","bundle_sha256":"0638c8904aadb70c40599ba7d425f42456ef1d9faf3d1e0e7d65f8e2f2ceab72"}}