{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:35AGBAUW2YUDGNU6GE3IAWNWIQ","short_pith_number":"pith:35AGBAUW","canonical_record":{"source":{"id":"2607.26365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T00:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"1f67a549f735f58fdfef751d4c0379b111761630f6a1da8035cfceed47b834e8","abstract_canon_sha256":"5ba5fd9015c01635e2806cc310736322490699fa479fab39728d8bf95d19c0dc"},"schema_version":"1.0"},"canonical_sha256":"df40608296d62833369e31368059b64425715c43394048dcdae2885a711ea2ba","source":{"kind":"arxiv","id":"2607.26365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26365","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26365v1","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26365","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"35AGBAUW2YUD","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"35AGBAUW2YUDGNU6","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"35AGBAUW","created_at":"2026-07-30T01:18:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:35AGBAUW2YUDGNU6GE3IAWNWIQ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T00:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"1f67a549f735f58fdfef751d4c0379b111761630f6a1da8035cfceed47b834e8","abstract_canon_sha256":"5ba5fd9015c01635e2806cc310736322490699fa479fab39728d8bf95d19c0dc"},"schema_version":"1.0"},"canonical_sha256":"df40608296d62833369e31368059b64425715c43394048dcdae2885a711ea2ba","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df40608296d62833369e31368059b64425715c43394048dcdae2885a711ea2ba","last_reissued_at":"2026-07-30T01:18:12.789852Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:12.789852Z"},"source_kind":"arxiv","source_id":"2607.26365","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":"2026-07-30T01:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rJPST47KNOgRw9LjHJeA8/n1OI5qAFxYK6tooGlBzO+/Cb6KIz28v6ee+AU4UTLw8e6ICuGSfoMtc1uirKGuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:32.999731Z"},"content_sha256":"9458e28adfdb467b91046b94197812c921c5e53ccf414b2d7a21dd1e318515d6","schema_version":"1.0","event_id":"sha256:9458e28adfdb467b91046b94197812c921c5e53ccf414b2d7a21dd1e318515d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:35AGBAUW2YUDGNU6GE3IAWNWIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Embedding Items at Scale: Comparing GNN-Based and ID-Based Item Embeddings in the Yandex Ecosystem","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Artem Matveev, Kirill Khrylchenko, Sergei Makeev, Vladimir Baikalov","submitted_at":"2026-07-29T00:44:25Z","abstract_excerpt":"Transformer-based sequential recommendation models, which process sequences of user-item interactions, rely heavily on the item embedding strategy. Existing approaches either use pretrained item embeddings or learn them end-to-end with the transformer. To the best of our knowledge, no prior work has compared these options from both cost and quality perspectives in a large-scale industrial setting. This paper is a case study that compares pretrained industrial graph neural network item embeddings with end-to-end trainable item embeddings across two mature production recommendation systems at Ya"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26365","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/2607.26365/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":"2026-07-30T01:18:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksboMwLC2+Ll9KrnWXUdcqybvvoCqSGRmG+EFYJ1P5CfTAmn6Oi5VkP/E5sObhdEGQu7l/B05mKxrkM9v7cYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:16:33.000390Z"},"content_sha256":"739becddedc3608ab5db8770ed47c44abd9eddae60edaff607097ff3d2b1aec7","schema_version":"1.0","event_id":"sha256:739becddedc3608ab5db8770ed47c44abd9eddae60edaff607097ff3d2b1aec7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35AGBAUW2YUDGNU6GE3IAWNWIQ/bundle.json","state_url":"https://pith.science/pith/35AGBAUW2YUDGNU6GE3IAWNWIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35AGBAUW2YUDGNU6GE3IAWNWIQ/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":"2026-08-03T19:16:33Z","links":{"resolver":"https://pith.science/pith/35AGBAUW2YUDGNU6GE3IAWNWIQ","bundle":"https://pith.science/pith/35AGBAUW2YUDGNU6GE3IAWNWIQ/bundle.json","state":"https://pith.science/pith/35AGBAUW2YUDGNU6GE3IAWNWIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35AGBAUW2YUDGNU6GE3IAWNWIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:35AGBAUW2YUDGNU6GE3IAWNWIQ","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":"5ba5fd9015c01635e2806cc310736322490699fa479fab39728d8bf95d19c0dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T00:44:25Z","title_canon_sha256":"1f67a549f735f58fdfef751d4c0379b111761630f6a1da8035cfceed47b834e8"},"schema_version":"1.0","source":{"id":"2607.26365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26365","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26365v1","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26365","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"pith_short_12","alias_value":"35AGBAUW2YUD","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"pith_short_16","alias_value":"35AGBAUW2YUDGNU6","created_at":"2026-07-30T01:18:12Z"},{"alias_kind":"pith_short_8","alias_value":"35AGBAUW","created_at":"2026-07-30T01:18:12Z"}],"graph_snapshots":[{"event_id":"sha256:739becddedc3608ab5db8770ed47c44abd9eddae60edaff607097ff3d2b1aec7","target":"graph","created_at":"2026-07-30T01:18:12Z","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/2607.26365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based sequential recommendation models, which process sequences of user-item interactions, rely heavily on the item embedding strategy. Existing approaches either use pretrained item embeddings or learn them end-to-end with the transformer. To the best of our knowledge, no prior work has compared these options from both cost and quality perspectives in a large-scale industrial setting. This paper is a case study that compares pretrained industrial graph neural network item embeddings with end-to-end trainable item embeddings across two mature production recommendation systems at Ya","authors_text":"Artem Matveev, Kirill Khrylchenko, Sergei Makeev, Vladimir Baikalov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T00:44:25Z","title":"Embedding Items at Scale: Comparing GNN-Based and ID-Based Item Embeddings in the Yandex Ecosystem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26365","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":"sha256:9458e28adfdb467b91046b94197812c921c5e53ccf414b2d7a21dd1e318515d6","target":"record","created_at":"2026-07-30T01:18:12Z","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":"5ba5fd9015c01635e2806cc310736322490699fa479fab39728d8bf95d19c0dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-29T00:44:25Z","title_canon_sha256":"1f67a549f735f58fdfef751d4c0379b111761630f6a1da8035cfceed47b834e8"},"schema_version":"1.0","source":{"id":"2607.26365","kind":"arxiv","version":1}},"canonical_sha256":"df40608296d62833369e31368059b64425715c43394048dcdae2885a711ea2ba","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df40608296d62833369e31368059b64425715c43394048dcdae2885a711ea2ba","first_computed_at":"2026-07-30T01:18:12.789852Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:18:12.789852Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9458e28adfdb467b91046b94197812c921c5e53ccf414b2d7a21dd1e318515d6","sha256:739becddedc3608ab5db8770ed47c44abd9eddae60edaff607097ff3d2b1aec7"],"state_sha256":"cd041db48087ae2dca9ce6294f441ab0baf760dfd3e23ad93ce7ed0796a2bd37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJONvlOQ4aRffV4qUVtoIF927DW3vizkgrIT1QcIG6++fMSI4WxFzAONWidHeBGX0lAgz/OmI7wDvluYfFC/CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:16:33.005633Z","bundle_sha256":"adea4c9f4134b8f1d846a02e8a1fd11da804bce0882ea94ee3b7cf597da27ce1"}}