{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V34JZEA642LP3VOHOR2FOBFEZ6","short_pith_number":"pith:V34JZEA6","canonical_record":{"source":{"id":"2501.16790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-28T08:42:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b9a9826d394efa296596bc571e13617d66b7a72b5472fad9f42afac455e375f","abstract_canon_sha256":"ecde4d35fe17c06d6585b577f82995e9a2413f17c582af4623fb2ab429232648"},"schema_version":"1.0"},"canonical_sha256":"aef89c901ee696fdd5c774745704a4cfb06fe064883c09d54754fe92de14327c","source":{"kind":"arxiv","id":"2501.16790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16790","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16790v1","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16790","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"V34JZEA642LP","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"V34JZEA642LP3VOH","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"V34JZEA6","created_at":"2026-07-05T10:06:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V34JZEA642LP3VOHOR2FOBFEZ6","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-28T08:42:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b9a9826d394efa296596bc571e13617d66b7a72b5472fad9f42afac455e375f","abstract_canon_sha256":"ecde4d35fe17c06d6585b577f82995e9a2413f17c582af4623fb2ab429232648"},"schema_version":"1.0"},"canonical_sha256":"aef89c901ee696fdd5c774745704a4cfb06fe064883c09d54754fe92de14327c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:18.619879Z","signature_b64":"fURpa1GgdgtbKqby05zbhP/i1OBrUzzWaIf+cYTylKyoKXifHNEnnChcWdVimS6VexvkbqjAKLWKiKATeNIeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aef89c901ee696fdd5c774745704a4cfb06fe064883c09d54754fe92de14327c","last_reissued_at":"2026-07-05T10:06:18.619390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:18.619390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16790","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":"2026-07-05T10:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ulKpULtEIvBsLbp+/zwlrGIfs9B2GJUcCTygAh1yoK0l+ftlRggyBiP3S2tV1Z+NZgZB+PqBrBnAFCHma/cBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:21:19.234527Z"},"content_sha256":"0618be66ac57b28bc49cde6b81ce48d9e44a6c1a84ed903d150e47fd8c3d21c9","schema_version":"1.0","event_id":"sha256:0618be66ac57b28bc49cde6b81ce48d9e44a6c1a84ed903d150e47fd8c3d21c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V34JZEA642LP3VOHOR2FOBFEZ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exponential Family Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kevin Christian Wibisono, Yixin Wang","submitted_at":"2025-01-28T08:42:58Z","abstract_excerpt":"The self-attention mechanism is the backbone of the transformer neural network underlying most large language models. It can capture complex word patterns and long-range dependencies in natural language. This paper introduces exponential family attention (EFA), a probabilistic generative model that extends self-attention to handle high-dimensional sequence, spatial, or spatial-temporal data of mixed data types, including both discrete and continuous observations. The key idea of EFA is to model each observation conditional on all other existing observations, called the context, whose relevance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16790","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/2501.16790/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":"2026-07-05T10:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IHyAuvnptsYy/6rmfApUio9i1KKNtfG+WEJnBZKdkr9kwtJxLLINSngcm4ELYChDht8zuzkYHwHfaAHgN6e2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:21:19.235481Z"},"content_sha256":"2f736b457d40acb1f8f8733aea703434c1fb1a4051715fdfe1fb72a80c52758e","schema_version":"1.0","event_id":"sha256:2f736b457d40acb1f8f8733aea703434c1fb1a4051715fdfe1fb72a80c52758e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V34JZEA642LP3VOHOR2FOBFEZ6/bundle.json","state_url":"https://pith.science/pith/V34JZEA642LP3VOHOR2FOBFEZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V34JZEA642LP3VOHOR2FOBFEZ6/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":"2026-08-10T23:21:19Z","links":{"resolver":"https://pith.science/pith/V34JZEA642LP3VOHOR2FOBFEZ6","bundle":"https://pith.science/pith/V34JZEA642LP3VOHOR2FOBFEZ6/bundle.json","state":"https://pith.science/pith/V34JZEA642LP3VOHOR2FOBFEZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V34JZEA642LP3VOHOR2FOBFEZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V34JZEA642LP3VOHOR2FOBFEZ6","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":"ecde4d35fe17c06d6585b577f82995e9a2413f17c582af4623fb2ab429232648","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-28T08:42:58Z","title_canon_sha256":"7b9a9826d394efa296596bc571e13617d66b7a72b5472fad9f42afac455e375f"},"schema_version":"1.0","source":{"id":"2501.16790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16790","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16790v1","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16790","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"V34JZEA642LP","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_16","alias_value":"V34JZEA642LP3VOH","created_at":"2026-07-05T10:06:18Z"},{"alias_kind":"pith_short_8","alias_value":"V34JZEA6","created_at":"2026-07-05T10:06:18Z"}],"graph_snapshots":[{"event_id":"sha256:2f736b457d40acb1f8f8733aea703434c1fb1a4051715fdfe1fb72a80c52758e","target":"graph","created_at":"2026-07-05T10:06:18Z","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/2501.16790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The self-attention mechanism is the backbone of the transformer neural network underlying most large language models. It can capture complex word patterns and long-range dependencies in natural language. This paper introduces exponential family attention (EFA), a probabilistic generative model that extends self-attention to handle high-dimensional sequence, spatial, or spatial-temporal data of mixed data types, including both discrete and continuous observations. The key idea of EFA is to model each observation conditional on all other existing observations, called the context, whose relevance","authors_text":"Kevin Christian Wibisono, Yixin Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-28T08:42:58Z","title":"Exponential Family Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16790","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":"sha256:0618be66ac57b28bc49cde6b81ce48d9e44a6c1a84ed903d150e47fd8c3d21c9","target":"record","created_at":"2026-07-05T10:06:18Z","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":"ecde4d35fe17c06d6585b577f82995e9a2413f17c582af4623fb2ab429232648","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-28T08:42:58Z","title_canon_sha256":"7b9a9826d394efa296596bc571e13617d66b7a72b5472fad9f42afac455e375f"},"schema_version":"1.0","source":{"id":"2501.16790","kind":"arxiv","version":1}},"canonical_sha256":"aef89c901ee696fdd5c774745704a4cfb06fe064883c09d54754fe92de14327c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aef89c901ee696fdd5c774745704a4cfb06fe064883c09d54754fe92de14327c","first_computed_at":"2026-07-05T10:06:18.619390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:18.619390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fURpa1GgdgtbKqby05zbhP/i1OBrUzzWaIf+cYTylKyoKXifHNEnnChcWdVimS6VexvkbqjAKLWKiKATeNIeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:18.619879Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0618be66ac57b28bc49cde6b81ce48d9e44a6c1a84ed903d150e47fd8c3d21c9","sha256:2f736b457d40acb1f8f8733aea703434c1fb1a4051715fdfe1fb72a80c52758e"],"state_sha256":"0487eb4f7ce11b5d1a9a9168fdf891a44aa407c7dac5209bd95225abab60ecaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YvuoG2btUlYITxAFcKrrypc0427OqgWou+t5iAfF1apT0tZLqw7H/VYFcmcDRht40V8+Vj68QBG5PrjFdBC0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:21:19.241451Z","bundle_sha256":"4545a093d3ea91244bb4c35522ce69209d41a9f123fb203c202f9c3d37a1fb1f"}}