{"as_of":"2026-08-12T22:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dcf2d7cf2b99b812c7246e3cd1e4ef263cd66e1678e6c844b93e2091b8263766","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:16:21.023602Z","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":"2026-06-29T13:33:28.004393Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.14694","last_updated":"2025-03-12T06:01:05Z","snapshot_observed_at":"2026-08-07T17:11:01.815885Z","submitted_at":"2025-03-12T06:01:05Z","title":"HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.14694","snapshot_observed_at":"2026-08-07T11:16:21.023602Z","title":"arXiv preprint arXiv:2503.14694 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.02975","last_updated":"2025-06-03T15:14:00Z","snapshot_observed_at":"2026-08-08T06:27:57.629343Z","submitted_at":"2025-06-03T15:14:00Z","title":"HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T11:16:21.023602Z"},"links":{"cited_paper":"/paper/2503.14694","citing_paper":"/paper/2506.02975"},"observation_digest":"sha256:c104102cc882a6ddb68ee86c42bbeed2fea3801bbe7496a41a5475e123099c0f","observation_id":"9c9854a8-3074-4a3b-9afa-01ab99df80f4","resolution":{"observed_at":"2026-08-07T11:16:21.023602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14694","last_updated":"2025-03-12T06:01:05Z","snapshot_observed_at":"2026-08-07T17:11:01.815885Z","submitted_at":"2025-03-12T06:01:05Z","title":"HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding","version":1},"cited_work":{"arxiv_id":"2503.14694","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.14694","snapshot_observed_at":"2026-06-29T13:33:28.004393Z","title":"Haplovl: A single- transformer baseline for multi-modal understanding","venue":null,"work_id":"72a8544e-2cc4-4127-8e65-59e99a339407","year":2024},"citing_paper":{"arxiv_id":"2605.12500","last_updated":"2026-05-12T17:59:58Z","snapshot_observed_at":"2026-07-06T23:24:13.851504Z","submitted_at":"2026-05-12T17:59:58Z","title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","version":1},"reference_index":151,"source":"pdf_text","source_observed_at":"2026-05-13T05:12:37.339084Z"},"links":{"cited_paper":"/paper/2503.14694","citing_paper":"/paper/2605.12500"},"observation_digest":"sha256:815f6a95cf03814e641bbdafdfadcc0322406a46c9a44891db9b43e8a16d60e2","observation_id":"404043d8-76ec-4fbc-9349-53a84328090b","resolution":{"observed_at":"2026-05-13T05:17:18.559368Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14694","last_updated":"2025-03-12T06:01:05Z","snapshot_observed_at":"2026-08-07T17:11:01.815885Z","submitted_at":"2025-03-12T06:01:05Z","title":"HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding","version":1},"cited_work":{"arxiv_id":"2503.14694","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.14694","snapshot_observed_at":"2026-06-29T13:33:28.004393Z","title":"Haplovl: A single- transformer baseline for multi-modal understanding","venue":null,"work_id":"72a8544e-2cc4-4127-8e65-59e99a339407","year":2024},"citing_paper":{"arxiv_id":"2605.28820","last_updated":"2026-05-27T17:59:55Z","snapshot_observed_at":"2026-07-06T23:38:19.096349Z","submitted_at":"2026-05-27T17:59:55Z","title":"From Pixels to Words -- Towards Native One-Vision Models at Scale","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T13:29:53.006064Z"},"links":{"cited_paper":"/paper/2503.14694","citing_paper":"/paper/2605.28820"},"observation_digest":"sha256:5718cb3bfc816728c091b01d7ef4233eba0c2943a5de0a3b0c14f64dc453d859","observation_id":"91f6ad7a-cd68-46cc-a942-2e48006fb6d1","resolution":{"observed_at":"2026-06-29T13:33:28.005804Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.14694/citation-record","integrity":"/paper/2503.14694/integrity","json":"/paper/2503.14694/citation-record.json","paper":"/paper/2503.14694"},"outbound":[],"paper":{"arxiv_id":"2503.14694","last_updated":"2025-03-12T06:01:05Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T17:11:01.815885Z","submitted_at":"2025-03-12T06:01:05Z","title":"HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.14694."}