{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O3PH7VOW5CG4V7LNSQF6AB6VAD","short_pith_number":"pith:O3PH7VOW","schema_version":"1.0","canonical_sha256":"76de7fd5d6e88dcafd6d940be007d500f9b18f3692b819ede80226456b5efe70","source":{"kind":"arxiv","id":"2111.15133","version":1},"attestation_state":"computed","paper":{"title":"LossPlot: A Better Way to Visualize Loss Landscapes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.LG","authors_text":"Harsh Kothari, Mikhail Tokarev, Rahul Damineni, Robert Bain","submitted_at":"2021-11-30T05:29:46Z","abstract_excerpt":"Investigations into the loss landscapes of deep neural networks are often laborious. This work documents our user-driven approach to create a platform for semi-automating this process. LossPlot accepts data in the form of a csv, and allows multiple trained minimizers of the loss function to be manipulated in sync. Other features include a simple yet intuitive checkbox UI, summary statistics, and the ability to control clipping which other methods do not offer."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.15133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T05:29:46Z","cross_cats_sorted":["cs.CV","cs.HC"],"title_canon_sha256":"3ac04f02a1e934f2ef0103dc479aa4c2b9581d81a1c634959ba22a2ed90b6cd6","abstract_canon_sha256":"357471c05467d50aa19c3ae92e434c33ac6c2c55302b895b3b4b01e7933ab84a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:23.256105Z","signature_b64":"1CmTXas2WIFlHeauhf3ZmH68UGxWANErhQTRgXm5VvVW6BQZTV+DHZqfe6kP0ngYREOa1QW8+tBuz3ASrFn/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76de7fd5d6e88dcafd6d940be007d500f9b18f3692b819ede80226456b5efe70","last_reissued_at":"2026-07-05T03:36:23.255754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:23.255754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LossPlot: A Better Way to Visualize Loss Landscapes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.LG","authors_text":"Harsh Kothari, Mikhail Tokarev, Rahul Damineni, Robert Bain","submitted_at":"2021-11-30T05:29:46Z","abstract_excerpt":"Investigations into the loss landscapes of deep neural networks are often laborious. This work documents our user-driven approach to create a platform for semi-automating this process. LossPlot accepts data in the form of a csv, and allows multiple trained minimizers of the loss function to be manipulated in sync. Other features include a simple yet intuitive checkbox UI, summary statistics, and the ability to control clipping which other methods do not offer."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15133","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.15133/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.15133","created_at":"2026-07-05T03:36:23.255813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.15133v1","created_at":"2026-07-05T03:36:23.255813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15133","created_at":"2026-07-05T03:36:23.255813+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3PH7VOW5CG4","created_at":"2026-07-05T03:36:23.255813+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3PH7VOW5CG4V7LN","created_at":"2026-07-05T03:36:23.255813+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3PH7VOW","created_at":"2026-07-05T03:36:23.255813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10649","citing_title":"Deep Loss Convexification for Learning Iterative Models","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD","json":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD.json","graph_json":"https://pith.science/api/pith-number/O3PH7VOW5CG4V7LNSQF6AB6VAD/graph.json","events_json":"https://pith.science/api/pith-number/O3PH7VOW5CG4V7LNSQF6AB6VAD/events.json","paper":"https://pith.science/paper/O3PH7VOW"},"agent_actions":{"view_html":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD","download_json":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD.json","view_paper":"https://pith.science/paper/O3PH7VOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.15133&json=true","fetch_graph":"https://pith.science/api/pith-number/O3PH7VOW5CG4V7LNSQF6AB6VAD/graph.json","fetch_events":"https://pith.science/api/pith-number/O3PH7VOW5CG4V7LNSQF6AB6VAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD/action/storage_attestation","attest_author":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD/action/author_attestation","sign_citation":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD/action/citation_signature","submit_replication":"https://pith.science/pith/O3PH7VOW5CG4V7LNSQF6AB6VAD/action/replication_record"}},"created_at":"2026-07-05T03:36:23.255813+00:00","updated_at":"2026-07-05T03:36:23.255813+00:00"}