{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XGNTNYUCDQFISU6J64ANOVUG44","short_pith_number":"pith:XGNTNYUC","canonical_record":{"source":{"id":"2605.26419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T01:15:10Z","cross_cats_sorted":[],"title_canon_sha256":"7c12e84deb316a468265607eab2d09f3d155a6119f297b24a8c31a7d81ae8498","abstract_canon_sha256":"ff1e7daa80b345bb75c373c3890c912911e23f924a8f5dc8acc823e90bed4ed4"},"schema_version":"1.0"},"canonical_sha256":"b99b36e2821c0a8953c9f700d75686e735378c4cca5ef5af1d9942562d2b4efc","source":{"kind":"arxiv","id":"2605.26419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26419","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26419v1","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26419","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"XGNTNYUCDQFI","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"XGNTNYUCDQFISU6J","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"XGNTNYUC","created_at":"2026-05-27T01:05:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XGNTNYUCDQFISU6J64ANOVUG44","target":"record","payload":{"canonical_record":{"source":{"id":"2605.26419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T01:15:10Z","cross_cats_sorted":[],"title_canon_sha256":"7c12e84deb316a468265607eab2d09f3d155a6119f297b24a8c31a7d81ae8498","abstract_canon_sha256":"ff1e7daa80b345bb75c373c3890c912911e23f924a8f5dc8acc823e90bed4ed4"},"schema_version":"1.0"},"canonical_sha256":"b99b36e2821c0a8953c9f700d75686e735378c4cca5ef5af1d9942562d2b4efc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:16.887729Z","signature_b64":"ZuTpWjdYjyYNtBoQEkdstyitgjz4N5TCdCXn7fEvcJxGTaUpuFPYgg4+8wzB7k+DAImyC2jOpq/6erkbEGhfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b99b36e2821c0a8953c9f700d75686e735378c4cca5ef5af1d9942562d2b4efc","last_reissued_at":"2026-05-27T01:05:16.887199Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:16.887199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.26419","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":"2026-05-27T01:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ZkXrk23HfV6P1IUWcG8tRONzo/aX1m8lXoP3OAgATouNkr+zL4cHeCC/Rm/tyw6khnGGq7Y7hZCVbHvX8sSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:23:04.172618Z"},"content_sha256":"a3d1c945f686366d87017cccb4733c6aab6028fb067fb324dfa3dcc4e5f58790","schema_version":"1.0","event_id":"sha256:a3d1c945f686366d87017cccb4733c6aab6028fb067fb324dfa3dcc4e5f58790"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XGNTNYUCDQFISU6J64ANOVUG44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Amortized Factor Inference Networks for Posterior Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Joohwan Ko, Justin Domke","submitted_at":"2026-05-26T01:15:10Z","abstract_excerpt":"Amortized inference promises fast test-time Bayesian inference, but existing methods are inherently tied to fixed models. Extending amortization to unseen models typically requires retraining or costly test-time finetuning. In this paper, we ask: is it possible to build a single inference network capable of generalizing across varying priors, likelihoods, and dimensionality? We introduce Amortized Factor Inference Networks (AFINs), a family of encode-merge-decode inference networks built on dimension-independent modules that map a model specification and its observations to the parameters of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26419","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/2605.26419/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":"2026-05-27T01:05:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PaJeDISqgeXZbTC2GttCPb1oOjTbHB3pwIPbYAfhv3ySQ6Xa1DRhgY3LT3+DoIJfeZHEVOa+4IpPwuez/6tKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:23:04.172989Z"},"content_sha256":"284fb635222333f7f8fba0b7e97b091dc4fb544e659bbd6d1f8c3be5bf308911","schema_version":"1.0","event_id":"sha256:284fb635222333f7f8fba0b7e97b091dc4fb544e659bbd6d1f8c3be5bf308911"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGNTNYUCDQFISU6J64ANOVUG44/bundle.json","state_url":"https://pith.science/pith/XGNTNYUCDQFISU6J64ANOVUG44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGNTNYUCDQFISU6J64ANOVUG44/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":"2026-07-06T19:23:04Z","links":{"resolver":"https://pith.science/pith/XGNTNYUCDQFISU6J64ANOVUG44","bundle":"https://pith.science/pith/XGNTNYUCDQFISU6J64ANOVUG44/bundle.json","state":"https://pith.science/pith/XGNTNYUCDQFISU6J64ANOVUG44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGNTNYUCDQFISU6J64ANOVUG44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XGNTNYUCDQFISU6J64ANOVUG44","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":"ff1e7daa80b345bb75c373c3890c912911e23f924a8f5dc8acc823e90bed4ed4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T01:15:10Z","title_canon_sha256":"7c12e84deb316a468265607eab2d09f3d155a6119f297b24a8c31a7d81ae8498"},"schema_version":"1.0","source":{"id":"2605.26419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26419","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26419v1","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26419","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_12","alias_value":"XGNTNYUCDQFI","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_16","alias_value":"XGNTNYUCDQFISU6J","created_at":"2026-05-27T01:05:16Z"},{"alias_kind":"pith_short_8","alias_value":"XGNTNYUC","created_at":"2026-05-27T01:05:16Z"}],"graph_snapshots":[{"event_id":"sha256:284fb635222333f7f8fba0b7e97b091dc4fb544e659bbd6d1f8c3be5bf308911","target":"graph","created_at":"2026-05-27T01:05:16Z","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/2605.26419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Amortized inference promises fast test-time Bayesian inference, but existing methods are inherently tied to fixed models. Extending amortization to unseen models typically requires retraining or costly test-time finetuning. In this paper, we ask: is it possible to build a single inference network capable of generalizing across varying priors, likelihoods, and dimensionality? We introduce Amortized Factor Inference Networks (AFINs), a family of encode-merge-decode inference networks built on dimension-independent modules that map a model specification and its observations to the parameters of a","authors_text":"Joohwan Ko, Justin Domke","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T01:15:10Z","title":"Amortized Factor Inference Networks for Posterior Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26419","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:a3d1c945f686366d87017cccb4733c6aab6028fb067fb324dfa3dcc4e5f58790","target":"record","created_at":"2026-05-27T01:05:16Z","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":"ff1e7daa80b345bb75c373c3890c912911e23f924a8f5dc8acc823e90bed4ed4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T01:15:10Z","title_canon_sha256":"7c12e84deb316a468265607eab2d09f3d155a6119f297b24a8c31a7d81ae8498"},"schema_version":"1.0","source":{"id":"2605.26419","kind":"arxiv","version":1}},"canonical_sha256":"b99b36e2821c0a8953c9f700d75686e735378c4cca5ef5af1d9942562d2b4efc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b99b36e2821c0a8953c9f700d75686e735378c4cca5ef5af1d9942562d2b4efc","first_computed_at":"2026-05-27T01:05:16.887199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:16.887199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZuTpWjdYjyYNtBoQEkdstyitgjz4N5TCdCXn7fEvcJxGTaUpuFPYgg4+8wzB7k+DAImyC2jOpq/6erkbEGhfCw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:16.887729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3d1c945f686366d87017cccb4733c6aab6028fb067fb324dfa3dcc4e5f58790","sha256:284fb635222333f7f8fba0b7e97b091dc4fb544e659bbd6d1f8c3be5bf308911"],"state_sha256":"f053eebe223f162d80a4333f8e3c2d0b1b21e3ddbcec15ffd23fc6978b8b70f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"95Zf47Ku5/r2M5C/C6rGjsfd7apGbaLUFCDSRnUMqkCBy1nx/J15p8cLAEmKTOtxjtHudhP5aHE4gyvnGWiGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:23:04.174831Z","bundle_sha256":"6123606acaea9b9f2e6427b0c41a647cac61326fcea8dca3943eb4be8027012a"}}