{"as_of":"2026-08-12T05:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c01eba1b8f52e2e8962235ad5f7509dbd0ab87ebe02c1cc3f54a506fbe02fe74","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T15:20:40.299735Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-14T21:15:07.466245Z","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":"2026-05-14T21:17:59.329778Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"cited_work":{"arxiv_id":"2501.14216","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.14216","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2501.14216 , year=","venue":null,"work_id":"17833f6c-1cca-4409-ba8b-94f3b4948e8b","year":null},"citing_paper":{"arxiv_id":"2605.12649","last_updated":"2026-05-25T06:52:53Z","snapshot_observed_at":"2026-08-04T00:56:32.436112Z","submitted_at":"2026-05-12T18:55:53Z","title":"DIVER:Diving Deeper into Distilled Data via Expressive Semantic Recovery","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-05-14T21:15:07.466245Z"},"links":{"cited_paper":"/paper/2501.14216","citing_paper":"/paper/2605.12649"},"observation_digest":"sha256:0abcc027c16166d6fc3b53fdc27bc92b170f8eb97314719c08f804327ac18dbc","observation_id":"15f78035-9052-4522-95d0-440abf10ac5f","resolution":{"observed_at":"2026-05-14T21:17:59.332453Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.14216/citation-record","integrity":"/paper/2501.14216/integrity","json":"/paper/2501.14216/citation-record.json","paper":"/paper/2501.14216"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:20:40.632006Z","title":"(17) Again, for each G′ 1 ∈ G, define a probability measurePG′ 1 C on C by PG′ 1 C (c′) = fc′(G′ 1)","venue":null,"work_id":"1ab1b83d-752d-4294-90f1-d9b871592453","year":null},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.266845Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:bed693fd495308c2a273991d34c676c09dba65ba2bdd1d675c9df3630b8c0eb7","observation_id":"f1893b10-ef39-4bf4-a59c-226abceec3d8","resolution":{"observed_at":"2026-08-10T15:20:40.636603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.02530","last_updated":"2023-09-12T02:16:45Z","snapshot_observed_at":"2026-08-12T04:16:37.324818Z","submitted_at":"2023-09-05T18:52:35Z","title":"Diffusion on the Probability Simplex","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.02530","snapshot_observed_at":"2026-08-10T15:20:40.206367Z","title":"Diffusion on the probability simplex","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.206367Z"},"links":{"cited_paper":"/paper/2309.02530","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:216ba47e3c2c92f97a2ccb74f76dc89dd9d1b6b9676328959bdb73ee0785e5f4","observation_id":"9f3d47c7-91db-479f-ba80-c92e11b0f2a8","resolution":{"observed_at":"2026-08-10T15:20:40.206367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-10T15:20:40.217298Z","title":"6, 8, 32 Jonathan Ho and Tim Salimans","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.217298Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:0589e5fceb81c10d90a9ba8b402554d2039dff5d3851a23ad671ba9b3964a720","observation_id":"fdf4a80e-791d-45fc-973f-69ffb3edde74","resolution":{"observed_at":"2026-08-10T15:20:40.217298Z","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":"2026-08-10T15:20:40.646870Z","title":"Equivariant diffusion for molecule generation in 3d","venue":null,"work_id":"bc0a9497-0dd4-4f6d-ad4a-d5553f2f6b5b","year":2022},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.227056Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:2451db90a41df4560112c650c4b54459cc3b5dac44bed003f9af54041fe2d12f","observation_id":"9c10824f-5c0a-4bdf-977f-dee6113e533b","resolution":{"observed_at":"2026-08-10T15:20:40.652420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12347","last_updated":"2023-06-04T10:09:36Z","snapshot_observed_at":"2026-08-09T12:19:13.251973Z","submitted_at":"2023-05-21T04:49:53Z","title":"Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12347","snapshot_observed_at":"2026-08-10T15:20:40.231433Z","title":"Learning joint 2d & 3d diffusion models for complete molecule generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.231433Z"},"links":{"cited_paper":"/paper/2305.12347","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:81e19cf974c59577c9d7aabb4e7291f010b6a727746834cb3193d8488ca5185f","observation_id":"634520cf-8ed0-49b6-849c-63cc45efb52d","resolution":{"observed_at":"2026-08-10T15:20:40.231433Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.03241","last_updated":"2023-04-12T10:36:44Z","snapshot_observed_at":"2026-08-05T03:04:44.382109Z","submitted_at":"2023-02-07T03:57:55Z","title":"Continual Pre-training of Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.03241","snapshot_observed_at":"2026-08-10T15:20:40.237320Z","title":"Optimizing diffusion noise can serve as universal motion priors","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.237320Z"},"links":{"cited_paper":"/paper/2302.03241","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:d2e9221a357a68714560f955f00340d9dbba848d272c58ac3a9bcc83293c96c7","observation_id":"6deeb7fe-ca9f-402d-ab34-f68a016fab92","resolution":{"observed_at":"2026-08-10T15:20:40.237320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02314","last_updated":"2024-05-28T16:16:42Z","snapshot_observed_at":"2026-08-09T17:55:41.119656Z","submitted_at":"2024-02-04T01:55:00Z","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.02314","snapshot_observed_at":"2026-08-10T15:20:40.242143Z","title":"Selecting large language model to fine-tune via rectified scaling law","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.242143Z"},"links":{"cited_paper":"/paper/2402.02314","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:4954d98b2cc8c3d268e527a4660f50d999d8740316c65dd4291c387d3550924a","observation_id":"1e7a544f-7197-4a9a-8073-ec4958a08e87","resolution":{"observed_at":"2026-08-10T15:20:40.242143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.07508","last_updated":"2023-05-11T08:11:19Z","snapshot_observed_at":"2026-07-31T07:41:42.387468Z","submitted_at":"2023-05-11T08:11:19Z","title":"MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.07508","snapshot_observed_at":"2026-08-10T15:20:40.246997Z","title":"Geometry-complete diffusion for 3d molecule generation and optimization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.246997Z"},"links":{"cited_paper":"/paper/2305.07508","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:9fd4b23f11520a3814a7ca74c68ae6ab16e4555b29b495750a430b4581d2b153","observation_id":"88d7dd43-1654-43d2-adf9-77c1d76f81b5","resolution":{"observed_at":"2026-08-10T15:20:40.246997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.02142","last_updated":"2024-05-22T16:55:51Z","snapshot_observed_at":"2026-08-01T16:47:47.176192Z","submitted_at":"2023-11-03T16:50:26Z","title":"Sparse Training of Discrete Diffusion Models for Graph Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.02142","snapshot_observed_at":"2026-08-10T15:20:40.252172Z","title":"Sparse training of discrete diffusion models for graph generation","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.252172Z"},"links":{"cited_paper":"/paper/2311.02142","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:9a3fcdac7d78b3a413c637db511489794db2b0dd2faff0bd527a4518274b6bc8","observation_id":"d96fcdf3-3620-4594-9566-442d40ffb1a8","resolution":{"observed_at":"2026-08-10T15:20:40.252172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.10025","last_updated":"2024-05-01T02:58:30Z","snapshot_observed_at":"2026-07-06T14:53:42.192162Z","submitted_at":"2023-02-20T15:14:46Z","title":"DINOISER: Diffused Conditional Sequence Learning by Manipulating Noises","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.10025","snapshot_observed_at":"2026-08-10T15:20:40.261997Z","title":"Tfg: Unified training-free guidance for diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.261997Z"},"links":{"cited_paper":"/paper/2302.10025","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:021387e0375f65bc1e1fb7a82d9b758e0af9ca8bfb7c82e330beb52ece316912","observation_id":"eff9aeec-a274-4391-bffb-0680e03a90e1","resolution":{"observed_at":"2026-08-10T15:20:40.261997Z","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":"2026-08-10T15:20:40.617568Z","title":"Now we are ready to verify that the above joint probability measure P satisfies the desired properties","venue":null,"work_id":"c83abb5d-5fd5-47af-bd0d-97050a2a6a60","year":null},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.271393Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:664695413f43f574750db47be86b2027bfd1a5066fd78c20861a24b4c4149ac4","observation_id":"1f830ad3-84ea-4e53-b338-93a7929fde87","resolution":{"observed_at":"2026-08-10T15:20:40.622439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:20:40.601406Z","title":null,"venue":null,"work_id":"8214b3f8-d607-4219-b184-1213add7a1b1","year":null},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.275876Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:6736e3fec3eaa05af035111557fcc9aefbf003ae606d637aae5edfae80134db1","observation_id":"28160afb-d603-4b09-ae7f-2b3ca2dd5d09","resolution":{"observed_at":"2026-08-10T15:20:40.606172Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:20:40.584579Z","title":"(20) Thus, the marginal distribution of {Gt}t∈[0,1] under P is PG","venue":null,"work_id":"3790a0ba-ca87-4263-8a13-1812f97ecfe3","year":2025},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.280911Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:b4c6239a14cd2d5414d805e7c63179b8da70612ebf341bd760823855a011be6b","observation_id":"1d01d64f-8c78-47cc-9529-bc3c1a738d3f","resolution":{"observed_at":"2026-08-10T15:20:40.589201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:20:40.569338Z","title":"(21) This establishes the specified alignment with the target predictor","venue":null,"work_id":"178504ed-9f48-4cdf-a5c8-54d6a01223e9","year":2025},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.285225Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:903095f9d0ea04c574edd67c2e8b43fc5d6c1310a8261afc34587a4eb4d85a69","observation_id":"eac0aff9-d076-4c42-86fa-86a705a05614","resolution":{"observed_at":"2026-08-10T15:20:40.574357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:20:40.554544Z","title":null,"venue":null,"work_id":"503b2860-fdd7-4932-886c-be318682faf8","year":2022},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.290267Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:3fb41bcc8c536d82ee7a0214e57adda3ccfe66e8433f1db366b01f54e7f43014","observation_id":"e2814974-2573-458e-a94b-0b1147103e63","resolution":{"observed_at":"2026-08-10T15:20:40.559071Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:20:40.539016Z","title":"inference with external potentials","venue":null,"work_id":"c34c2dec-ce36-4bae-8ade-28c378f5568e","year":2021},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.295103Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:70c958cf73d54c9ef51dbabbb68fcbd7c30437f5d937409195ef65021d45f1eb","observation_id":"b7b7ff3c-8f43-4627-bf33-e8b846d9f688","resolution":{"observed_at":"2026-08-10T15:20:40.543932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:20:40.519000Z","title":"#Atoms” predicts the molecular properties by only using the number of atoms in the molecule. If a baseline outperforms “#Atoms","venue":null,"work_id":"3ed84780-182a-432c-b9c4-f415e47e7b23","year":2024},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.299735Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:983b785ac45f9f905c3f45322d95284b24b0ba97f16ecbb5e9dd05c4f0488187","observation_id":"1c12805b-937d-400e-b875-a894243be252","resolution":{"observed_at":"2026-08-10T15:20:40.527380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.08933","last_updated":"2023-02-14T06:45:49Z","snapshot_observed_at":"2026-07-06T14:06:34.310083Z","submitted_at":"2022-10-17T10:49:08Z","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.08933","snapshot_observed_at":"2026-08-10T15:20:40.212060Z","title":"Inverse design of 3d molecular structures with conditional generative neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.212060Z"},"links":{"cited_paper":"/paper/2210.08933","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:eb63b3422826d6edcf98a749258ee5d347263f4ca4f5ea89875af48f72d69f97","observation_id":"bf77bb29-95c6-4c4d-a535-2c206426a070","resolution":{"observed_at":"2026-08-10T15:20:40.212060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.04236","last_updated":"2022-11-08T13:30:27Z","snapshot_observed_at":"2026-08-11T01:11:41.456510Z","submitted_at":"2022-11-08T13:30:27Z","title":"Self-conditioned Embedding Diffusion for Text Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.04236","snapshot_observed_at":"2026-08-10T15:20:40.257325Z","title":"Self-conditioned embedding diffusion for text generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.257325Z"},"links":{"cited_paper":"/paper/2211.04236","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:72f5914a0470add4e756e2018c1cb1dee1aec58b0531f55d6f7e3fc4f17b2aa3","observation_id":"f489676f-1633-423a-be3f-b2f677692d05","resolution":{"observed_at":"2026-08-10T15:20:40.257325Z","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":"2026-08-10T15:20:40.662606Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":"2df4c583-4ebc-4bbc-8df3-422dd83e31dd","year":2020},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.222385Z"},"links":{"citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:6520bdeddc6b1dad0aba7aea45dc250225248535436b49106f9bbb7968be8c1d","observation_id":"d6f3b5b9-066e-415f-a2ce-41b5bce5abe2","resolution":{"observed_at":"2026-08-10T15:20:40.671221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.09236","last_updated":"2024-03-13T22:49:33Z","snapshot_observed_at":"2026-08-12T04:15:44.056973Z","submitted_at":"2023-12-14T18:57:56Z","title":"A framework for conditional diffusion modelling with applications in motif scaffolding for protein design","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.09236","snapshot_observed_at":"2026-08-10T15:20:40.194823Z","title":"Score-based diffusion models for accelerated mri","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.194823Z"},"links":{"cited_paper":"/paper/2312.09236","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:db4b6857c232d797330b80fe997ef46be7d4aebc651c7758087db04fd901f93e","observation_id":"0b597218-ed8d-404c-9ac3-98589e250bf7","resolution":{"observed_at":"2026-08-10T15:20:40.194823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10516","last_updated":"2025-04-04T07:57:36Z","snapshot_observed_at":"2026-08-10T15:02:35.449973Z","submitted_at":"2024-10-14T13:58:13Z","title":"UniGEM: A Unified Approach to Generation and Property Prediction for Molecules","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10516","snapshot_observed_at":"2026-08-10T15:20:40.201052Z","title":"Unigem: A unified approach to generation and property prediction for molecules","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow","version":3},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-10T15:20:40.201052Z"},"links":{"cited_paper":"/paper/2410.10516","citing_paper":"/paper/2501.14216"},"observation_digest":"sha256:eab4cb81dc345cc315b263d75b8adf591341412963b4623a6d766a3636cf6a2d","observation_id":"86f162b5-c858-4b17-897d-77ea869d581f","resolution":{"observed_at":"2026-08-10T15:20:40.201052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.14216","last_updated":"2025-03-18T07:30:25Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T04:15:52.371706Z","submitted_at":"2025-01-24T03:44:16Z","title":"TFG-Flow: Training-free Guidance in Multimodal Generative Flow"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":8},"total_outbound_references":22},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 1 inbound Pith citation observation for arXiv:2501.14216."}