{"as_of":"2026-08-09T15:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:993e7cd1abe5d2230d58585e82dd04e5500d6e5ead2b88b40ce0186e5bb38857","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:12:54.713185Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T10:10:16.661082Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"cited_work":{"arxiv_id":"2506.00232","doi":"10.48550/arxiv.2506.00232","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.00232","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Composerag: A modular and composable rag for corpus-grounded multi-hop question answering","venue":"ArXiv.org","work_id":"3876e29f-55b0-48ca-8921-692cbeb7eb66","year":2025},"citing_paper":{"arxiv_id":"2602.13933","last_updated":"2026-05-01T05:12:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-02-15T00:06:19Z","title":"HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-15T21:58:30.784843Z"},"links":{"cited_paper":"/paper/2506.00232","citing_paper":"/paper/2602.13933"},"observation_digest":"sha256:9d211717f1d24a79ae78edc417fba6e0b6747aeaf5ff5c3e3f6fda1b8cd2a512","observation_id":"f139c760-df11-44b1-8871-f49f6d4df90d","resolution":{"observed_at":"2026-05-15T22:00:21.266812Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"cited_work":{"arxiv_id":"2506.00232","doi":"10.48550/arxiv.2506.00232","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.00232","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Composerag: A modular and composable rag for corpus-grounded multi-hop question answering","venue":"ArXiv.org","work_id":"3876e29f-55b0-48ca-8921-692cbeb7eb66","year":2025},"citing_paper":{"arxiv_id":"2606.22681","last_updated":"2026-06-21T21:46:41Z","snapshot_observed_at":"2026-08-01T21:45:47.385301Z","submitted_at":"2026-06-21T21:46:41Z","title":"Only Ask What You Don't Know: Grounded Delta Planning for Efficient Multi-step RAG","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-06-26T10:10:16.661082Z"},"links":{"cited_paper":"/paper/2506.00232","citing_paper":"/paper/2606.22681"},"observation_digest":"sha256:372ea271c7b27f8432064c8dfeddff3e468ece8d97724cce83ffd1d189c0d1e7","observation_id":"78ef1a62-cf3f-42fc-bd24-7bddc102dfa8","resolution":{"observed_at":"2026-06-26T10:29:19.107085Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.00232/citation-record","integrity":"/paper/2506.00232/integrity","json":"/paper/2506.00232/citation-record.json","paper":"/paper/2506.00232"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T12:12:50.274162Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.274162Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:f74f28149ec7bebee2710d600474ab0ad3a7468b48838c11aa84bdcccbe4501e","observation_id":"2a2bf7f1-6168-418f-9d7f-facdaa496068","resolution":{"observed_at":"2026-08-07T12:12:50.274162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14732","last_updated":"2024-09-30T21:25:22Z","snapshot_observed_at":"2026-07-06T18:34:33.717998Z","submitted_at":"2024-06-20T20:55:38Z","title":"TTQA-RS- A break-down prompting approach for Multi-hop Table-Text Question Answering with Reasoning and Summarization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14732","snapshot_observed_at":"2026-08-07T12:12:50.290909Z","title":"Ttqa-rs -a break-down prompting approach for multi-hop table-text question answering with reasonin g and summarization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.290909Z"},"links":{"cited_paper":"/paper/2406.14732","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:ddc41b63d5d1ee06664c3cde9ce36aa6e2c854457d86408737438e5c45060264","observation_id":"dd702a8f-5c22-46f7-8d1e-02968d455bfc","resolution":{"observed_at":"2026-08-07T12:12:50.290909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:13:00.479944Z","title":"Improving language models by retrieving from trillio ns of tokens","venue":null,"work_id":"f12c7559-f2d8-4a11-adaf-6c803b8de2c9","year":2022},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.364185Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:6fba1d75d07b5c1d6f308770c4bc7f6d7dbd63ee61a3de00ec1ac5d2312394fc","observation_id":"b064e2a9-c739-4dfa-be29-493fc44a2157","resolution":{"observed_at":"2026-08-07T12:13:00.673102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:13:00.210479Z","title":"Language mod- els are few-shot learners","venue":null,"work_id":"f7064d16-8e40-4c22-8dc1-2e39e0b4e1a4","year":1901},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.468576Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:868d6d73d94f9ad92997071f7aa44dc833745e330d6c1829a880ded6c66da2cd","observation_id":"7080d842-fdcb-46eb-8cdb-22fef5200e34","resolution":{"observed_at":"2026-08-07T12:13:00.332325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00610","last_updated":"2024-03-31T08:58:54Z","snapshot_observed_at":"2026-08-09T13:15:07.647793Z","submitted_at":"2024-03-31T08:58:54Z","title":"RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.00610","snapshot_observed_at":"2026-08-07T12:12:50.516414Z","title":"Rq-rag: Learning to refine queries for retrieval augment ed generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.516414Z"},"links":{"cited_paper":"/paper/2404.00610","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:803667c767fdd5c8cac4e17376ea76f8f59b2baa50dcec0139db18cec0a580d7","observation_id":"b046fa8a-8a51-4e6d-8db0-bd6e083d1a6b","resolution":{"observed_at":"2026-08-07T12:12:50.516414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08281","last_updated":"2025-10-23T09:36:08Z","snapshot_observed_at":"2026-07-31T05:45:37.385210Z","submitted_at":"2024-01-16T11:12:36Z","title":"The Faiss library","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08281","snapshot_observed_at":"2026-08-07T12:12:50.552759Z","title":"The faiss library","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.552759Z"},"links":{"cited_paper":"/paper/2401.08281","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:b260a1d85cfce7b98fa5a1b34e0b32e2f6cbcfc0ae39446c3772320356bebd43","observation_id":"6b94b0bd-c26c-48e6-a1a2-7bed17040264","resolution":{"observed_at":"2026-08-07T12:12:50.552759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T12:12:50.601126Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.601126Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:4d40c9b5bcecc8fb71047d637b1be7bee31210211b5f58596ec4d592ce00ce8c","observation_id":"7baadc78-0fc9-4f33-a3cf-ac18fd19ebf8","resolution":{"observed_at":"2026-08-07T12:12:50.601126Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.15594","last_updated":"2025-10-19T10:32:43Z","snapshot_observed_at":"2026-08-02T10:23:50.881300Z","submitted_at":"2024-11-23T16:03:35Z","title":"A Survey on LLM-as-a-Judge","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.15594","snapshot_observed_at":"2026-08-07T12:12:50.636543Z","title":"A survey on llm-as- a-judge","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.636543Z"},"links":{"cited_paper":"/paper/2411.15594","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:d1a940b39fb15d41c06a282b11c06e8701da6038163542ca269f3eaf7f28dbf6","observation_id":"a5d51a28-9a72-4cd4-a445-3a32da3b6fc9","resolution":{"observed_at":"2026-08-07T12:12:50.636543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:50.726961Z","title":"Retrieval aug- mented language model pre-training","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.726961Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:f4d85f2f1c180d7259bf280a5023bc76c3f3506727e0e5bfb243403d18025e92","observation_id":"33eb8edf-0a14-4353-b588-284847dc739a","resolution":{"observed_at":"2026-08-07T12:12:50.726961Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.01060","last_updated":"2020-11-12T07:47:48Z","snapshot_observed_at":"2026-07-06T10:10:56.466018Z","submitted_at":"2020-11-02T15:42:40Z","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.01060","snapshot_observed_at":"2026-08-07T12:12:50.772066Z","title":"Constructing a multi-hop qa dataset for comprehensive evaluation of reas oning steps","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.772066Z"},"links":{"cited_paper":"/paper/2011.01060","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:30adbfb2007081e7d8cc8b6f8828b0579bebf53f8e6a060f3fc667b1eeb59257","observation_id":"9a6544ff-3691-471b-98e4-9a9173de2af9","resolution":{"observed_at":"2026-08-07T12:12:50.772066Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:59.972404Z","title":"Atlas: Few-shot learning with retrieval augmented language models","venue":null,"work_id":"b83f316d-7ede-406a-bb85-c41fe5349b79","year":2023},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.813325Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:457983ef5bb1d5d15ed8c20c3a40365c1ed9f87ef856d3d7459bcb95b9f574bd","observation_id":"9d51d29d-d139-42de-82ea-b3fcccb57239","resolution":{"observed_at":"2026-08-07T12:13:00.096256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:59.636173Z","title":"Survey of hallucination i n natural language generation","venue":null,"work_id":"13f8d15e-6b2f-4681-949e-2bb1c046cd20","year":2023},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.853967Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:678ef54906234efc3bf8af8231713dd7d943bb87f64f7bb26c529a8eececaf50","observation_id":"bb2c07f9-33ec-4928-be81-d844494868e8","resolution":{"observed_at":"2026-08-07T12:12:59.816341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.09516","last_updated":"2025-08-05T19:08:38Z","snapshot_observed_at":"2026-07-06T20:51:28.022519Z","submitted_at":"2025-03-12T16:26:39Z","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.09516","snapshot_observed_at":"2026-08-07T12:12:50.922800Z","title":"Search-r1: Training llms to reason and leverage search engines with reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.922800Z"},"links":{"cited_paper":"/paper/2503.09516","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:f0232dca8b5dd0767f43b13fc7ffc7db622da60e75cc96b552bc15b9ed4bbc0e","observation_id":"bad5df60-7863-4571-93b5-3ee844af2121","resolution":{"observed_at":"2026-08-07T12:12:50.922800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13576","last_updated":"2025-02-24T02:46:52Z","snapshot_observed_at":"2026-08-08T09:22:36.004067Z","submitted_at":"2024-05-22T12:12:40Z","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13576","snapshot_observed_at":"2026-08-07T12:12:50.978650Z","title":"Flashrag: A m odular toolkit for efficient retrieval-augmented generation research","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:50.978650Z"},"links":{"cited_paper":"/paper/2405.13576","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:e71b32e00f6bf7482c52a6d96002d16e2924dc4e9bc5dcf66fdedf4b11be5705","observation_id":"a887edc1-7636-4d14-ac8b-9af3802b5512","resolution":{"observed_at":"2026-08-07T12:12:50.978650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.13081","last_updated":"2024-04-17T01:15:54Z","snapshot_observed_at":"2026-07-06T18:02:53.240463Z","submitted_at":"2024-04-17T01:15:54Z","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13081","snapshot_observed_at":"2026-08-07T12:12:51.050892Z","title":"Sure: Summarizing retrievals using answer candidates for open- domain qa of llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.050892Z"},"links":{"cited_paper":"/paper/2404.13081","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:c5f38c8cd01a2258927d62187a0a568f18229d0756b18748d84c86408c89a51d","observation_id":"65e11b93-ab68-4f51-83e3-b7298ca0bfe8","resolution":{"observed_at":"2026-08-07T12:12:51.050892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05794","last_updated":"2024-10-24T14:57:52Z","snapshot_observed_at":"2026-07-06T18:27:45.631190Z","submitted_at":"2024-06-09T14:11:19Z","title":"RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.05794","snapshot_observed_at":"2026-08-07T12:12:51.134973Z","title":"Re-rag: Improving open-d omain qa performance and interpretability with relevance estimator in retrieval-a ugmented generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.134973Z"},"links":{"cited_paper":"/paper/2406.05794","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:891613c12a55175c7df8b241ca87fe25980a3a9993d034c2ae87f0b34f27b001","observation_id":"8c33b2e6-8718-4926-ae9d-7682e26f27b9","resolution":{"observed_at":"2026-08-07T12:12:51.134973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:59.290640Z","title":"Retrieval- augmented generation for knowledge-intensive nlp tasks","venue":null,"work_id":"94b433a8-0c8d-4405-b354-48fd00a082fd","year":2020},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.220777Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:85089bbb7048ae6a542029402e478079270de46bfeeb5df8391f4af788ef6cb8","observation_id":"e6cedce8-12c3-4067-ad4a-a2c45f831111","resolution":{"observed_at":"2026-08-07T12:12:59.440519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.05366","last_updated":"2025-01-09T16:48:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-09T16:48:17Z","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.05366","snapshot_observed_at":"2026-08-07T12:12:51.279476Z","title":"Search-o1: Agentic search-enhanced large re asoning models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.279476Z"},"links":{"cited_paper":"/paper/2501.05366","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:dc83682eaba521b94e4a54741b0a928a9478f09c41ccbdad465c1ce463ed55b7","observation_id":"06f3618b-6a14-48a7-8435-33113f461228","resolution":{"observed_at":"2026-08-07T12:12:51.279476Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.02252","last_updated":"2021-05-27T15:20:59Z","snapshot_observed_at":"2026-08-07T22:58:49.396675Z","submitted_at":"2020-09-04T15:32:19Z","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.02252","snapshot_observed_at":"2026-08-07T12:12:51.315087Z","title":"Kilt: a benchmark for knowledge intensive language tasks","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.315087Z"},"links":{"cited_paper":"/paper/2009.02252","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:9382f656cd5d1655a1a37eccfbee0d57e7e46ce0935922cfee296a9105b3e2ba","observation_id":"f00a0c21-6089-43e1-99b2-19f84d67a7e7","resolution":{"observed_at":"2026-08-07T12:12:51.315087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03350","last_updated":"2023-10-17T18:57:17Z","snapshot_observed_at":"2026-07-31T15:52:06.089691Z","submitted_at":"2022-10-07T06:50:23Z","title":"Measuring and Narrowing the Compositionality Gap in Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.03350","snapshot_observed_at":"2026-08-07T12:12:51.360713Z","title":"Measuring and narrowing the compositionality gap in langua ge models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.360713Z"},"links":{"cited_paper":"/paper/2210.03350","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:0f2ccb20a47b635ee4749cad23472b3d863d12933e746eb2b9f7bf64bac8ae83","observation_id":"c8e696e0-9e11-46a4-ba56-205a5bd1f999","resolution":{"observed_at":"2026-08-07T12:12:51.360713Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.05592","last_updated":"2025-03-18T08:32:24Z","snapshot_observed_at":"2026-08-09T05:07:17.305244Z","submitted_at":"2025-03-07T17:14:44Z","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.05592","snapshot_observed_at":"2026-08-07T12:12:51.464695Z","title":"R1-searcher: Incentivizing the sear ch capability in llms via reinforce- ment learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.464695Z"},"links":{"cited_paper":"/paper/2503.05592","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:762a9c499cf2f9b29b513084222a2b30dd9b66e9b660488168739345c62e405e","observation_id":"0d6bd54e-d4bb-40bb-9c42-bea4a0bbca4c","resolution":{"observed_at":"2026-08-07T12:12:51.464695Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.09542","last_updated":"2024-12-28T06:20:54Z","snapshot_observed_at":"2026-08-06T00:21:17.259026Z","submitted_at":"2023-04-19T10:16:03Z","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.09542","snapshot_observed_at":"2026-08-07T12:12:51.562830Z","title":"Is chatgpt good at search? investigat ing large language models as re-ranking agents","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.562830Z"},"links":{"cited_paper":"/paper/2304.09542","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:095374a3984bec12b0b96685bced7b0210a43f88797dffe119859f1ceaded098","observation_id":"b8371d11-effc-44e1-ac2c-07874bcfcde4","resolution":{"observed_at":"2026-08-07T12:12:51.562830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.07861","last_updated":"2025-01-14T05:56:26Z","snapshot_observed_at":"2026-08-08T00:22:22.679304Z","submitted_at":"2025-01-14T05:56:26Z","title":"ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.07861","snapshot_observed_at":"2026-08-07T12:12:51.669991Z","title":"Rearter: Retrieval-augmented reason ing with trustworthy process rewarding","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.669991Z"},"links":{"cited_paper":"/paper/2501.07861","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:b39cd373615c5d7cc3012c3764ff55f4859f9b4d2897416a15b6c497bccaf13b","observation_id":"82927590-9c6f-4fa8-9170-b3707016782c","resolution":{"observed_at":"2026-08-07T12:12:51.669991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T12:12:51.805171Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.805171Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:4c259adfac662fc8c97b59aa99e9587061a9f92a860e56cdfb298baafd62e8dc","observation_id":"837b3e97-0dc4-43df-aa1f-e5d343914099","resolution":{"observed_at":"2026-08-07T12:12:51.805171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:59.033764Z","title":"♪ musique: Multihop questions via single-hop question composition","venue":null,"work_id":"e81e7a89-79f3-4ffc-b3dc-f78905503302","year":2022},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.915172Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:0e52c6595aa3623edf8ca41fcf3f161847ee1677fd4131308c434c6c016a4560","observation_id":"8299ca5b-2e92-4206-a229-23cbbe017c6d","resolution":{"observed_at":"2026-08-07T12:12:59.151924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20753","last_updated":"2025-02-04T15:30:36Z","snapshot_observed_at":"2026-08-08T17:29:28.578703Z","submitted_at":"2024-10-28T05:35:04Z","title":"Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.20753","snapshot_observed_at":"2026-08-07T12:12:51.978169Z","title":"Plan-rag: Planning-guided retrieval augm ented generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:51.978169Z"},"links":{"cited_paper":"/paper/2410.20753","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:b1696ae3cc8f2f108bb677ba4c43bea4f3d77bb3fa1c7f5c138e32bfe8311f63","observation_id":"64e53bab-6ce5-4f47-b39d-cc26eed7f705","resolution":{"observed_at":"2026-08-07T12:12:51.978169Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.03533","last_updated":"2024-02-22T06:21:51Z","snapshot_observed_at":"2026-07-06T14:27:46.217000Z","submitted_at":"2022-12-07T09:25:54Z","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.03533","snapshot_observed_at":"2026-08-07T12:12:52.077629Z","title":"Text embeddings by weakly-supervis ed contrastive pre-training","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.077629Z"},"links":{"cited_paper":"/paper/2212.03533","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:575391879d4d0b51bc0fa156ee89481659883655fa002b26628128de7c431416","observation_id":"6b48723a-5145-475f-a7fb-058b98c2dd86","resolution":{"observed_at":"2026-08-07T12:12:52.077629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:58.785846Z","title":"Chain-of-thought prompting elicits reas oning in large language models","venue":null,"work_id":"12b6af1a-93a1-4f2e-92e0-e5adacea353c","year":2022},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.131383Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:956f4c6952a0fb9737783a89d924598da68c6a691574a92d735340492d70c00d","observation_id":"b86d79af-ac85-45fa-a03d-b2bcad60e820","resolution":{"observed_at":"2026-08-07T12:12:58.924060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11166","last_updated":"2024-02-17T02:21:44Z","snapshot_observed_at":"2026-08-03T22:37:56.873870Z","submitted_at":"2024-02-17T02:21:44Z","title":"GenDec: A robust generative Question-decomposition method for Multi-hop reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11166","snapshot_observed_at":"2026-08-07T12:12:52.186107Z","title":"Gendec: A robust generative question-decomposition metho d for multi-hop reasoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.186107Z"},"links":{"cited_paper":"/paper/2402.11166","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:d876611b7b6ec9546db056fac6c0b60cee928d63e480696446e764f05f60f774","observation_id":"6e0b9527-ea17-47a2-a9c2-69d1129080b6","resolution":{"observed_at":"2026-08-07T12:12:52.186107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.12756","last_updated":"2021-02-19T22:15:03Z","snapshot_observed_at":"2026-08-08T13:42:50.719443Z","submitted_at":"2020-09-27T06:12:29Z","title":"Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.12756","snapshot_observed_at":"2026-08-07T12:12:52.255422Z","title":"Answering complex open- domain questions with multi-hop dense retrieval","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.255422Z"},"links":{"cited_paper":"/paper/2009.12756","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:082094883590951ccf3b3ebe263bdc44549e56e287cf395e82ec49ae19086f99","observation_id":"99d65b93-7d38-4ef4-a630-a83c57b268c7","resolution":{"observed_at":"2026-08-07T12:12:52.255422Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-07T12:12:52.336979Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.336979Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:ae65d26bc5c474594e675866cf685a9083fb64e4f0a5bc95fff37892698608f5","observation_id":"4b075729-1c94-49ab-b24d-0b4821f75ead","resolution":{"observed_at":"2026-08-07T12:12:52.336979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.09600","last_updated":"2018-09-25T17:28:20Z","snapshot_observed_at":"2026-08-09T10:11:58.541007Z","submitted_at":"2018-09-25T17:28:20Z","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.09600","snapshot_observed_at":"2026-08-07T12:12:52.429845Z","title":"Hotpotqa: A dataset for di verse, explainable multi-hop question answering","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.429845Z"},"links":{"cited_paper":"/paper/1809.09600","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:168dd9157bb514a3f748ffc37df177f281adfa899a853e2c37c5cf45a53a38f0","observation_id":"86944795-4ebc-419b-aa3d-3adffa2a6574","resolution":{"observed_at":"2026-08-07T12:12:52.429845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19443","last_updated":"2024-11-29T03:01:05Z","snapshot_observed_at":"2026-08-09T13:13:41.300334Z","submitted_at":"2024-11-29T03:01:05Z","title":"Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.19443","snapshot_observed_at":"2026-08-07T12:12:52.492006Z","title":"Auto-rag: Autono mous retrieval-augmented genera- tion for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.492006Z"},"links":{"cited_paper":"/paper/2411.19443","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:21fa74a7abcbaf37650975ee54b061c2ca519fd4b5b4bfc24bc8518bde3354ed","observation_id":"540297d9-3e53-4369-acc1-58fdeb1024a4","resolution":{"observed_at":"2026-08-07T12:12:52.492006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15056","last_updated":"2023-05-24T11:45:59Z","snapshot_observed_at":"2026-07-06T15:32:25.931739Z","submitted_at":"2023-05-24T11:45:59Z","title":"Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering","version":1},"cited_work":{"arxiv_id":"2305.15056","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.15056","snapshot_observed_at":"2026-08-07T12:12:54.811029Z","title":"Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering","venue":"cs.CL","work_id":"1b6109c6-a93d-4863-ab2f-5a1b13559cc7","year":2023},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.533727Z"},"links":{"cited_paper":"/paper/2305.15056","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:ed5777e3f51433f0111be58d26fccbd2c37d728ef9f1ae796a2f8bcf5a8492ca","observation_id":"ab5cb329-bd06-4f9d-9b8b-97d8b3890953","resolution":{"observed_at":"2026-08-07T12:12:54.872020Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.06559","last_updated":"2025-05-26T14:03:32Z","snapshot_observed_at":"2026-08-09T05:18:18.356511Z","submitted_at":"2024-12-09T15:11:40Z","title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.06559","snapshot_observed_at":"2026-08-07T12:12:52.620513Z","title":"Processbench: Identify ing process errors in mathematical reasoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.620513Z"},"links":{"cited_paper":"/paper/2412.06559","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:9a0d4290cb8e48300b5e12fa5d3087f133f52c0c4f6c0717366e92baa4d60a3c","observation_id":"e03ee049-c628-48ee-92c8-0920c821ef84","resolution":{"observed_at":"2026-08-07T12:12:52.620513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.04259","last_updated":"2024-09-26T11:42:35Z","snapshot_observed_at":"2026-08-05T15:40:45.605478Z","submitted_at":"2024-08-08T06:57:49Z","title":"EfficientRAG: Efficient Retriever for Multi-Hop Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.04259","snapshot_observed_at":"2026-08-07T12:12:52.693071Z","title":"#1\" or pronouns like","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.693071Z"},"links":{"cited_paper":"/paper/2408.04259","citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:875c59a227ee815b73e02c046ae6d39eb8a44ed3bcd1007ad0d8f4a0d8683a5f","observation_id":"99b97800-acc8-4355-b6ea-7fe595d3035d","resolution":{"observed_at":"2026-08-07T12:12:52.693071Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:58.571537Z","title":null,"venue":null,"work_id":"3d725315-8186-42aa-a5dd-15544f66e2f1","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.795569Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:25d1bcf9e7f7251dc43a964e6ee354ea7a45db785976f445d40889c9abb8635c","observation_id":"d6653f07-a679-42bb-9f73-d6aaf58a08c7","resolution":{"observed_at":"2026-08-07T12:12:58.706163Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:58.358346Z","title":"T o perform the comparison, the populations of Canada and Australia must first be individually achieved","venue":null,"work_id":"1b1d1a27-df7c-4ee7-a17f-8b5d2c26c63b","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.909211Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:879c06ec7b4c98a946a6cb63a383d4d140ad930dc2b5b1f949706fda572f5176","observation_id":"601e2ad0-9169-438a-8903-7a36b93a4198","resolution":{"observed_at":"2026-08-07T12:12:58.463190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:58.260904Z","title":null,"venue":null,"work_id":"330e7414-bac0-4862-ba3e-c87a0736384b","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:52.977049Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:8184abd3b2a7f0669d5def0600632283ed4016956371ccb11f71229c39a4a72b","observation_id":"e7cee9b4-0cda-47f1-b8ab-31ba6d2263a6","resolution":{"observed_at":"2026-08-07T12:12:58.310005Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:58.115389Z","title":null,"venue":null,"work_id":"f7143873-6f6e-4985-b04b-ac369202db78","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.046701Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:f72b24c5cf0e0dac251f0602d96442c416086c736f2cd91f7c1055c7fb786587","observation_id":"d4b5cff3-584e-488e-b987-82c516722cde","resolution":{"observed_at":"2026-08-07T12:12:58.174962Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:58.000088Z","title":"Australia has a population o f #2","venue":null,"work_id":"169a1705-2e56-47b5-9894-2dab39b583e3","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.074481Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:c4ddb58429102e731895267b0f5294c32dd12dde6af41678f7177e62f1bdbf5f","observation_id":"63bb6c61-1669-4727-af15-ad61eb0d6b31","resolution":{"observed_at":"2026-08-07T12:12:58.047760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:57.769909Z","title":null,"venue":null,"work_id":"74b94f32-9a94-479d-af30-8828162771ea","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.156492Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:10e6b2a86245de444615a20b2d65ec1ea199e12d236ab196f05fbb1548b26153","observation_id":"8867a4a7-1559-4da9-9da0-6943201d0f11","resolution":{"observed_at":"2026-08-07T12:12:57.859694Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:57.630552Z","title":null,"venue":null,"work_id":"3bc429a3-2b2e-4322-ae80-d674f92deb5c","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.243312Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:124568034f526d4d08c4761d801da9bd4b10a265de895476c95f62736bd680fa","observation_id":"3c008805-32a5-4058-af13-34b41a202d90","resolution":{"observed_at":"2026-08-07T12:12:57.706224Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:57.506512Z","title":"The length of Tigris is #2","venue":null,"work_id":"c20093f8-7598-45b6-abdf-d09c98667fc8","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.323644Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:bc758b8b4270b949da242d5ab9f44c1282db5bc70c844a906f8940b0d0b1fc31","observation_id":"601697b1-c7a0-46fe-9963-7bb9ae9ebb06","resolution":{"observed_at":"2026-08-07T12:12:57.546866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:57.354559Z","title":null,"venue":null,"work_id":"965a74f9-63fd-42e3-91e5-aa502df42714","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.402831Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:6ccee2c0095eda8d7f2e3fdede4afe87283d7145e8a73776e8af1faadc257f3a","observation_id":"acd3f197-31d0-457b-a5bc-123554a956a8","resolution":{"observed_at":"2026-08-07T12:12:57.439451Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:57.211272Z","title":null,"venue":null,"work_id":"53ef11bb-9894-4e5e-9f3d-70fbca38165a","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.433102Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:63a2734e7d8c277538e3c8400d3f54f2b8d2ff9ef8a66c7265ca8d2386006990","observation_id":"aff6d78b-91b0-41cd-89fc-4d0591f6ebbb","resolution":{"observed_at":"2026-08-07T12:12:57.272448Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:57.045794Z","title":"Once both are identified, their geographical di stance can be obtained","venue":null,"work_id":"fdc9bd6d-c3bc-4b4d-a796-6281b66f329d","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.482120Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:44475df69b211f2f641508450a6f5472fb855147c5cefa057f188eed18aaf144","observation_id":"de86dbe8-aec7-4258-80ce-c59e47195ac0","resolution":{"observed_at":"2026-08-07T12:12:57.108918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:56.904268Z","title":null,"venue":null,"work_id":"fc6c9215-c155-45e4-923b-d3c19f70d2b1","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.528577Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:515089b075fec4bf4324c7e74d1e6af66f4f37b2c99a9d7827eb09f0312b2808","observation_id":"8b3ae6a5-7aac-491e-aa2a-1980b78a8c88","resolution":{"observed_at":"2026-08-07T12:12:56.969155Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:56.727044Z","title":null,"venue":null,"work_id":"76fb7cb1-6ebf-4ae3-8e3a-638bcd81a65d","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.656495Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:3877bfa9ac25157c27507a78a09cc87b5e4f1bdd4479c219413e380c5384609c","observation_id":"c7c13d0f-7616-4233-979c-7c402e810b08","resolution":{"observed_at":"2026-08-07T12:12:56.817450Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:56.585225Z","title":"First, the country where the Eiffel Tower is loca ted must be found, followed by identifying its capital city","venue":null,"work_id":"e8854308-0d94-42d7-8bea-36b8a59e5b37","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.765919Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:bb62f450bc03d5328da0bc50dd44bd8d57f41b629877e9ef685f945040e2194c","observation_id":"4009c79f-132f-4f50-9a99-9e2f5095c91b","resolution":{"observed_at":"2026-08-07T12:12:56.667904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:56.401246Z","title":null,"venue":null,"work_id":"a6794b57-8735-4347-91c3-5bcf2bfc57dd","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.886175Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:eb8646d24dc3ef17ca934a9687fe58d8ad1a3643970ada7608887a7ade192b35","observation_id":"1e74a87e-3c95-457b-978b-0a5e6a540f7b","resolution":{"observed_at":"2026-08-07T12:12:56.482272Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:56.217427Z","title":null,"venue":null,"work_id":"ad670092-9bac-425d-a04d-5a189d3845ea","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:53.943628Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:f5ed09e0477e8640e732e9d77bc092931a5d5e0af5a8877b6c54559ace916d8a","observation_id":"c9fbae5e-7011-437a-89af-2a2bf03e7b35","resolution":{"observed_at":"2026-08-07T12:12:56.312012Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:56.061669Z","title":null,"venue":null,"work_id":"cfef0394-d025-4806-b835-0263e4897752","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:54.050780Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:e1488ef9ce8c995e4b9d3cfe215970d05e15689f15198334d724ae55e14864c2","observation_id":"28848d23-57af-4fe7-bbf7-2d0360a43ece","resolution":{"observed_at":"2026-08-07T12:12:56.125381Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:55.915930Z","title":"#number\", don’t use the","venue":null,"work_id":"743588cc-019c-45b6-9f96-4ad6676c79b9","year":2001},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:54.138453Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:1b4172a95559e36ab05f47b8998c3cb4c41a3e89848d7eabfc046ce2225c0ee6","observation_id":"87f4dc02-575e-44ce-adaa-73577043a910","resolution":{"observed_at":"2026-08-07T12:12:56.014590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:55.453903Z","title":"Instead of asking about where th e company is located, specify that we need the **headquarters** location","venue":null,"work_id":"060edab3-5964-4029-b6f5-076828a57ab9","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:54.404979Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:1c2f74ec97779ea34f66f39987f241d331009542615b4406861e2c83949b1523","observation_id":"8df871b4-c098-4115-ab17-ffd721d2f37d","resolution":{"observed_at":"2026-08-07T12:12:55.557421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:55.752176Z","title":null,"venue":null,"work_id":"37f11032-5dfd-46a4-871a-2c47c108c430","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:54.466524Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:8920eef03095521464b36427b0c7480a51ee333619d73439289510f93edab98a","observation_id":"ebe50fa6-8166-4868-891a-4a60a0c54a91","resolution":{"observed_at":"2026-08-07T12:12:55.846272Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:55.625380Z","title":null,"venue":null,"work_id":"52f446ba-11a8-435b-8c69-df9f84633f96","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:54.544284Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:485c2de96fd1e5738df2a6794306533a2bea502468a5c501d3442162e8c32ae8","observation_id":"c3e928c5-0044-41c6-b320-6fd35b25db74","resolution":{"observed_at":"2026-08-07T12:12:55.654939Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:55.300503Z","title":null,"venue":null,"work_id":"94a9793f-1a66-4cfe-b599-53c0983c67c7","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:54.613094Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:cb9dcbc242ca6cd5ff0ed1e502876f61bfe48e9b84ac9210ce67db0c039347fd","observation_id":"94169a27-a7d7-4e69-9390-742e0c2dbdc2","resolution":{"observed_at":"2026-08-07T12:12:55.406555Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:12:55.168756Z","title":"Given a question, an answer, and the supporting passages, ev aluate the answer based on the following criteria: a","venue":null,"work_id":"0a315b72-0238-4ef0-b95c-b77fbe638375","year":null},"citing_paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T12:12:54.713185Z"},"links":{"citing_paper":"/paper/2506.00232"},"observation_digest":"sha256:38f7ab4caeabc26752b1ea7b75105e204fc16271473cc5333a80e065ae76c65a","observation_id":"69ac44e6-6b8d-4320-9630-8f77828354f8","resolution":{"observed_at":"2026-08-07T12:12:55.217299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.00232","last_updated":"2025-05-30T21:10:30Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-09T15:00:40.989350Z","submitted_at":"2025-05-30T21:10:30Z","title":"ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":42,"verified_exact":1,"verified_fuzzy":15},"total_outbound_references":59},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 2 inbound Pith citation observations for arXiv:2506.00232."}