{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AG6M6SE6PCCZQXLKJDTPNA6G3T","short_pith_number":"pith:AG6M6SE6","canonical_record":{"source":{"id":"2308.08031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.ST","submitted_at":"2023-08-15T20:45:51Z","cross_cats_sorted":["q-fin.CP","stat.AP"],"title_canon_sha256":"0c48b77d45819f6c710f48134a2a337c5bc7c134a2b7fc1a9f73da5ae8904484","abstract_canon_sha256":"75ae15763144160b85ae9612faabef3f4e92f7d94d635f1f483262005b4a668f"},"schema_version":"1.0"},"canonical_sha256":"01bccf489e7885985d6a48e6f683c6dcf570926933976896b9212ed630d745a3","source":{"kind":"arxiv","id":"2308.08031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.08031","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"arxiv_version","alias_value":"2308.08031v1","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08031","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"pith_short_12","alias_value":"AG6M6SE6PCCZ","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"pith_short_16","alias_value":"AG6M6SE6PCCZQXLK","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"pith_short_8","alias_value":"AG6M6SE6","created_at":"2026-07-05T06:41:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AG6M6SE6PCCZQXLKJDTPNA6G3T","target":"record","payload":{"canonical_record":{"source":{"id":"2308.08031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.ST","submitted_at":"2023-08-15T20:45:51Z","cross_cats_sorted":["q-fin.CP","stat.AP"],"title_canon_sha256":"0c48b77d45819f6c710f48134a2a337c5bc7c134a2b7fc1a9f73da5ae8904484","abstract_canon_sha256":"75ae15763144160b85ae9612faabef3f4e92f7d94d635f1f483262005b4a668f"},"schema_version":"1.0"},"canonical_sha256":"01bccf489e7885985d6a48e6f683c6dcf570926933976896b9212ed630d745a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:53.377334Z","signature_b64":"RgrbXDYHnKQkybq1ax6t4Lm5Jieb0fzYzQqJsakY8QNSbVIFO772INvZdLiFoY3N7TXATJfLWhBBmwP7frX6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01bccf489e7885985d6a48e6f683c6dcf570926933976896b9212ed630d745a3","last_reissued_at":"2026-07-05T06:41:53.376767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:53.376767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.08031","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":"2026-07-05T06:41:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"11f+KKJ5r4W5svNASX2HoBpAYooQMtmDwlN1K0ERg9uCE0Y9x/eAJPeeht3YpHq64NnR2IATYEHfURBtNcNaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:23:55.672025Z"},"content_sha256":"db8cf91a6b2a06ca76de734a40f626fb2f70698a77fb8ccf6a1ce2893677a62c","schema_version":"1.0","event_id":"sha256:db8cf91a6b2a06ca76de734a40f626fb2f70698a77fb8ccf6a1ce2893677a62c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AG6M6SE6PCCZQXLKJDTPNA6G3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Company Similarity using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.CP","stat.AP"],"primary_cat":"q-fin.ST","authors_text":"Dhagash Mehta, Dhruv Desai, Dimitrios Vamvourellis, M\\'at\\'e Toth, Snigdha Bhagat, Stefano Pasquali","submitted_at":"2023-08-15T20:45:51Z","abstract_excerpt":"Identifying companies with similar profiles is a core task in finance with a wide range of applications in portfolio construction, asset pricing and risk attribution. When a rigorous definition of similarity is lacking, financial analysts usually resort to 'traditional' industry classifications such as Global Industry Classification System (GICS) which assign a unique category to each company at different levels of granularity. Due to their discrete nature, though, GICS classifications do not allow for ranking companies in terms of similarity. In this paper, we explore the ability of pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08031","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/2308.08031/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":"2026-07-05T06:41:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AWbPSsFsaJ/W6D4Omd6ITXEbb7Nw/bfqpjCaRjEsAK5smM0RfTbJzZzJ4A3p9DKfl9NODDs5v4NtEDbReYfRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:23:55.672560Z"},"content_sha256":"36acdfa29cf03a3d747e2fdc0edf0b66e8bb855066925dcaec02b98461a7e27b","schema_version":"1.0","event_id":"sha256:36acdfa29cf03a3d747e2fdc0edf0b66e8bb855066925dcaec02b98461a7e27b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AG6M6SE6PCCZQXLKJDTPNA6G3T/bundle.json","state_url":"https://pith.science/pith/AG6M6SE6PCCZQXLKJDTPNA6G3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AG6M6SE6PCCZQXLKJDTPNA6G3T/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":"2026-08-06T07:23:55Z","links":{"resolver":"https://pith.science/pith/AG6M6SE6PCCZQXLKJDTPNA6G3T","bundle":"https://pith.science/pith/AG6M6SE6PCCZQXLKJDTPNA6G3T/bundle.json","state":"https://pith.science/pith/AG6M6SE6PCCZQXLKJDTPNA6G3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AG6M6SE6PCCZQXLKJDTPNA6G3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AG6M6SE6PCCZQXLKJDTPNA6G3T","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":"75ae15763144160b85ae9612faabef3f4e92f7d94d635f1f483262005b4a668f","cross_cats_sorted":["q-fin.CP","stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.ST","submitted_at":"2023-08-15T20:45:51Z","title_canon_sha256":"0c48b77d45819f6c710f48134a2a337c5bc7c134a2b7fc1a9f73da5ae8904484"},"schema_version":"1.0","source":{"id":"2308.08031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.08031","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"arxiv_version","alias_value":"2308.08031v1","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08031","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"pith_short_12","alias_value":"AG6M6SE6PCCZ","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"pith_short_16","alias_value":"AG6M6SE6PCCZQXLK","created_at":"2026-07-05T06:41:53Z"},{"alias_kind":"pith_short_8","alias_value":"AG6M6SE6","created_at":"2026-07-05T06:41:53Z"}],"graph_snapshots":[{"event_id":"sha256:36acdfa29cf03a3d747e2fdc0edf0b66e8bb855066925dcaec02b98461a7e27b","target":"graph","created_at":"2026-07-05T06:41:53Z","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/2308.08031/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying companies with similar profiles is a core task in finance with a wide range of applications in portfolio construction, asset pricing and risk attribution. When a rigorous definition of similarity is lacking, financial analysts usually resort to 'traditional' industry classifications such as Global Industry Classification System (GICS) which assign a unique category to each company at different levels of granularity. Due to their discrete nature, though, GICS classifications do not allow for ranking companies in terms of similarity. In this paper, we explore the ability of pre-train","authors_text":"Dhagash Mehta, Dhruv Desai, Dimitrios Vamvourellis, M\\'at\\'e Toth, Snigdha Bhagat, Stefano Pasquali","cross_cats":["q-fin.CP","stat.AP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.ST","submitted_at":"2023-08-15T20:45:51Z","title":"Company Similarity using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08031","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:db8cf91a6b2a06ca76de734a40f626fb2f70698a77fb8ccf6a1ce2893677a62c","target":"record","created_at":"2026-07-05T06:41:53Z","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":"75ae15763144160b85ae9612faabef3f4e92f7d94d635f1f483262005b4a668f","cross_cats_sorted":["q-fin.CP","stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.ST","submitted_at":"2023-08-15T20:45:51Z","title_canon_sha256":"0c48b77d45819f6c710f48134a2a337c5bc7c134a2b7fc1a9f73da5ae8904484"},"schema_version":"1.0","source":{"id":"2308.08031","kind":"arxiv","version":1}},"canonical_sha256":"01bccf489e7885985d6a48e6f683c6dcf570926933976896b9212ed630d745a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01bccf489e7885985d6a48e6f683c6dcf570926933976896b9212ed630d745a3","first_computed_at":"2026-07-05T06:41:53.376767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:53.376767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RgrbXDYHnKQkybq1ax6t4Lm5Jieb0fzYzQqJsakY8QNSbVIFO772INvZdLiFoY3N7TXATJfLWhBBmwP7frX6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:53.377334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.08031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db8cf91a6b2a06ca76de734a40f626fb2f70698a77fb8ccf6a1ce2893677a62c","sha256:36acdfa29cf03a3d747e2fdc0edf0b66e8bb855066925dcaec02b98461a7e27b"],"state_sha256":"6ce550651ec1313dc1430e9334c8bda7084667046644d160befcd81095dfd306"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ufQO8XqEfNBcX9LBh91F2M6GpuyDccQQ9TtrgOBDNRnXS7ji1q9BplBJPo30Y+ZT6mpMDOPMz57rLp7NO2loCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:23:55.677640Z","bundle_sha256":"73240a112986027b884c6581d0cff3c392cabc06f86b962832bf9ae5a7684608"}}