{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V7Z7EG6BCK5ERVXJK5YIG7TZ3N","short_pith_number":"pith:V7Z7EG6B","canonical_record":{"source":{"id":"2508.01643","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-03T08:04:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c631355cbe77dbe2c8cda6c14117d741bc234b7c52f000b33df30366899600f0","abstract_canon_sha256":"f71727359e65e4bd7c223dbc46eb9462e994ad0456150dd84bbd4d9115d557b1"},"schema_version":"1.0"},"canonical_sha256":"aff3f21bc112ba48d6e95770837e79db793c4565da8356ee66d94f0392b51327","source":{"kind":"arxiv","id":"2508.01643","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01643","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01643v1","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01643","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_12","alias_value":"V7Z7EG6BCK5E","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_16","alias_value":"V7Z7EG6BCK5ERVXJ","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_8","alias_value":"V7Z7EG6B","created_at":"2026-07-05T11:47:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V7Z7EG6BCK5ERVXJK5YIG7TZ3N","target":"record","payload":{"canonical_record":{"source":{"id":"2508.01643","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-03T08:04:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c631355cbe77dbe2c8cda6c14117d741bc234b7c52f000b33df30366899600f0","abstract_canon_sha256":"f71727359e65e4bd7c223dbc46eb9462e994ad0456150dd84bbd4d9115d557b1"},"schema_version":"1.0"},"canonical_sha256":"aff3f21bc112ba48d6e95770837e79db793c4565da8356ee66d94f0392b51327","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:42.805139Z","signature_b64":"e5k8o2Tbi4wtODPMZkmELCQvuQuAJz6hLyOd5XMPAxIKI4ZHxIZmaDz1SmM+89JZmcQDt11ly491u6te5IaRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aff3f21bc112ba48d6e95770837e79db793c4565da8356ee66d94f0392b51327","last_reissued_at":"2026-07-05T11:47:42.804683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:42.804683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.01643","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":"2026-07-05T11:47:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nn+T3Pgp5EaUbePENI9xYdbWWkRdjEVAWFJA93jDZHJVKj+x7YIvCP4JWrrTOeFq4NS6HZMGSEzxLjiN0myYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:10:20.497547Z"},"content_sha256":"4563fbb306b9b59984fc5b188a5fdf10198c76ea2020494b7dc59308a0c77133","schema_version":"1.0","event_id":"sha256:4563fbb306b9b59984fc5b188a5fdf10198c76ea2020494b7dc59308a0c77133"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V7Z7EG6BCK5ERVXJK5YIG7TZ3N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ali Shiraee Kasmaee, Hamidreza Mahyar, Mehdi Astaraki, Mohammad Arshi Saloot, Mohammad Khodadad, Nicholas Sherck, Soheila Samiee","submitted_at":"2025-08-03T08:04:44Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems in chemistry heavily depend on accurate and relevant retrieval of chemical literature. However, general-purpose text embedding models frequently fail to adequately represent complex chemical terminologies, resulting in suboptimal retrieval quality. Specialized embedding models tailored to chemical literature retrieval have not yet been developed, leaving a substantial performance gap. To address this challenge, we introduce ChEmbed, a domain-adapted family of text embedding models fine-tuned on a dataset comprising chemistry-specific text from the P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01643","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/2508.01643/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":"2026-07-05T11:47:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVZ8svY//7pp5QfzI9ayZc7+ceiYBzBgEhvL88dE4VphWIlwIaPIQaVs1eErBiRAYVB4hlWnWRooRULlTmHtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:10:20.498052Z"},"content_sha256":"6ff953eb09f4ec48220a69247fd2b2d9602fca103e607e2f588a53a3b25785ab","schema_version":"1.0","event_id":"sha256:6ff953eb09f4ec48220a69247fd2b2d9602fca103e607e2f588a53a3b25785ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7Z7EG6BCK5ERVXJK5YIG7TZ3N/bundle.json","state_url":"https://pith.science/pith/V7Z7EG6BCK5ERVXJK5YIG7TZ3N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7Z7EG6BCK5ERVXJK5YIG7TZ3N/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":"2026-08-18T09:10:20Z","links":{"resolver":"https://pith.science/pith/V7Z7EG6BCK5ERVXJK5YIG7TZ3N","bundle":"https://pith.science/pith/V7Z7EG6BCK5ERVXJK5YIG7TZ3N/bundle.json","state":"https://pith.science/pith/V7Z7EG6BCK5ERVXJK5YIG7TZ3N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7Z7EG6BCK5ERVXJK5YIG7TZ3N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V7Z7EG6BCK5ERVXJK5YIG7TZ3N","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":"f71727359e65e4bd7c223dbc46eb9462e994ad0456150dd84bbd4d9115d557b1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-03T08:04:44Z","title_canon_sha256":"c631355cbe77dbe2c8cda6c14117d741bc234b7c52f000b33df30366899600f0"},"schema_version":"1.0","source":{"id":"2508.01643","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01643","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01643v1","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01643","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_12","alias_value":"V7Z7EG6BCK5E","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_16","alias_value":"V7Z7EG6BCK5ERVXJ","created_at":"2026-07-05T11:47:42Z"},{"alias_kind":"pith_short_8","alias_value":"V7Z7EG6B","created_at":"2026-07-05T11:47:42Z"}],"graph_snapshots":[{"event_id":"sha256:6ff953eb09f4ec48220a69247fd2b2d9602fca103e607e2f588a53a3b25785ab","target":"graph","created_at":"2026-07-05T11:47:42Z","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/2508.01643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems in chemistry heavily depend on accurate and relevant retrieval of chemical literature. However, general-purpose text embedding models frequently fail to adequately represent complex chemical terminologies, resulting in suboptimal retrieval quality. Specialized embedding models tailored to chemical literature retrieval have not yet been developed, leaving a substantial performance gap. To address this challenge, we introduce ChEmbed, a domain-adapted family of text embedding models fine-tuned on a dataset comprising chemistry-specific text from the P","authors_text":"Ali Shiraee Kasmaee, Hamidreza Mahyar, Mehdi Astaraki, Mohammad Arshi Saloot, Mohammad Khodadad, Nicholas Sherck, Soheila Samiee","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-03T08:04:44Z","title":"ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01643","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":"sha256:4563fbb306b9b59984fc5b188a5fdf10198c76ea2020494b7dc59308a0c77133","target":"record","created_at":"2026-07-05T11:47:42Z","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":"f71727359e65e4bd7c223dbc46eb9462e994ad0456150dd84bbd4d9115d557b1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-03T08:04:44Z","title_canon_sha256":"c631355cbe77dbe2c8cda6c14117d741bc234b7c52f000b33df30366899600f0"},"schema_version":"1.0","source":{"id":"2508.01643","kind":"arxiv","version":1}},"canonical_sha256":"aff3f21bc112ba48d6e95770837e79db793c4565da8356ee66d94f0392b51327","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aff3f21bc112ba48d6e95770837e79db793c4565da8356ee66d94f0392b51327","first_computed_at":"2026-07-05T11:47:42.804683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:42.804683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e5k8o2Tbi4wtODPMZkmELCQvuQuAJz6hLyOd5XMPAxIKI4ZHxIZmaDz1SmM+89JZmcQDt11ly491u6te5IaRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:42.805139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01643","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4563fbb306b9b59984fc5b188a5fdf10198c76ea2020494b7dc59308a0c77133","sha256:6ff953eb09f4ec48220a69247fd2b2d9602fca103e607e2f588a53a3b25785ab"],"state_sha256":"f66dfb74926b11a3ca9b50e04639e6d2bdbb0815140242e58feb42cf2ab3dcf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vpWyzmVjBP2nsOfD46gND/vDRfHVlW6cs93+68ZfjDTFeWxynr/pab9SgxO2Jc8pli94DvGTCyI9HN8h15TiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:10:20.503918Z","bundle_sha256":"b9144d8cf0157662cb29c927b70c8f603aaaf8892c0ef08380e40218771e7b1e"}}