{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RZC5SVGGNLHYAUQY57IYVROVS3","short_pith_number":"pith:RZC5SVGG","canonical_record":{"source":{"id":"2305.04177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T03:29:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"349a1bdba6d6692856afe51f9077c25167419f9d4733ce0f3312cb4f0ca8b6b6","abstract_canon_sha256":"8d2d6afca206707cf52df19a7317c81c472c0d97a324b66f44723e562943c552"},"schema_version":"1.0"},"canonical_sha256":"8e45d954c66acf805218efd18ac5d596ccde27b535b09c6fa14f27cebf8eb4e6","source":{"kind":"arxiv","id":"2305.04177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04177","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04177v1","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04177","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"pith_short_12","alias_value":"RZC5SVGGNLHY","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"pith_short_16","alias_value":"RZC5SVGGNLHYAUQY","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"pith_short_8","alias_value":"RZC5SVGG","created_at":"2026-07-05T06:07:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RZC5SVGGNLHYAUQY57IYVROVS3","target":"record","payload":{"canonical_record":{"source":{"id":"2305.04177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T03:29:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"349a1bdba6d6692856afe51f9077c25167419f9d4733ce0f3312cb4f0ca8b6b6","abstract_canon_sha256":"8d2d6afca206707cf52df19a7317c81c472c0d97a324b66f44723e562943c552"},"schema_version":"1.0"},"canonical_sha256":"8e45d954c66acf805218efd18ac5d596ccde27b535b09c6fa14f27cebf8eb4e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:45.459944Z","signature_b64":"Lt/R40aQ/GmwYgqmSjaKsQIO+saVTA7/waVJQbLnh+jtAJYbwZ8UzqTc3MVpQDKyvAbElZbz67o0DcatyBwbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e45d954c66acf805218efd18ac5d596ccde27b535b09c6fa14f27cebf8eb4e6","last_reissued_at":"2026-07-05T06:07:45.459564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:45.459564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.04177","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":"2026-07-05T06:07:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iwn7tp+DSV5nWl2YiudFn8LiXdQwKZZxGao8cVVNyt85JCIxE8P2b8APHBOVxCkbrPwbx2KzsDMkQOk67TiVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:51:18.303144Z"},"content_sha256":"41d5e4a7334e430484bd0e6b5f747aef1b8dd69a80b12fc508390b90e482dd0b","schema_version":"1.0","event_id":"sha256:41d5e4a7334e430484bd0e6b5f747aef1b8dd69a80b12fc508390b90e482dd0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RZC5SVGGNLHYAUQY57IYVROVS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexander Brechalov, Anastasia Razdaibiedina","submitted_at":"2023-05-07T03:29:55Z","abstract_excerpt":"Learning semantically meaningful representations from scientific documents can facilitate academic literature search and improve performance of recommendation systems. Pre-trained language models have been shown to learn rich textual representations, yet they cannot provide powerful document-level representations for scientific articles. We propose MIReAD, a simple method that learns high-quality representations of scientific papers by fine-tuning transformer model to predict the target journal class based on the abstract. We train MIReAD on more than 500,000 PubMed and arXiv abstracts across "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04177","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/2305.04177/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":"2026-07-05T06:07:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"24Psx3QZwTMZT0GoXy4wzN69u3QGhEaj/APmpJVPjwXSxuPXV+2KFoqUMK5um9NCu3wPU65ifGkxUOn4F/paCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:51:18.304131Z"},"content_sha256":"572baafc260a265ad0d03d718dc7b808c4dfdbfce0bd5f601d51b1236fbc5f28","schema_version":"1.0","event_id":"sha256:572baafc260a265ad0d03d718dc7b808c4dfdbfce0bd5f601d51b1236fbc5f28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/bundle.json","state_url":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZC5SVGGNLHYAUQY57IYVROVS3/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":"2026-08-19T13:51:18Z","links":{"resolver":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3","bundle":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/bundle.json","state":"https://pith.science/pith/RZC5SVGGNLHYAUQY57IYVROVS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZC5SVGGNLHYAUQY57IYVROVS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RZC5SVGGNLHYAUQY57IYVROVS3","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":"8d2d6afca206707cf52df19a7317c81c472c0d97a324b66f44723e562943c552","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T03:29:55Z","title_canon_sha256":"349a1bdba6d6692856afe51f9077c25167419f9d4733ce0f3312cb4f0ca8b6b6"},"schema_version":"1.0","source":{"id":"2305.04177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.04177","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"arxiv_version","alias_value":"2305.04177v1","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04177","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"pith_short_12","alias_value":"RZC5SVGGNLHY","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"pith_short_16","alias_value":"RZC5SVGGNLHYAUQY","created_at":"2026-07-05T06:07:45Z"},{"alias_kind":"pith_short_8","alias_value":"RZC5SVGG","created_at":"2026-07-05T06:07:45Z"}],"graph_snapshots":[{"event_id":"sha256:572baafc260a265ad0d03d718dc7b808c4dfdbfce0bd5f601d51b1236fbc5f28","target":"graph","created_at":"2026-07-05T06:07:45Z","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/2305.04177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning semantically meaningful representations from scientific documents can facilitate academic literature search and improve performance of recommendation systems. Pre-trained language models have been shown to learn rich textual representations, yet they cannot provide powerful document-level representations for scientific articles. We propose MIReAD, a simple method that learns high-quality representations of scientific papers by fine-tuning transformer model to predict the target journal class based on the abstract. We train MIReAD on more than 500,000 PubMed and arXiv abstracts across ","authors_text":"Alexander Brechalov, Anastasia Razdaibiedina","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T03:29:55Z","title":"MIReAD: Simple Method for Learning High-quality Representations from Scientific Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04177","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":"sha256:41d5e4a7334e430484bd0e6b5f747aef1b8dd69a80b12fc508390b90e482dd0b","target":"record","created_at":"2026-07-05T06:07:45Z","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":"8d2d6afca206707cf52df19a7317c81c472c0d97a324b66f44723e562943c552","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-07T03:29:55Z","title_canon_sha256":"349a1bdba6d6692856afe51f9077c25167419f9d4733ce0f3312cb4f0ca8b6b6"},"schema_version":"1.0","source":{"id":"2305.04177","kind":"arxiv","version":1}},"canonical_sha256":"8e45d954c66acf805218efd18ac5d596ccde27b535b09c6fa14f27cebf8eb4e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e45d954c66acf805218efd18ac5d596ccde27b535b09c6fa14f27cebf8eb4e6","first_computed_at":"2026-07-05T06:07:45.459564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:45.459564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lt/R40aQ/GmwYgqmSjaKsQIO+saVTA7/waVJQbLnh+jtAJYbwZ8UzqTc3MVpQDKyvAbElZbz67o0DcatyBwbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:45.459944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.04177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41d5e4a7334e430484bd0e6b5f747aef1b8dd69a80b12fc508390b90e482dd0b","sha256:572baafc260a265ad0d03d718dc7b808c4dfdbfce0bd5f601d51b1236fbc5f28"],"state_sha256":"599e1643d364c2cd1ccad03e7b4b926f5c5833a96685f171f67498a5f084846a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w/qxMPyIRp9zMl808zqvOHPGsqR7aksgvzkyJKo9GQMi8WeHEwUGBRvAfHP8FUeFa3daVXexD0uRH7whNUTGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T13:51:18.313559Z","bundle_sha256":"b2d5299bc9a79e6f99658a3eb01c9df219e6e838ccda8a2fa5ef19c798adcb53"}}