{"as_of":"2026-08-16T01:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:80d5e0605ccd38ad8912b394778cdd86cb8361bee9d408c156e6e76ea54af30b","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:05:01.887836Z","state":"measured"},{"denominator":19,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":19,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.22771/citation-record","integrity":"/paper/2506.22771/integrity","json":"/paper/2506.22771/citation-record.json","paper":"/paper/2506.22771"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:05:04.882974Z","title":"Compute trends across three eras of machine learning,","venue":null,"work_id":"88e0a5ae-4ab9-4ffb-a0c0-7518660771f0","year":2022},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.089848Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:400133946775372905c972736f230dd35d5f7636a7204d512721fda412d36f7a","observation_id":"c2d9f7db-2ad9-4d91-9e40-527abd79aa16","resolution":{"observed_at":"2026-08-06T22:05:04.954533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:05:04.739986Z","title":"Imagenet training in minutes,","venue":null,"work_id":"75f62de8-dce2-4b89-8816-75315f296c3b","year":2018},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.131557Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:2befb07828735abfb5502aebedebea0ce8bf79b28f2885f8f97f26c41bdc5ffe","observation_id":"2e2d4846-acc0-425c-999c-4bf03942400a","resolution":{"observed_at":"2026-08-06T22:05:04.785459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:05:00.171003Z","title":"Training language models to follow instructions with human feedback,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.171003Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:9cf1ad1c512edc33c4e3314a6cf54d0730ae75380e60a48abea0316657ecb381","observation_id":"1c2813f1-5004-43d8-81e6-6249fb87f8aa","resolution":{"observed_at":"2026-08-06T22:05:00.171003Z","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":"2026-08-06T22:05:04.579521Z","title":"A comprehensive survey on tinyml,","venue":null,"work_id":"a9f02e81-7ebd-47c4-8629-2554e755e013","year":2023},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.317670Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:cc33eb6cd50ca1d862119989eaf209b42b46dcff8f1e5a151db074ef35400c22","observation_id":"5978c431-2947-46c1-86cf-10771c5d85d7","resolution":{"observed_at":"2026-08-06T22:05:04.660063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:05:04.402438Z","title":"Wenet: Configurable neural network with dynamic weight-enabling for efficient inference,","venue":null,"work_id":"d2741fd7-8c87-44a1-b7d2-38b0c09ebc68","year":2023},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.443619Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:a9852e65d19aa89cd279b088bc441a0e296cb541625ac47a4d9a7417e98e2f2a","observation_id":"e283a2a6-bd85-4e3e-a4ea-59db22cc0d83","resolution":{"observed_at":"2026-08-06T22:05:04.484567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:05:00.607517Z","title":"A survey of quantization methods for efficient neural network infer- ence,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.607517Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:d08d6983c2663c23af9fd80e580631bdb233e54dd571bbdaccf620184bf96815","observation_id":"cc5d3215-d258-4624-aef6-493352a854b6","resolution":{"observed_at":"2026-08-06T22:05:00.607517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.13345","last_updated":"2022-12-27T02:54:46Z","snapshot_observed_at":"2026-08-13T13:14:04.763006Z","submitted_at":"2022-12-27T02:54:46Z","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.13345","snapshot_observed_at":"2026-08-06T22:05:00.714991Z","title":"The forward-forward algorithm: Some preliminary investi- gations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.714991Z"},"links":{"cited_paper":"/paper/2212.13345","citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:d5239ca46cefb211e0dc0a819965e42d0b2c6920f70601a39d95cce0e3d166c1","observation_id":"b630089e-fc2c-4c3e-9c54-965e08c50043","resolution":{"observed_at":"2026-08-06T22:05:00.714991Z","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":"2026-08-06T22:05:00.757191Z","title":"Ptqd: Accurate post-training quantization for diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.757191Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:390fc2ecd649fb1f9195163f40ed86f7cc05ba1484f875a78f0d70335e1e953a","observation_id":"c4d29269-5225-4995-99a9-5ac34829ee58","resolution":{"observed_at":"2026-08-06T22:05:00.757191Z","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":"2026-08-06T22:05:00.861177Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.861177Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:ccac2e7f0c6c6a955904dc7638b308c14f04d8ac04a69bafacfff9e874455abf","observation_id":"15a54f2c-16b1-41e6-8d56-d8411cb0232d","resolution":{"observed_at":"2026-08-06T22:05:00.861177Z","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":"2026-08-06T22:05:04.085101Z","title":"Make repvgg greater again: A quantization-aware approach,","venue":null,"work_id":"31fe84b9-a69f-4532-bcaa-4a298369899a","year":2024},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:00.946659Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:8ed1dbf1861ae3157b4241a2f6909ab8e4f04c88b75bcb53a4dddc970a88b2ab","observation_id":"31abfc42-fc42-4770-89dd-fa15e3afee2f","resolution":{"observed_at":"2026-08-06T22:05:04.204835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:05:03.877916Z","title":"Mixed precision training,","venue":null,"work_id":"57504539-38c1-4c3f-bfb1-f2fa7da4d1fb","year":2018},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.019309Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:c1d9961b77d4d565caeed0a24b3a910dd7411f19b75b18ff47f32abbc58d2301","observation_id":"1170c9a0-8edc-4c66-9555-8151485e2c6f","resolution":{"observed_at":"2026-08-06T22:05:03.956735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:05:03.638345Z","title":"A block mini- float representation for training deep neural networks,","venue":null,"work_id":"8f695e2c-2908-41be-8527-55ed1e4f4036","year":2020},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.097280Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:06b7c150ebc14052d45863e95f991102a284547d093e7845b2f7ec56bf4b01ad","observation_id":"8e7c7906-6d06-409e-a5e7-3f598f741149","resolution":{"observed_at":"2026-08-06T22:05:03.760618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:05:03.247177Z","title":"Towards unified int8 training for convolutional neural network,","venue":null,"work_id":"4bcbd931-8926-450a-9470-237b9e8fdd42","year":2020},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.184681Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:179b291c1aeedeb13fd1e340b950248cbfdc25da90e207342916a47ca4e1e49c","observation_id":"6b70becc-2218-49a6-9294-ed5cf2a6365d","resolution":{"observed_at":"2026-08-06T22:05:03.422967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:05:02.766251Z","title":"Distri- bution adaptive int8 quantization for training cnns,","venue":null,"work_id":"92c682cb-20b8-4f8f-ae5c-676bae55245a","year":2021},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.283769Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:c585be492c81faf6b82bd1e5e91cdcc3360bff5c2178e247272cdc30e0ed3902","observation_id":"d56973c4-37a0-415f-bb46-95124c003094","resolution":{"observed_at":"2026-08-06T22:05:03.085050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:05:02.418634Z","title":"Gradient distribution-aware int8 training for neural networks,","venue":null,"work_id":"a7e26dac-4593-419e-bd2c-0762090808b0","year":2023},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.393850Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:1dd7a8d5f94e3a318c83d209335b010c429942cc746e9c2e57b198f869207113","observation_id":"c68ed10c-48c7-4b20-bae3-ef0f06323c99","resolution":{"observed_at":"2026-08-06T22:05:02.531505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-06T22:05:02.131017Z","title":"Deep learning with limited numerical precision,","venue":null,"work_id":"bf50db89-3566-4150-bfd4-509c2a9eaf3f","year":2015},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.482384Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:d6c9da27d253bcdb5f71ad709086432f0e8c5ab4de0c9799d1928a77ff6f088e","observation_id":"d020df79-5c47-4077-8e4f-2d92e15007b2","resolution":{"observed_at":"2026-08-06T22:05:02.271050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:05:01.640006Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.640006Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:87150e86f44a4cfcb7d546276fa39fdeb22123128583ab3f7fea0c91143fcf96","observation_id":"f33e32a2-88e2-42db-b4b7-64929e7f528c","resolution":{"observed_at":"2026-08-06T22:05:01.640006Z","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":"2026-08-06T22:05:01.740786Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.740786Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:c56e05350b76a772f9f4b83e12587ee1d1f80b62b9516514d7dd3649af747680","observation_id":"f7f15ccb-6412-47a7-aca3-e9de62db124b","resolution":{"observed_at":"2026-08-06T22:05:01.740786Z","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":"2026-08-06T22:05:01.887836Z","title":"Efficientnet: Rethinking model scaling for con- volutional neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:05:01.887836Z"},"links":{"citing_paper":"/paper/2506.22771"},"observation_digest":"sha256:63cc70d65d43ea2e4124946f855768734e2406a02cbc17f18e670518a53dc287","observation_id":"415c7e60-f2b0-47bd-9cdf-d5a8d341dc93","resolution":{"observed_at":"2026-08-06T22:05:01.887836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.22771","last_updated":"2025-06-28T06:16:26Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T22:15:03.211836Z","submitted_at":"2025-06-28T06:16:26Z","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":11},"total_outbound_references":19},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2506.22771."}