{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OVVNSLGBZOIKBXTFVFVFELEFNC","short_pith_number":"pith:OVVNSLGB","canonical_record":{"source":{"id":"2310.07815","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-11T18:56:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e9f93227308bc06a9f68c6a10e8b9bf6705891d11ec473f001ab2314292e1ec7","abstract_canon_sha256":"2fef1cdaea82fd6faffd3bda9db9fdee5d42509320b1acb705da67542d534333"},"schema_version":"1.0"},"canonical_sha256":"756ad92cc1cb90a0de65a96a522c85689ade088a0e6ab42bcf0bc975a8950b4e","source":{"kind":"arxiv","id":"2310.07815","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07815","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07815v3","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07815","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_12","alias_value":"OVVNSLGBZOIK","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_16","alias_value":"OVVNSLGBZOIKBXTF","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_8","alias_value":"OVVNSLGB","created_at":"2026-07-05T08:31:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OVVNSLGBZOIKBXTFVFVFELEFNC","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07815","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-11T18:56:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e9f93227308bc06a9f68c6a10e8b9bf6705891d11ec473f001ab2314292e1ec7","abstract_canon_sha256":"2fef1cdaea82fd6faffd3bda9db9fdee5d42509320b1acb705da67542d534333"},"schema_version":"1.0"},"canonical_sha256":"756ad92cc1cb90a0de65a96a522c85689ade088a0e6ab42bcf0bc975a8950b4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:06.395573Z","signature_b64":"wzBF2iGwPbDYWZz9mUDF8M4xzvYY377uz4sAFRt6tuapdnUUZYfPWpZeWxNRv2NGEKA40J0TIYq5ApT1tLBiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"756ad92cc1cb90a0de65a96a522c85689ade088a0e6ab42bcf0bc975a8950b4e","last_reissued_at":"2026-07-05T08:31:06.395160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:06.395160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07815","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O7QywOOW4VTpV3ge3xOvQS9eTDE6ibLgL6l3Yr1qqbb05tAN6RL3i+Cam2BlVygSTtrkwnF5iBZNnds/rKVrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:07:04.589736Z"},"content_sha256":"063af45f145b834c146b47854c63c24843fed0abbdb00bed4fbfdef1b800ad1b","schema_version":"1.0","event_id":"sha256:063af45f145b834c146b47854c63c24843fed0abbdb00bed4fbfdef1b800ad1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OVVNSLGBZOIKBXTFVFVFELEFNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models As Semantic Indexers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Bowen Jin, Guoyin Wang, Hanqing Lu, Hansi Zeng, Jiawei Han, Ruirui Li, Suhang Wang, Tianxin Wei, Xianfeng Tang, Xiusi Chen, Yang Li, Zheng Li, Zhengyang Wang","submitted_at":"2023-10-11T18:56:15Z","abstract_excerpt":"Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs. Previous studies typically adopt a two-stage pipeline to learn semantic IDs by first procuring embeddings using off-the-shelf text encoders and then deriving IDs based on the embeddings. However, each step introduces potential information loss, and there is usually an inherent mismatch between the distribution of embeddings within the latent space produced by text encoders and the anticipated distribution required for semantic in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07815","kind":"arxiv","version":3},"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/2310.07815/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":"2026-07-05T08:31:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Q3wuIxoJiw3rOzebnPhliYXpZXOl/FivznL/kWuumHdfbz4iR3IOCbXNr/pE8cLnBOeCJKLT2IahlmT58WiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:07:04.590347Z"},"content_sha256":"c788e96d8f07adb6f3a6f5500cbea318c7133c44e5ce5273861ce4965361504f","schema_version":"1.0","event_id":"sha256:c788e96d8f07adb6f3a6f5500cbea318c7133c44e5ce5273861ce4965361504f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVVNSLGBZOIKBXTFVFVFELEFNC/bundle.json","state_url":"https://pith.science/pith/OVVNSLGBZOIKBXTFVFVFELEFNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVVNSLGBZOIKBXTFVFVFELEFNC/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":"2026-08-10T13:07:04Z","links":{"resolver":"https://pith.science/pith/OVVNSLGBZOIKBXTFVFVFELEFNC","bundle":"https://pith.science/pith/OVVNSLGBZOIKBXTFVFVFELEFNC/bundle.json","state":"https://pith.science/pith/OVVNSLGBZOIKBXTFVFVFELEFNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVVNSLGBZOIKBXTFVFVFELEFNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OVVNSLGBZOIKBXTFVFVFELEFNC","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":"2fef1cdaea82fd6faffd3bda9db9fdee5d42509320b1acb705da67542d534333","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-11T18:56:15Z","title_canon_sha256":"e9f93227308bc06a9f68c6a10e8b9bf6705891d11ec473f001ab2314292e1ec7"},"schema_version":"1.0","source":{"id":"2310.07815","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07815","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07815v3","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07815","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_12","alias_value":"OVVNSLGBZOIK","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_16","alias_value":"OVVNSLGBZOIKBXTF","created_at":"2026-07-05T08:31:06Z"},{"alias_kind":"pith_short_8","alias_value":"OVVNSLGB","created_at":"2026-07-05T08:31:06Z"}],"graph_snapshots":[{"event_id":"sha256:c788e96d8f07adb6f3a6f5500cbea318c7133c44e5ce5273861ce4965361504f","target":"graph","created_at":"2026-07-05T08:31:06Z","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/2310.07815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs. Previous studies typically adopt a two-stage pipeline to learn semantic IDs by first procuring embeddings using off-the-shelf text encoders and then deriving IDs based on the embeddings. However, each step introduces potential information loss, and there is usually an inherent mismatch between the distribution of embeddings within the latent space produced by text encoders and the anticipated distribution required for semantic in","authors_text":"Bowen Jin, Guoyin Wang, Hanqing Lu, Hansi Zeng, Jiawei Han, Ruirui Li, Suhang Wang, Tianxin Wei, Xianfeng Tang, Xiusi Chen, Yang Li, Zheng Li, Zhengyang Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-11T18:56:15Z","title":"Language Models As Semantic Indexers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07815","kind":"arxiv","version":3},"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":"sha256:063af45f145b834c146b47854c63c24843fed0abbdb00bed4fbfdef1b800ad1b","target":"record","created_at":"2026-07-05T08:31:06Z","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":"2fef1cdaea82fd6faffd3bda9db9fdee5d42509320b1acb705da67542d534333","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-10-11T18:56:15Z","title_canon_sha256":"e9f93227308bc06a9f68c6a10e8b9bf6705891d11ec473f001ab2314292e1ec7"},"schema_version":"1.0","source":{"id":"2310.07815","kind":"arxiv","version":3}},"canonical_sha256":"756ad92cc1cb90a0de65a96a522c85689ade088a0e6ab42bcf0bc975a8950b4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"756ad92cc1cb90a0de65a96a522c85689ade088a0e6ab42bcf0bc975a8950b4e","first_computed_at":"2026-07-05T08:31:06.395160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:06.395160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wzBF2iGwPbDYWZz9mUDF8M4xzvYY377uz4sAFRt6tuapdnUUZYfPWpZeWxNRv2NGEKA40J0TIYq5ApT1tLBiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:06.395573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07815","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:063af45f145b834c146b47854c63c24843fed0abbdb00bed4fbfdef1b800ad1b","sha256:c788e96d8f07adb6f3a6f5500cbea318c7133c44e5ce5273861ce4965361504f"],"state_sha256":"a0ccc650eca84c8cd6e37497bf2839040205b6b2defa871535c0b4d6d1456f90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wuyr4OrPtxxyvOJ0+WmVkz7jLHB3bWEfN3GGNMep+FqLipeCpajkqncmo9Bx0omOH5us+Wz9dF3j/AsvFNTrAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:07:04.594086Z","bundle_sha256":"823064252671e5c7df84ac9ee0ad34eba4eff99c32da5d7d2e45342d1b2963e1"}}