{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KWCOJYRRUBMHKSJZX3AZUCHGER","short_pith_number":"pith:KWCOJYRR","canonical_record":{"source":{"id":"2412.06924","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T19:10:03Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"af27c2521c79823ef5749a302d9d8068b8ce8725b4ef8134a05c1abb220cc95a","abstract_canon_sha256":"ef35a9eed602b85ce0d895f1ab791b13f9d54d833ab33ae9b5cb75402ca0a058"},"schema_version":"1.0"},"canonical_sha256":"5584e4e231a058754939bec19a08e6245938682d4cd67e71f9e402c2f82b0624","source":{"kind":"arxiv","id":"2412.06924","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06924","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06924v1","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06924","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"pith_short_12","alias_value":"KWCOJYRRUBMH","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"pith_short_16","alias_value":"KWCOJYRRUBMHKSJZ","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"pith_short_8","alias_value":"KWCOJYRR","created_at":"2026-07-05T09:47:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KWCOJYRRUBMHKSJZX3AZUCHGER","target":"record","payload":{"canonical_record":{"source":{"id":"2412.06924","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T19:10:03Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"af27c2521c79823ef5749a302d9d8068b8ce8725b4ef8134a05c1abb220cc95a","abstract_canon_sha256":"ef35a9eed602b85ce0d895f1ab791b13f9d54d833ab33ae9b5cb75402ca0a058"},"schema_version":"1.0"},"canonical_sha256":"5584e4e231a058754939bec19a08e6245938682d4cd67e71f9e402c2f82b0624","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:00.317077Z","signature_b64":"CPd8okp2t6+1C21sUxLw1ywlF7j8kXt72U/Wrj4cUeQ5tM1AG/Q7Qzz1W2+kNfiCWbcc2UMG8w6YQCB+hbvUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5584e4e231a058754939bec19a08e6245938682d4cd67e71f9e402c2f82b0624","last_reissued_at":"2026-07-05T09:47:00.316438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:00.316438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.06924","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":"2026-07-05T09:47:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5peI0FId+aC2yt+0kGzImhGhmjMHpdfNx533s6IB7q+tcjl+3E3hJ+NHtKnW+CeJ3kEcr0EhGgSYaMi7tDVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:13:41.159059Z"},"content_sha256":"25fd6cecad71d5c0fbb2be8357098a1e7b0945f30cf8e0085a3eca7635cca081","schema_version":"1.0","event_id":"sha256:25fd6cecad71d5c0fbb2be8357098a1e7b0945f30cf8e0085a3eca7635cca081"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KWCOJYRRUBMHKSJZX3AZUCHGER","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient user history modeling with amortized inference for deep learning recommendation models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Aman Gupta, Fedor Borisyuk, Lars Hertel, Neil Daftary, Rahul Mazumder","submitted_at":"2024-12-09T19:10:03Z","abstract_excerpt":"We study user history modeling via Transformer encoders in deep learning recommendation models (DLRM). Such architectures can significantly improve recommendation quality, but usually incur high latency cost necessitating infrastructure upgrades or very small Transformer models. An important part of user history modeling is early fusion of the candidate item and various methods have been studied. We revisit early fusion and compare concatenation of the candidate to each history item against appending it to the end of the list as a separate item. Using the latter method, allows us to reformulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06924","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/2412.06924/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":"2026-07-05T09:47:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3rnvbzPiJbQzLGJO3YkhdGeFWGdctJlUIZ8dbm9vSmHsDvlMkgjzShQpNg/+a4FSLS61aTkw1Apvjm7Dk/XxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:13:41.159565Z"},"content_sha256":"056ef39acf851a95e3e4e623075c2190e9305074658c1209e68873bc57623993","schema_version":"1.0","event_id":"sha256:056ef39acf851a95e3e4e623075c2190e9305074658c1209e68873bc57623993"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KWCOJYRRUBMHKSJZX3AZUCHGER/bundle.json","state_url":"https://pith.science/pith/KWCOJYRRUBMHKSJZX3AZUCHGER/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KWCOJYRRUBMHKSJZX3AZUCHGER/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":"2026-08-09T01:13:41Z","links":{"resolver":"https://pith.science/pith/KWCOJYRRUBMHKSJZX3AZUCHGER","bundle":"https://pith.science/pith/KWCOJYRRUBMHKSJZX3AZUCHGER/bundle.json","state":"https://pith.science/pith/KWCOJYRRUBMHKSJZX3AZUCHGER/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KWCOJYRRUBMHKSJZX3AZUCHGER/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KWCOJYRRUBMHKSJZX3AZUCHGER","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":"ef35a9eed602b85ce0d895f1ab791b13f9d54d833ab33ae9b5cb75402ca0a058","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T19:10:03Z","title_canon_sha256":"af27c2521c79823ef5749a302d9d8068b8ce8725b4ef8134a05c1abb220cc95a"},"schema_version":"1.0","source":{"id":"2412.06924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06924","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06924v1","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06924","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"pith_short_12","alias_value":"KWCOJYRRUBMH","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"pith_short_16","alias_value":"KWCOJYRRUBMHKSJZ","created_at":"2026-07-05T09:47:00Z"},{"alias_kind":"pith_short_8","alias_value":"KWCOJYRR","created_at":"2026-07-05T09:47:00Z"}],"graph_snapshots":[{"event_id":"sha256:056ef39acf851a95e3e4e623075c2190e9305074658c1209e68873bc57623993","target":"graph","created_at":"2026-07-05T09:47:00Z","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/2412.06924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study user history modeling via Transformer encoders in deep learning recommendation models (DLRM). Such architectures can significantly improve recommendation quality, but usually incur high latency cost necessitating infrastructure upgrades or very small Transformer models. An important part of user history modeling is early fusion of the candidate item and various methods have been studied. We revisit early fusion and compare concatenation of the candidate to each history item against appending it to the end of the list as a separate item. Using the latter method, allows us to reformulat","authors_text":"Aman Gupta, Fedor Borisyuk, Lars Hertel, Neil Daftary, Rahul Mazumder","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T19:10:03Z","title":"Efficient user history modeling with amortized inference for deep learning recommendation models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06924","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":"sha256:25fd6cecad71d5c0fbb2be8357098a1e7b0945f30cf8e0085a3eca7635cca081","target":"record","created_at":"2026-07-05T09:47:00Z","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":"ef35a9eed602b85ce0d895f1ab791b13f9d54d833ab33ae9b5cb75402ca0a058","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T19:10:03Z","title_canon_sha256":"af27c2521c79823ef5749a302d9d8068b8ce8725b4ef8134a05c1abb220cc95a"},"schema_version":"1.0","source":{"id":"2412.06924","kind":"arxiv","version":1}},"canonical_sha256":"5584e4e231a058754939bec19a08e6245938682d4cd67e71f9e402c2f82b0624","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5584e4e231a058754939bec19a08e6245938682d4cd67e71f9e402c2f82b0624","first_computed_at":"2026-07-05T09:47:00.316438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:00.316438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CPd8okp2t6+1C21sUxLw1ywlF7j8kXt72U/Wrj4cUeQ5tM1AG/Q7Qzz1W2+kNfiCWbcc2UMG8w6YQCB+hbvUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:00.317077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25fd6cecad71d5c0fbb2be8357098a1e7b0945f30cf8e0085a3eca7635cca081","sha256:056ef39acf851a95e3e4e623075c2190e9305074658c1209e68873bc57623993"],"state_sha256":"8f3c5c78333dedc8652c8e0fdd26e78fd79ec1b9bce0ceb1b9c2093e6cfe372b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ymwqMEnuVwWoCMMk6CDPjVPwbvfBkylLVHLwiNdCxuw0imfhSlTf9hbxTw8UiVykHbMRFk7o3x2uArHLWvlBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:13:41.163164Z","bundle_sha256":"798bfdd58b610c2f21d3d532d54e350c16308bd56218d292e15a47de407f34bb"}}