{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OEPJHI7M2VW7WQEF34IEXDM4C6","short_pith_number":"pith:OEPJHI7M","schema_version":"1.0","canonical_sha256":"711e93a3ecd56dfb4085df104b8d9c17b453221c4b71ff78eecd0ba1f77ac9b2","source":{"kind":"arxiv","id":"2607.22610","version":1},"attestation_state":"computed","paper":{"title":"Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jessica Tang, Sharad Agarwal, Shraddha Barke","submitted_at":"2026-06-14T17:14:01Z","abstract_excerpt":"When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies propagate across prior turns? Existing context attribution methods process the full context in a single pass, recovering surface-level dependencies but missing the layered, non-linear structure of real-world dialogues and multi-step reasoning tasks. We introduce multi-turn context attribution (MTCA): given a target span in a model response, the task of tracing attribution backward across turns to identify not only which prior turns were direct"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.22610","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-14T17:14:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"59c2843dc4249e13918fcfaf8e79a2ccb8afa83ec58bf5023e981769d9fba139","abstract_canon_sha256":"f7066cf69bf44de969eead60dd87f8dbd5719705d1c1f231c2d26a31642ff080"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:44.863668Z","signature_b64":"DD8S9UTzwdkCPuN872XcpqtclXZ8E5KARB3VGYmvzjBxeMkopbzw8s3OiUDQOtDnU9IB6zFKBHbjZM2jrjPfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"711e93a3ecd56dfb4085df104b8d9c17b453221c4b71ff78eecd0ba1f77ac9b2","last_reissued_at":"2026-07-28T00:21:44.862815Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:44.862815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jessica Tang, Sharad Agarwal, Shraddha Barke","submitted_at":"2026-06-14T17:14:01Z","abstract_excerpt":"When a language model produces a response in a multi-turn conversation, which tokens from prior turns shaped that answer, and how did those dependencies propagate across prior turns? Existing context attribution methods process the full context in a single pass, recovering surface-level dependencies but missing the layered, non-linear structure of real-world dialogues and multi-step reasoning tasks. We introduce multi-turn context attribution (MTCA): given a target span in a model response, the task of tracing attribution backward across turns to identify not only which prior turns were direct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22610","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/2607.22610/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.22610","created_at":"2026-07-28T00:21:44.863252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22610v1","created_at":"2026-07-28T00:21:44.863252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22610","created_at":"2026-07-28T00:21:44.863252+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEPJHI7M2VW7","created_at":"2026-07-28T00:21:44.863252+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEPJHI7M2VW7WQEF","created_at":"2026-07-28T00:21:44.863252+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEPJHI7M","created_at":"2026-07-28T00:21:44.863252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6","json":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6.json","graph_json":"https://pith.science/api/pith-number/OEPJHI7M2VW7WQEF34IEXDM4C6/graph.json","events_json":"https://pith.science/api/pith-number/OEPJHI7M2VW7WQEF34IEXDM4C6/events.json","paper":"https://pith.science/paper/OEPJHI7M"},"agent_actions":{"view_html":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6","download_json":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6.json","view_paper":"https://pith.science/paper/OEPJHI7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22610&json=true","fetch_graph":"https://pith.science/api/pith-number/OEPJHI7M2VW7WQEF34IEXDM4C6/graph.json","fetch_events":"https://pith.science/api/pith-number/OEPJHI7M2VW7WQEF34IEXDM4C6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6/action/storage_attestation","attest_author":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6/action/author_attestation","sign_citation":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6/action/citation_signature","submit_replication":"https://pith.science/pith/OEPJHI7M2VW7WQEF34IEXDM4C6/action/replication_record"}},"created_at":"2026-07-28T00:21:44.863252+00:00","updated_at":"2026-07-28T00:21:44.863252+00:00"}