{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JMJKFFSUK7OZCD72P4O66VBC56","short_pith_number":"pith:JMJKFFSU","canonical_record":{"source":{"id":"2410.24126","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T16:50:39Z","cross_cats_sorted":[],"title_canon_sha256":"25a1e775fc11253fd004cbc64ec97a2535465eaa02f92a314eb54f2f6b53410a","abstract_canon_sha256":"70797cc34a520bd758c257659cdccdac989de1343b89692b054e2dc072920621"},"schema_version":"1.0"},"canonical_sha256":"4b12a2965457dd910ffa7f1def5422efbc543af6b0b38dfed29a764fee9a214e","source":{"kind":"arxiv","id":"2410.24126","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24126","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24126v2","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24126","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_12","alias_value":"JMJKFFSUK7OZ","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_16","alias_value":"JMJKFFSUK7OZCD72","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_8","alias_value":"JMJKFFSU","created_at":"2026-07-05T09:29:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JMJKFFSUK7OZCD72P4O66VBC56","target":"record","payload":{"canonical_record":{"source":{"id":"2410.24126","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T16:50:39Z","cross_cats_sorted":[],"title_canon_sha256":"25a1e775fc11253fd004cbc64ec97a2535465eaa02f92a314eb54f2f6b53410a","abstract_canon_sha256":"70797cc34a520bd758c257659cdccdac989de1343b89692b054e2dc072920621"},"schema_version":"1.0"},"canonical_sha256":"4b12a2965457dd910ffa7f1def5422efbc543af6b0b38dfed29a764fee9a214e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:36.064577Z","signature_b64":"EbcsX3snmTYUPBv11xAjEHdZQ1cdrJjEZ3tXiZo1/ge6E5t0LkBZD8cLLfJboVkIB9rJ/NtxbrwPM71ekW2QDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b12a2965457dd910ffa7f1def5422efbc543af6b0b38dfed29a764fee9a214e","last_reissued_at":"2026-07-05T09:29:36.064109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:36.064109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.24126","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:29:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IAXp0qJN2vUgz9/e+KP3htmvQ3/XNGrRmUq25UPzdxdRGgl4wSTyZ34PJAyEQjWJZ3rr3WPv2ClUFjhUTyiEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:41:33.273785Z"},"content_sha256":"90a736b938e4bccb73126915a6135a1728e3fb5109e4395f8732584bb6b9ecd5","schema_version":"1.0","event_id":"sha256:90a736b938e4bccb73126915a6135a1728e3fb5109e4395f8732584bb6b9ecd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JMJKFFSUK7OZCD72P4O66VBC56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-environment Topic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Feder, David Blei, Dominic Sobhani","submitted_at":"2024-10-31T16:50:39Z","abstract_excerpt":"Probabilistic topic models are a powerful tool for extracting latent themes from large text datasets. In many text datasets, we also observe per-document covariates (e.g., source, style, political affiliation) that act as environments that modulate a \"global\" (environment-agnostic) topic representation. Accurately learning these representations is important for prediction on new documents in unseen environments and for estimating the causal effect of topics on real-world outcomes. To this end, we introduce the Multi-environment Topic Model (MTM), an unsupervised probabilistic model that separa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24126","kind":"arxiv","version":2},"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/2410.24126/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":"2026-07-05T09:29:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3JBB1+k/b6NI2pyuf3HprHelXqvYbA/c9i9lj0n9T2oDwJpXEGv7ScOrLYOUkfji4u+Vskoz7wGKK4PMc9wAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:41:33.274620Z"},"content_sha256":"1ecaab98ea3f804044e9d6d8be03d79329337e16f82f79304d25d9a77148f021","schema_version":"1.0","event_id":"sha256:1ecaab98ea3f804044e9d6d8be03d79329337e16f82f79304d25d9a77148f021"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMJKFFSUK7OZCD72P4O66VBC56/bundle.json","state_url":"https://pith.science/pith/JMJKFFSUK7OZCD72P4O66VBC56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMJKFFSUK7OZCD72P4O66VBC56/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":"2026-08-13T04:41:33Z","links":{"resolver":"https://pith.science/pith/JMJKFFSUK7OZCD72P4O66VBC56","bundle":"https://pith.science/pith/JMJKFFSUK7OZCD72P4O66VBC56/bundle.json","state":"https://pith.science/pith/JMJKFFSUK7OZCD72P4O66VBC56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMJKFFSUK7OZCD72P4O66VBC56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JMJKFFSUK7OZCD72P4O66VBC56","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":"70797cc34a520bd758c257659cdccdac989de1343b89692b054e2dc072920621","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T16:50:39Z","title_canon_sha256":"25a1e775fc11253fd004cbc64ec97a2535465eaa02f92a314eb54f2f6b53410a"},"schema_version":"1.0","source":{"id":"2410.24126","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.24126","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.24126v2","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.24126","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_12","alias_value":"JMJKFFSUK7OZ","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_16","alias_value":"JMJKFFSUK7OZCD72","created_at":"2026-07-05T09:29:36Z"},{"alias_kind":"pith_short_8","alias_value":"JMJKFFSU","created_at":"2026-07-05T09:29:36Z"}],"graph_snapshots":[{"event_id":"sha256:1ecaab98ea3f804044e9d6d8be03d79329337e16f82f79304d25d9a77148f021","target":"graph","created_at":"2026-07-05T09:29:36Z","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/2410.24126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Probabilistic topic models are a powerful tool for extracting latent themes from large text datasets. In many text datasets, we also observe per-document covariates (e.g., source, style, political affiliation) that act as environments that modulate a \"global\" (environment-agnostic) topic representation. Accurately learning these representations is important for prediction on new documents in unseen environments and for estimating the causal effect of topics on real-world outcomes. To this end, we introduce the Multi-environment Topic Model (MTM), an unsupervised probabilistic model that separa","authors_text":"Amir Feder, David Blei, Dominic Sobhani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T16:50:39Z","title":"Multi-environment Topic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.24126","kind":"arxiv","version":2},"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":"sha256:90a736b938e4bccb73126915a6135a1728e3fb5109e4395f8732584bb6b9ecd5","target":"record","created_at":"2026-07-05T09:29:36Z","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":"70797cc34a520bd758c257659cdccdac989de1343b89692b054e2dc072920621","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T16:50:39Z","title_canon_sha256":"25a1e775fc11253fd004cbc64ec97a2535465eaa02f92a314eb54f2f6b53410a"},"schema_version":"1.0","source":{"id":"2410.24126","kind":"arxiv","version":2}},"canonical_sha256":"4b12a2965457dd910ffa7f1def5422efbc543af6b0b38dfed29a764fee9a214e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b12a2965457dd910ffa7f1def5422efbc543af6b0b38dfed29a764fee9a214e","first_computed_at":"2026-07-05T09:29:36.064109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:36.064109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EbcsX3snmTYUPBv11xAjEHdZQ1cdrJjEZ3tXiZo1/ge6E5t0LkBZD8cLLfJboVkIB9rJ/NtxbrwPM71ekW2QDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:36.064577Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.24126","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90a736b938e4bccb73126915a6135a1728e3fb5109e4395f8732584bb6b9ecd5","sha256:1ecaab98ea3f804044e9d6d8be03d79329337e16f82f79304d25d9a77148f021"],"state_sha256":"0ebf9135ba717989a8348e4beccb1c9557b20abda52ff29d5276864046a44227"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KT69bmAx0IIufh+GFNi/KoCODRyTPMV+t7dbgY2ygRxzobVtglZOORYjfabaJorXXK3D/gHW0cB0beATdqBpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:41:33.281870Z","bundle_sha256":"fe0a9658ec5e7d9301fe3b93c2245550f7343a3e7b93e47d950d29cb815dc426"}}