{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WLSDRR76NWI6ZY64UJWRXAR4ZK","short_pith_number":"pith:WLSDRR76","canonical_record":{"source":{"id":"2606.23591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T17:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"a8cbf95cd8978dbb6b8648bb324169e83b32c6fd092ab7849cdeaa41ed0b02ad","abstract_canon_sha256":"8160fc6b18d9482ea2d9861091927b549068cbf863a44f461545dbe069292d4f"},"schema_version":"1.0"},"canonical_sha256":"b2e438c7fe6d91ece3dca26d1b823ccaa7543ea29d9ba6edd785e4c373b67838","source":{"kind":"arxiv","id":"2606.23591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23591","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23591v1","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23591","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"WLSDRR76NWI6","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"WLSDRR76NWI6ZY64","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"WLSDRR76","created_at":"2026-06-23T03:14:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WLSDRR76NWI6ZY64UJWRXAR4ZK","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T17:00:04Z","cross_cats_sorted":[],"title_canon_sha256":"a8cbf95cd8978dbb6b8648bb324169e83b32c6fd092ab7849cdeaa41ed0b02ad","abstract_canon_sha256":"8160fc6b18d9482ea2d9861091927b549068cbf863a44f461545dbe069292d4f"},"schema_version":"1.0"},"canonical_sha256":"b2e438c7fe6d91ece3dca26d1b823ccaa7543ea29d9ba6edd785e4c373b67838","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:31.767242Z","signature_b64":"jHQ7cLfoCHPzEZFe3kf2A5fntb5iev27VYE0QACVOXXkBDyWvCpHI5kmlaWKC5Ahd9sQSa+/eXd3KALtlVmcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2e438c7fe6d91ece3dca26d1b823ccaa7543ea29d9ba6edd785e4c373b67838","last_reissued_at":"2026-06-23T03:14:31.766835Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:31.766835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23591","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":"2026-06-23T03:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gAtBdxM9GjzD05wjjrHIa+vLgQ1M66QwdodIz9mLHgpujlJQv+XxaivGHtUpEX4X5IlwVRV1Zu4B6Ws2kWPwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:24:45.732858Z"},"content_sha256":"3fe2869b7e42c3306d8838507a9dbf2a254fa1bb610d798710531050e6669c3e","schema_version":"1.0","event_id":"sha256:3fe2869b7e42c3306d8838507a9dbf2a254fa1bb610d798710531050e6669c3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WLSDRR76NWI6ZY64UJWRXAR4ZK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christopher J. Anders, Henrique Da Silva Gameiro, Mohammad Emtiyaz Khan, Nico Daheim","submitted_at":"2026-06-22T17:00:04Z","abstract_excerpt":"One way to understand LLM behavior is to trace its output back to the training data. Two types of measures are commonly used for output tracing: data-similarity and data-influence. The former is cheaper while the latter is believed to be more accurate. Even though many works have compared them for ground-truth tasks, no such comparisons exist for output tracing. Here, we fill this gap and precisely quantify the commonalities and differences between the two measures. We do this by first ranking the training documents according to each measure and then computing the overlap between the two ranki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23591","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/2606.23591/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":"2026-06-23T03:14:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4a+v8Dx5VdQr072Urjtbyv8xLPtRwRyscztjDzqkO16ZGNLsfmOOzZmqbtK24Ka1p3E4FDkK+QIWMbKGxY9MBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:24:45.733222Z"},"content_sha256":"a8cb2cc3ae321f609a7907563f9fb43a3e0973f28efd48c0f4b1d76c9fca3659","schema_version":"1.0","event_id":"sha256:a8cb2cc3ae321f609a7907563f9fb43a3e0973f28efd48c0f4b1d76c9fca3659"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WLSDRR76NWI6ZY64UJWRXAR4ZK/bundle.json","state_url":"https://pith.science/pith/WLSDRR76NWI6ZY64UJWRXAR4ZK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WLSDRR76NWI6ZY64UJWRXAR4ZK/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":"2026-06-27T21:24:45Z","links":{"resolver":"https://pith.science/pith/WLSDRR76NWI6ZY64UJWRXAR4ZK","bundle":"https://pith.science/pith/WLSDRR76NWI6ZY64UJWRXAR4ZK/bundle.json","state":"https://pith.science/pith/WLSDRR76NWI6ZY64UJWRXAR4ZK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WLSDRR76NWI6ZY64UJWRXAR4ZK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WLSDRR76NWI6ZY64UJWRXAR4ZK","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":"8160fc6b18d9482ea2d9861091927b549068cbf863a44f461545dbe069292d4f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T17:00:04Z","title_canon_sha256":"a8cbf95cd8978dbb6b8648bb324169e83b32c6fd092ab7849cdeaa41ed0b02ad"},"schema_version":"1.0","source":{"id":"2606.23591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23591","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23591v1","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23591","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_12","alias_value":"WLSDRR76NWI6","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_16","alias_value":"WLSDRR76NWI6ZY64","created_at":"2026-06-23T03:14:31Z"},{"alias_kind":"pith_short_8","alias_value":"WLSDRR76","created_at":"2026-06-23T03:14:31Z"}],"graph_snapshots":[{"event_id":"sha256:a8cb2cc3ae321f609a7907563f9fb43a3e0973f28efd48c0f4b1d76c9fca3659","target":"graph","created_at":"2026-06-23T03:14:31Z","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/2606.23591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One way to understand LLM behavior is to trace its output back to the training data. Two types of measures are commonly used for output tracing: data-similarity and data-influence. The former is cheaper while the latter is believed to be more accurate. Even though many works have compared them for ground-truth tasks, no such comparisons exist for output tracing. Here, we fill this gap and precisely quantify the commonalities and differences between the two measures. We do this by first ranking the training documents according to each measure and then computing the overlap between the two ranki","authors_text":"Christopher J. Anders, Henrique Da Silva Gameiro, Mohammad Emtiyaz Khan, Nico Daheim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T17:00:04Z","title":"Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23591","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":"sha256:3fe2869b7e42c3306d8838507a9dbf2a254fa1bb610d798710531050e6669c3e","target":"record","created_at":"2026-06-23T03:14:31Z","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":"8160fc6b18d9482ea2d9861091927b549068cbf863a44f461545dbe069292d4f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T17:00:04Z","title_canon_sha256":"a8cbf95cd8978dbb6b8648bb324169e83b32c6fd092ab7849cdeaa41ed0b02ad"},"schema_version":"1.0","source":{"id":"2606.23591","kind":"arxiv","version":1}},"canonical_sha256":"b2e438c7fe6d91ece3dca26d1b823ccaa7543ea29d9ba6edd785e4c373b67838","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2e438c7fe6d91ece3dca26d1b823ccaa7543ea29d9ba6edd785e4c373b67838","first_computed_at":"2026-06-23T03:14:31.766835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:31.766835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jHQ7cLfoCHPzEZFe3kf2A5fntb5iev27VYE0QACVOXXkBDyWvCpHI5kmlaWKC5Ahd9sQSa+/eXd3KALtlVmcDQ==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:31.767242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fe2869b7e42c3306d8838507a9dbf2a254fa1bb610d798710531050e6669c3e","sha256:a8cb2cc3ae321f609a7907563f9fb43a3e0973f28efd48c0f4b1d76c9fca3659"],"state_sha256":"7f6e2f81421c73abd8f46199689541f3771a703e8c63622daa04ca4651f7218d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wnFXFAJp2Qwad414nAVMIuEXi82qih8h2hceG+nCf9wU8X0AzOSUE2VHAzX2M5ciUNmVd4vja6fovRe019UUDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T21:24:45.735082Z","bundle_sha256":"c04364c4b1e5cf190a48a2ea63291768c21fd1a777eeff3346fdebf457fa252f"}}