{"as_of":"2026-08-08T22:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e873966d8911a0db401f322caeabee683abacd934e19929d10afde821186a54f","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:34:11.758174Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-12T10:01:29.579804Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.14546","last_updated":"2024-12-23T12:01:28Z","snapshot_observed_at":"2026-07-06T18:34:24.078145Z","submitted_at":"2024-06-20T17:55:04Z","title":"Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14546","snapshot_observed_at":"2026-08-07T14:34:11.758174Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18485","last_updated":"2025-05-24T03:19:36Z","snapshot_observed_at":"2026-08-07T14:28:31.571182Z","submitted_at":"2025-05-24T03:19:36Z","title":"The Prompt is Mightier than the Example","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T14:34:11.758174Z"},"links":{"cited_paper":"/paper/2406.14546","citing_paper":"/paper/2505.18485"},"observation_digest":"sha256:e869a292d334e29660e0dc580c0a570e9ac983f698efeb9a9bc785eabc469d9c","observation_id":"560dfe76-4e53-4706-94aa-4f106fedc1d0","resolution":{"observed_at":"2026-08-07T14:34:11.758174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14546","last_updated":"2024-12-23T12:01:28Z","snapshot_observed_at":"2026-07-06T18:34:24.078145Z","submitted_at":"2024-06-20T17:55:04Z","title":"Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14546","snapshot_observed_at":"2026-08-07T04:07:28.219516Z","title":"Connecting the dots: Llms can infer and verbalize latent structure from disparate training data, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.11613","last_updated":"2025-06-13T09:34:25Z","snapshot_observed_at":"2026-08-07T20:45:04.878203Z","submitted_at":"2025-06-13T09:34:25Z","title":"Model Organisms for Emergent Misalignment","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T04:07:28.219516Z"},"links":{"cited_paper":"/paper/2406.14546","citing_paper":"/paper/2506.11613"},"observation_digest":"sha256:e484eea35145b5d67f29cb50210b411e12fc7cbf875bdcdabc6a46c3e2c8d7af","observation_id":"e4000abf-55d7-47dd-9335-9c7e27a51c26","resolution":{"observed_at":"2026-08-07T04:07:28.219516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14546","last_updated":"2024-12-23T12:01:28Z","snapshot_observed_at":"2026-07-06T18:34:24.078145Z","submitted_at":"2024-06-20T17:55:04Z","title":"Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14546","snapshot_observed_at":"2026-08-07T04:09:27.678867Z","title":"Connecting the dots: Llms can infer and verbalize latent structure from disparate training data, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.11618","last_updated":"2025-06-20T17:23:55Z","snapshot_observed_at":"2026-08-07T07:50:03.690781Z","submitted_at":"2025-06-13T09:39:54Z","title":"Convergent Linear Representations of Emergent Misalignment","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T04:09:27.678867Z"},"links":{"cited_paper":"/paper/2406.14546","citing_paper":"/paper/2506.11618"},"observation_digest":"sha256:63a3590193756c0256b9fff45d10efe14aacf89c1c4e2bcc3922bd5ddc391250","observation_id":"3408638e-1214-4327-bd51-4847ba9a6e00","resolution":{"observed_at":"2026-08-07T04:09:27.678867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14546","last_updated":"2024-12-23T12:01:28Z","snapshot_observed_at":"2026-07-06T18:34:24.078145Z","submitted_at":"2024-06-20T17:55:04Z","title":"Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data","version":3},"cited_work":{"arxiv_id":"2406.14546","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.14546","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Connecting the dots: Llms can infer and verbalize latent structure from disparate training data","venue":null,"work_id":"65ba82a7-ebad-4e98-a956-597599b4da1d","year":2024},"citing_paper":{"arxiv_id":"2604.28082","last_updated":"2026-04-30T16:26:53Z","snapshot_observed_at":"2026-07-31T05:43:29.443796Z","submitted_at":"2026-04-30T16:26:53Z","title":"Characterizing the Consistency of the Emergent Misalignment Persona","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-07T08:06:58.635103Z"},"links":{"cited_paper":"/paper/2406.14546","citing_paper":"/paper/2604.28082"},"observation_digest":"sha256:e932f18bd39854ac1f669f8fbc6dd4346c0f56b3c5c40ad5a484c0c04bb0aa03","observation_id":"754bff99-2877-43b2-ac82-fe61f88e9305","resolution":{"observed_at":"2026-05-12T10:01:29.582468Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14546","last_updated":"2024-12-23T12:01:28Z","snapshot_observed_at":"2026-07-06T18:34:24.078145Z","submitted_at":"2024-06-20T17:55:04Z","title":"Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14546","snapshot_observed_at":"2026-08-01T00:38:42.989353Z","title":"Connecting the dots: LLMs can infer and verbalize latent structure from disparate training data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26173","last_updated":"2026-07-28T18:29:45Z","snapshot_observed_at":"2026-08-08T16:10:22.110949Z","submitted_at":"2026-07-28T18:29:45Z","title":"Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T00:38:42.989353Z"},"links":{"cited_paper":"/paper/2406.14546","citing_paper":"/paper/2607.26173"},"observation_digest":"sha256:8e654b76dc876e730b8cd9025550ed405233d21baa52ba48411476be1a1bc434","observation_id":"b1885033-e6ae-4ec6-bb3f-25c27ca3ddaf","resolution":{"observed_at":"2026-08-01T00:38:42.989353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.14546/citation-record","integrity":"/paper/2406.14546/integrity","json":"/paper/2406.14546/citation-record.json","paper":"/paper/2406.14546"},"outbound":[],"paper":{"arxiv_id":"2406.14546","last_updated":"2024-12-23T12:01:28Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:34:24.078145Z","submitted_at":"2024-06-20T17:55:04Z","title":"Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2406.14546."}