{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XW2NIGP5C4GTODSR56MDHOJXVS","short_pith_number":"pith:XW2NIGP5","canonical_record":{"source":{"id":"2406.04383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T05:54:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7d83c55f9d42e716a4efad775760e3790dae64cdb324025138fa753089dec09","abstract_canon_sha256":"961e945b3505cb8e53a7e2c0dcd9edb1533a0b53cec30bb1d5674b4bf62eef78"},"schema_version":"1.0"},"canonical_sha256":"bdb4d419fd170d370e51ef9833b937aca6c7b375572196b6e42d4c2225d4deee","source":{"kind":"arxiv","id":"2406.04383","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04383","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04383v2","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04383","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"pith_short_12","alias_value":"XW2NIGP5C4GT","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"pith_short_16","alias_value":"XW2NIGP5C4GTODSR","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"pith_short_8","alias_value":"XW2NIGP5","created_at":"2026-07-05T08:41:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XW2NIGP5C4GTODSR56MDHOJXVS","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T05:54:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7d83c55f9d42e716a4efad775760e3790dae64cdb324025138fa753089dec09","abstract_canon_sha256":"961e945b3505cb8e53a7e2c0dcd9edb1533a0b53cec30bb1d5674b4bf62eef78"},"schema_version":"1.0"},"canonical_sha256":"bdb4d419fd170d370e51ef9833b937aca6c7b375572196b6e42d4c2225d4deee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:26.969424Z","signature_b64":"mOveUWPSg08nprE3Bi3Kg0A9JtX3Q6sAwHNedrXrP+cQkzzJ/ijBscRy4AS4fr5lQTkvVT4snF6Gcc0Ky1FxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdb4d419fd170d370e51ef9833b937aca6c7b375572196b6e42d4c2225d4deee","last_reissued_at":"2026-07-05T08:41:26.968946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:26.968946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04383","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:41:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N8jcUUyanvoFzza3bLd9n2NnaxjA66nIgatLZcAEcJO22H3APL1/TYtGEuLfY5W+MGLmkun859e5zgnysGf1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:54:38.515969Z"},"content_sha256":"c3523c2c2400237a6c403ee10b3a7f7944e8e81a1a6891e947f59c8ab58f101a","schema_version":"1.0","event_id":"sha256:c3523c2c2400237a6c403ee10b3a7f7944e8e81a1a6891e947f59c8ab58f101a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XW2NIGP5C4GTODSR56MDHOJXVS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Latest LLMs for Leaderboard Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jennifer D'Souza, Salomon Kabongo, S\\\"oren Auer","submitted_at":"2024-06-06T05:54:45Z","abstract_excerpt":"The rapid advancements in Large Language Models (LLMs) have opened new avenues for automating complex tasks in AI research. This paper investigates the efficacy of different LLMs-Mistral 7B, Llama-2, GPT-4-Turbo and GPT-4.o in extracting leaderboard information from empirical AI research articles. We explore three types of contextual inputs to the models: DocTAET (Document Title, Abstract, Experimental Setup, and Tabular Information), DocREC (Results, Experiments, and Conclusions), and DocFULL (entire document). Our comprehensive study evaluates the performance of these models in generating (T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04383","kind":"arxiv","version":2},"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/2406.04383/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":"2026-07-05T08:41:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f1aNIGvRXW6uoCqXygP+/V9vL7Vc4NlCKeHOiB3LQ4jCqlWIYoeVFSng2uy6eCk49wf29wt7n8yPvC58Mk1HAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:54:38.516481Z"},"content_sha256":"f457b173449b9ab060b87bde6bc02cb077587aa77a1b78461825aa5e5f239bfe","schema_version":"1.0","event_id":"sha256:f457b173449b9ab060b87bde6bc02cb077587aa77a1b78461825aa5e5f239bfe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XW2NIGP5C4GTODSR56MDHOJXVS/bundle.json","state_url":"https://pith.science/pith/XW2NIGP5C4GTODSR56MDHOJXVS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XW2NIGP5C4GTODSR56MDHOJXVS/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":"2026-08-19T09:54:38Z","links":{"resolver":"https://pith.science/pith/XW2NIGP5C4GTODSR56MDHOJXVS","bundle":"https://pith.science/pith/XW2NIGP5C4GTODSR56MDHOJXVS/bundle.json","state":"https://pith.science/pith/XW2NIGP5C4GTODSR56MDHOJXVS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XW2NIGP5C4GTODSR56MDHOJXVS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XW2NIGP5C4GTODSR56MDHOJXVS","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":"961e945b3505cb8e53a7e2c0dcd9edb1533a0b53cec30bb1d5674b4bf62eef78","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T05:54:45Z","title_canon_sha256":"b7d83c55f9d42e716a4efad775760e3790dae64cdb324025138fa753089dec09"},"schema_version":"1.0","source":{"id":"2406.04383","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04383","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04383v2","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04383","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"pith_short_12","alias_value":"XW2NIGP5C4GT","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"pith_short_16","alias_value":"XW2NIGP5C4GTODSR","created_at":"2026-07-05T08:41:26Z"},{"alias_kind":"pith_short_8","alias_value":"XW2NIGP5","created_at":"2026-07-05T08:41:26Z"}],"graph_snapshots":[{"event_id":"sha256:f457b173449b9ab060b87bde6bc02cb077587aa77a1b78461825aa5e5f239bfe","target":"graph","created_at":"2026-07-05T08:41:26Z","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/2406.04383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancements in Large Language Models (LLMs) have opened new avenues for automating complex tasks in AI research. This paper investigates the efficacy of different LLMs-Mistral 7B, Llama-2, GPT-4-Turbo and GPT-4.o in extracting leaderboard information from empirical AI research articles. We explore three types of contextual inputs to the models: DocTAET (Document Title, Abstract, Experimental Setup, and Tabular Information), DocREC (Results, Experiments, and Conclusions), and DocFULL (entire document). Our comprehensive study evaluates the performance of these models in generating (T","authors_text":"Jennifer D'Souza, Salomon Kabongo, S\\\"oren Auer","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T05:54:45Z","title":"Exploring the Latest LLMs for Leaderboard Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04383","kind":"arxiv","version":2},"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:c3523c2c2400237a6c403ee10b3a7f7944e8e81a1a6891e947f59c8ab58f101a","target":"record","created_at":"2026-07-05T08:41:26Z","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":"961e945b3505cb8e53a7e2c0dcd9edb1533a0b53cec30bb1d5674b4bf62eef78","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-06T05:54:45Z","title_canon_sha256":"b7d83c55f9d42e716a4efad775760e3790dae64cdb324025138fa753089dec09"},"schema_version":"1.0","source":{"id":"2406.04383","kind":"arxiv","version":2}},"canonical_sha256":"bdb4d419fd170d370e51ef9833b937aca6c7b375572196b6e42d4c2225d4deee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdb4d419fd170d370e51ef9833b937aca6c7b375572196b6e42d4c2225d4deee","first_computed_at":"2026-07-05T08:41:26.968946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:41:26.968946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mOveUWPSg08nprE3Bi3Kg0A9JtX3Q6sAwHNedrXrP+cQkzzJ/ijBscRy4AS4fr5lQTkvVT4snF6Gcc0Ky1FxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:41:26.969424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04383","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3523c2c2400237a6c403ee10b3a7f7944e8e81a1a6891e947f59c8ab58f101a","sha256:f457b173449b9ab060b87bde6bc02cb077587aa77a1b78461825aa5e5f239bfe"],"state_sha256":"189e011dca9c4e5b99460bffc56a78a945eb1eb2522491c17ac3b43c51bb9c5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdlCcFdD79zhCwSv3Xyr7taBJ2qWsuqgkDMW9Ra+rvGzPDWC7n+t7JndymH2aGWbIoExbLo3EVZJTHu6MNSvAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:54:38.520487Z","bundle_sha256":"69118462f876a28b3c56b214ec1977ef09c51ed732e1f4f8f6750a072039d635"}}