{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GEQEYW4TBN73FHY5ZXYHDEHV5P","short_pith_number":"pith:GEQEYW4T","canonical_record":{"source":{"id":"2509.20904","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-25T08:44:22Z","cross_cats_sorted":[],"title_canon_sha256":"b0f8ba49a388d57d07ea8d4bb8c4a0777bd6f3ed2930f37444e543c836b469ef","abstract_canon_sha256":"dc10dccd938d51f5537d4a87938d729c28545fe6e074c51b1f538a83ea4bcc64"},"schema_version":"1.0"},"canonical_sha256":"31204c5b930b7fb29f1dcdf07190f5ebcc8387136e79c82357d6622ee9cb175b","source":{"kind":"arxiv","id":"2509.20904","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20904","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20904v3","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20904","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"GEQEYW4TBN73","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"GEQEYW4TBN73FHY5","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"GEQEYW4T","created_at":"2026-05-29T01:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GEQEYW4TBN73FHY5ZXYHDEHV5P","target":"record","payload":{"canonical_record":{"source":{"id":"2509.20904","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-25T08:44:22Z","cross_cats_sorted":[],"title_canon_sha256":"b0f8ba49a388d57d07ea8d4bb8c4a0777bd6f3ed2930f37444e543c836b469ef","abstract_canon_sha256":"dc10dccd938d51f5537d4a87938d729c28545fe6e074c51b1f538a83ea4bcc64"},"schema_version":"1.0"},"canonical_sha256":"31204c5b930b7fb29f1dcdf07190f5ebcc8387136e79c82357d6622ee9cb175b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:35.688382Z","signature_b64":"Fz7UBItrPoFgnniF73l0MiUyxKrxJ8OzgBXYiCH9jGlYblBz+ONTR37Aka9eofYOoN+m+3eqJYhcpHb2yO4cBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31204c5b930b7fb29f1dcdf07190f5ebcc8387136e79c82357d6622ee9cb175b","last_reissued_at":"2026-05-29T01:04:35.687741Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:35.687741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.20904","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":"2026-05-29T01:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/JzSke9i92bVSmhSbG9+gIjgaD6xUrrO48zovA+ANxZjmEhMsK1XwSr/HTjPlfomZFFX20qVtjugObevGvmPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:48:49.977595Z"},"content_sha256":"821bd0988965ec4de7f1e62dc3034a39f3ab549c3b2a76b1e9dc26cf66ef40f1","schema_version":"1.0","event_id":"sha256:821bd0988965ec4de7f1e62dc3034a39f3ab549c3b2a76b1e9dc26cf66ef40f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GEQEYW4TBN73FHY5ZXYHDEHV5P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chenchi Zhang, Junjun Zheng, Kairui Fu, Kun Kuang, Shengyu Zhang, Shuwen Xiao, Tao Zhang, Xiangheng Kong, Xinming Zhang, Yuliang Yan, Yuning Jiang, Ziyang Wang","submitted_at":"2025-09-25T08:44:22Z","abstract_excerpt":"Semantic identifiers (SIDs) have gained increasing attention in generative retrieval (GR) for recommendation due to their meaningful semantic discriminability. However, current studies in this field primarily (1) offer limited investigation into the construction strategies for better SIDs, and (2) their SID assessment typically relies on costly GR training. To address these challenges, we propose FORGE, a comprehensive benchmark for FOrming semantic identifieRs for Generative rEtrieval. Specifically, FORGE provides a taxonomy of the SID construction process from several perspectives and valida"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20904","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/2509.20904/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":"2026-05-29T01:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O9vSObg+Fzf5RSJuOSL+H3wJboyb3U7j1d4Wi+ayQ12YIvF5w43Peh08pieaJkYoSeowWcoossyYtIrYT1TrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:48:49.978369Z"},"content_sha256":"d2df33bdf32c29862f4e020c110c0aa339bd86e96397fa3396dacce8c0fb6dd3","schema_version":"1.0","event_id":"sha256:d2df33bdf32c29862f4e020c110c0aa339bd86e96397fa3396dacce8c0fb6dd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GEQEYW4TBN73FHY5ZXYHDEHV5P/bundle.json","state_url":"https://pith.science/pith/GEQEYW4TBN73FHY5ZXYHDEHV5P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GEQEYW4TBN73FHY5ZXYHDEHV5P/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":"2026-06-06T08:48:49Z","links":{"resolver":"https://pith.science/pith/GEQEYW4TBN73FHY5ZXYHDEHV5P","bundle":"https://pith.science/pith/GEQEYW4TBN73FHY5ZXYHDEHV5P/bundle.json","state":"https://pith.science/pith/GEQEYW4TBN73FHY5ZXYHDEHV5P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GEQEYW4TBN73FHY5ZXYHDEHV5P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GEQEYW4TBN73FHY5ZXYHDEHV5P","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":"dc10dccd938d51f5537d4a87938d729c28545fe6e074c51b1f538a83ea4bcc64","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-25T08:44:22Z","title_canon_sha256":"b0f8ba49a388d57d07ea8d4bb8c4a0777bd6f3ed2930f37444e543c836b469ef"},"schema_version":"1.0","source":{"id":"2509.20904","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.20904","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2509.20904v3","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.20904","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"GEQEYW4TBN73","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"GEQEYW4TBN73FHY5","created_at":"2026-05-29T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"GEQEYW4T","created_at":"2026-05-29T01:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:d2df33bdf32c29862f4e020c110c0aa339bd86e96397fa3396dacce8c0fb6dd3","target":"graph","created_at":"2026-05-29T01:04:35Z","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/2509.20904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic identifiers (SIDs) have gained increasing attention in generative retrieval (GR) for recommendation due to their meaningful semantic discriminability. However, current studies in this field primarily (1) offer limited investigation into the construction strategies for better SIDs, and (2) their SID assessment typically relies on costly GR training. To address these challenges, we propose FORGE, a comprehensive benchmark for FOrming semantic identifieRs for Generative rEtrieval. Specifically, FORGE provides a taxonomy of the SID construction process from several perspectives and valida","authors_text":"Chenchi Zhang, Junjun Zheng, Kairui Fu, Kun Kuang, Shengyu Zhang, Shuwen Xiao, Tao Zhang, Xiangheng Kong, Xinming Zhang, Yuliang Yan, Yuning Jiang, Ziyang Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-25T08:44:22Z","title":"FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.20904","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":"sha256:821bd0988965ec4de7f1e62dc3034a39f3ab549c3b2a76b1e9dc26cf66ef40f1","target":"record","created_at":"2026-05-29T01:04:35Z","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":"dc10dccd938d51f5537d4a87938d729c28545fe6e074c51b1f538a83ea4bcc64","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-25T08:44:22Z","title_canon_sha256":"b0f8ba49a388d57d07ea8d4bb8c4a0777bd6f3ed2930f37444e543c836b469ef"},"schema_version":"1.0","source":{"id":"2509.20904","kind":"arxiv","version":3}},"canonical_sha256":"31204c5b930b7fb29f1dcdf07190f5ebcc8387136e79c82357d6622ee9cb175b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31204c5b930b7fb29f1dcdf07190f5ebcc8387136e79c82357d6622ee9cb175b","first_computed_at":"2026-05-29T01:04:35.687741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:35.687741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fz7UBItrPoFgnniF73l0MiUyxKrxJ8OzgBXYiCH9jGlYblBz+ONTR37Aka9eofYOoN+m+3eqJYhcpHb2yO4cBQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:35.688382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.20904","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:821bd0988965ec4de7f1e62dc3034a39f3ab549c3b2a76b1e9dc26cf66ef40f1","sha256:d2df33bdf32c29862f4e020c110c0aa339bd86e96397fa3396dacce8c0fb6dd3"],"state_sha256":"7225b74d873f3ccb00c622ed4263ea5a6314e74418c7997c8ad5406178364869"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"StSLtEBkveVGB5lzpOk/ifi1rmZ5wo8C+muOSBfEMJE/6R5rH1EvGTBPtHOkr46J6/w3RxiQDg26lLmSTstNBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T08:48:49.981868Z","bundle_sha256":"2f92de581813d6fc6d909eaf4c63d4dba0cbaf0e20e400d286a6c3a0571b577d"}}