{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7Z42BLPKZGXVZLDT5LJDPOGTVL","short_pith_number":"pith:7Z42BLPK","canonical_record":{"source":{"id":"2607.10096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-11T03:24:26Z","cross_cats_sorted":[],"title_canon_sha256":"aa47835c5e7c1e15390a57e10fc1e1ec5ccb0cacb8c406a7cc5059c4800baf51","abstract_canon_sha256":"ebe93bb76462063d167cabc4a49d17d5d5815cc867bc7045bf529dd61af1f23f"},"schema_version":"1.0"},"canonical_sha256":"fe79a0adeac9af5cac73ead237b8d3aacc28eddda4e679a9a743e4dbfda86713","source":{"kind":"arxiv","id":"2607.10096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10096","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10096v1","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10096","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"pith_short_12","alias_value":"7Z42BLPKZGXV","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"pith_short_16","alias_value":"7Z42BLPKZGXVZLDT","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"pith_short_8","alias_value":"7Z42BLPK","created_at":"2026-07-14T00:18:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7Z42BLPKZGXVZLDT5LJDPOGTVL","target":"record","payload":{"canonical_record":{"source":{"id":"2607.10096","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-11T03:24:26Z","cross_cats_sorted":[],"title_canon_sha256":"aa47835c5e7c1e15390a57e10fc1e1ec5ccb0cacb8c406a7cc5059c4800baf51","abstract_canon_sha256":"ebe93bb76462063d167cabc4a49d17d5d5815cc867bc7045bf529dd61af1f23f"},"schema_version":"1.0"},"canonical_sha256":"fe79a0adeac9af5cac73ead237b8d3aacc28eddda4e679a9a743e4dbfda86713","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:51.513250Z","signature_b64":"IK4LfOWOUOK7SG6HT0Sz2CZ4S8wWHBgjT2AHXScT9hDkfHamAEw5l9xU4+eRmiAiSbmasvDxQIi84Lux8oI3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe79a0adeac9af5cac73ead237b8d3aacc28eddda4e679a9a743e4dbfda86713","last_reissued_at":"2026-07-14T00:18:51.512422Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:51.512422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.10096","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":"2026-07-14T00:18:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+b/EevNLW0QdibYjsHLY+CooPkTprYxTdmqLB3IIPBOlgnAxnI8ZQ7JD3gjOOK6qejFqL9zqkTB9Xsh9FH6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:12:53.927744Z"},"content_sha256":"d97f37f4a4b82a1f187ef0c30eda01d087c13497448115a38065023db4fcbbfd","schema_version":"1.0","event_id":"sha256:d97f37f4a4b82a1f187ef0c30eda01d087c13497448115a38065023db4fcbbfd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7Z42BLPKZGXVZLDT5LJDPOGTVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling and Stabilizing Large-Scale Embedding-Based Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ciya Liao, Cun Mu, Feng Liu, Hongwei Shang, Juexin Lin, Kaihao Li, Satya Chembolu, Tony Lee, Xinyi Liu, Xunfan Cai, Zhen Yang","submitted_at":"2026-07-11T03:24:26Z","abstract_excerpt":"Embedding-based retrieval (EBR) is foundational to large-scale e-commerce search, yet its effectiveness is often constrained by the quality of training signals and the representational capacity of the encoder. Standard dual-encoders suffer from a training-inference gap: they are optimized on narrow candidate pools but must discriminate against hundreds of millions of items during inference. Furthermore, while transitioning to higher-capacity backbones can mitigate this gap, simply replacing a mature model can lead to inconsistent retrieval behavior and a loss of the domain-specific knowledge e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10096","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/2607.10096/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":"2026-07-14T00:18:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IJX8l+u5yITLO2+qh5to/F+HUh2dS47C3YbPOAHZ3MD9eqABWfpweucfos6eRbcmMxJ1koprhM0wk+Q8Vs9yAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:12:53.928623Z"},"content_sha256":"0b00a4e7c5a108ac9e331c0886725158a1c715e507192a6209e4a7fc2b91ce84","schema_version":"1.0","event_id":"sha256:0b00a4e7c5a108ac9e331c0886725158a1c715e507192a6209e4a7fc2b91ce84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7Z42BLPKZGXVZLDT5LJDPOGTVL/bundle.json","state_url":"https://pith.science/pith/7Z42BLPKZGXVZLDT5LJDPOGTVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7Z42BLPKZGXVZLDT5LJDPOGTVL/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":"2026-08-05T21:12:53Z","links":{"resolver":"https://pith.science/pith/7Z42BLPKZGXVZLDT5LJDPOGTVL","bundle":"https://pith.science/pith/7Z42BLPKZGXVZLDT5LJDPOGTVL/bundle.json","state":"https://pith.science/pith/7Z42BLPKZGXVZLDT5LJDPOGTVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7Z42BLPKZGXVZLDT5LJDPOGTVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7Z42BLPKZGXVZLDT5LJDPOGTVL","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":"ebe93bb76462063d167cabc4a49d17d5d5815cc867bc7045bf529dd61af1f23f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-11T03:24:26Z","title_canon_sha256":"aa47835c5e7c1e15390a57e10fc1e1ec5ccb0cacb8c406a7cc5059c4800baf51"},"schema_version":"1.0","source":{"id":"2607.10096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10096","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10096v1","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10096","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"pith_short_12","alias_value":"7Z42BLPKZGXV","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"pith_short_16","alias_value":"7Z42BLPKZGXVZLDT","created_at":"2026-07-14T00:18:51Z"},{"alias_kind":"pith_short_8","alias_value":"7Z42BLPK","created_at":"2026-07-14T00:18:51Z"}],"graph_snapshots":[{"event_id":"sha256:0b00a4e7c5a108ac9e331c0886725158a1c715e507192a6209e4a7fc2b91ce84","target":"graph","created_at":"2026-07-14T00:18:51Z","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/2607.10096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embedding-based retrieval (EBR) is foundational to large-scale e-commerce search, yet its effectiveness is often constrained by the quality of training signals and the representational capacity of the encoder. Standard dual-encoders suffer from a training-inference gap: they are optimized on narrow candidate pools but must discriminate against hundreds of millions of items during inference. Furthermore, while transitioning to higher-capacity backbones can mitigate this gap, simply replacing a mature model can lead to inconsistent retrieval behavior and a loss of the domain-specific knowledge e","authors_text":"Ciya Liao, Cun Mu, Feng Liu, Hongwei Shang, Juexin Lin, Kaihao Li, Satya Chembolu, Tony Lee, Xinyi Liu, Xunfan Cai, Zhen Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-11T03:24:26Z","title":"Scaling and Stabilizing Large-Scale Embedding-Based Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10096","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:d97f37f4a4b82a1f187ef0c30eda01d087c13497448115a38065023db4fcbbfd","target":"record","created_at":"2026-07-14T00:18:51Z","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":"ebe93bb76462063d167cabc4a49d17d5d5815cc867bc7045bf529dd61af1f23f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-11T03:24:26Z","title_canon_sha256":"aa47835c5e7c1e15390a57e10fc1e1ec5ccb0cacb8c406a7cc5059c4800baf51"},"schema_version":"1.0","source":{"id":"2607.10096","kind":"arxiv","version":1}},"canonical_sha256":"fe79a0adeac9af5cac73ead237b8d3aacc28eddda4e679a9a743e4dbfda86713","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe79a0adeac9af5cac73ead237b8d3aacc28eddda4e679a9a743e4dbfda86713","first_computed_at":"2026-07-14T00:18:51.512422Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:51.512422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IK4LfOWOUOK7SG6HT0Sz2CZ4S8wWHBgjT2AHXScT9hDkfHamAEw5l9xU4+eRmiAiSbmasvDxQIi84Lux8oI3AA==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:51.513250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d97f37f4a4b82a1f187ef0c30eda01d087c13497448115a38065023db4fcbbfd","sha256:0b00a4e7c5a108ac9e331c0886725158a1c715e507192a6209e4a7fc2b91ce84"],"state_sha256":"08abc1788106e34e2c41c2de0811290a3721807145f17dab89997dd076304c2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/NjW2GlFGZ2I1jZCxIadNMzlcn1/b/4W4WfVHb/EnOx5DYsiDpgNABL5vaUN6E7yzuqYTzdtnfliIDfJryWSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:12:53.934800Z","bundle_sha256":"2ed2ee4dfab10d327dd43cca10a1abd236b2eacf008fec27f7263d2907279398"}}