{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7EQYT6KSBRIDQDFYGO447RVQ6A","short_pith_number":"pith:7EQYT6KS","canonical_record":{"source":{"id":"2412.03179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T10:05:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43e9f1f64c87be73e9dab4632bccdaa64be9d3c3b6c3d8e3d9082a7f898f13c2","abstract_canon_sha256":"1d419ee7b6d6eec5323d366e4d580ebb22b5b14e5fa202776d2b65c19ef72284"},"schema_version":"1.0"},"canonical_sha256":"f92189f9520c50380cb833b9cfc6b0f008bc22b43947128bf6a91f18f62ed43e","source":{"kind":"arxiv","id":"2412.03179","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03179","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03179v1","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03179","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_12","alias_value":"7EQYT6KSBRID","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_16","alias_value":"7EQYT6KSBRIDQDFY","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_8","alias_value":"7EQYT6KS","created_at":"2026-07-05T09:44:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7EQYT6KSBRIDQDFYGO447RVQ6A","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T10:05:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43e9f1f64c87be73e9dab4632bccdaa64be9d3c3b6c3d8e3d9082a7f898f13c2","abstract_canon_sha256":"1d419ee7b6d6eec5323d366e4d580ebb22b5b14e5fa202776d2b65c19ef72284"},"schema_version":"1.0"},"canonical_sha256":"f92189f9520c50380cb833b9cfc6b0f008bc22b43947128bf6a91f18f62ed43e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:26.004403Z","signature_b64":"MPkuAepNK4fpzwkF2eK7RBT4RD0+ZExfTSha9eWmdu1VjRz9ZZFvcGlJ6aSLkXKWitHM4MXl4CbKHVLJmpqUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f92189f9520c50380cb833b9cfc6b0f008bc22b43947128bf6a91f18f62ed43e","last_reissued_at":"2026-07-05T09:44:26.004008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:26.004008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03179","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FjTFiIWxfW8WIkWA0pBjZ5Tz+37FIBH/scJGmmpZVT508ohua4q+RydD/UAiNUO4OJLHmEU0OyFpIY65uJVCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:12:17.623372Z"},"content_sha256":"e13d3039969b8f77af4d7a6867d1777960b09ba265073809c4f78893f1f674bd","schema_version":"1.0","event_id":"sha256:e13d3039969b8f77af4d7a6867d1777960b09ba265073809c4f78893f1f674bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7EQYT6KSBRIDQDFYGO447RVQ6A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Maxime Fontana, Miaojing Shi, Michael Spratling","submitted_at":"2024-12-04T10:05:47Z","abstract_excerpt":"Multi-Task Learning (MTL) involves the concurrent training of multiple tasks, offering notable advantages for dense prediction tasks in computer vision. MTL not only reduces training and inference time as opposed to having multiple single-task models, but also enhances task accuracy through the interaction of multiple tasks. However, existing methods face limitations. They often rely on suboptimal cross-task interactions, resulting in task-specific predictions with poor geometric and predictive coherence. In addition, many approaches use inadequate loss weighting strategies, which do not addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03179","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/2412.03179/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:44:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gLjfAvEskp7EMnlaqrXv0OOGx8v3u3DiNI/6gdO2+iOtLIRQZYHyig8WxH0YB5iICFMftTGkppkOo/QK8iB5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:12:17.623929Z"},"content_sha256":"501a0bde9085d36f8b8081e8e049ba20c736ab989cf8b8e46be73e691bf257da","schema_version":"1.0","event_id":"sha256:501a0bde9085d36f8b8081e8e049ba20c736ab989cf8b8e46be73e691bf257da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7EQYT6KSBRIDQDFYGO447RVQ6A/bundle.json","state_url":"https://pith.science/pith/7EQYT6KSBRIDQDFYGO447RVQ6A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7EQYT6KSBRIDQDFYGO447RVQ6A/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T20:12:17Z","links":{"resolver":"https://pith.science/pith/7EQYT6KSBRIDQDFYGO447RVQ6A","bundle":"https://pith.science/pith/7EQYT6KSBRIDQDFYGO447RVQ6A/bundle.json","state":"https://pith.science/pith/7EQYT6KSBRIDQDFYGO447RVQ6A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7EQYT6KSBRIDQDFYGO447RVQ6A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7EQYT6KSBRIDQDFYGO447RVQ6A","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1d419ee7b6d6eec5323d366e4d580ebb22b5b14e5fa202776d2b65c19ef72284","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T10:05:47Z","title_canon_sha256":"43e9f1f64c87be73e9dab4632bccdaa64be9d3c3b6c3d8e3d9082a7f898f13c2"},"schema_version":"1.0","source":{"id":"2412.03179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03179","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03179v1","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03179","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_12","alias_value":"7EQYT6KSBRID","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_16","alias_value":"7EQYT6KSBRIDQDFY","created_at":"2026-07-05T09:44:26Z"},{"alias_kind":"pith_short_8","alias_value":"7EQYT6KS","created_at":"2026-07-05T09:44:26Z"}],"graph_snapshots":[{"event_id":"sha256:501a0bde9085d36f8b8081e8e049ba20c736ab989cf8b8e46be73e691bf257da","target":"graph","created_at":"2026-07-05T09:44:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.03179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Task Learning (MTL) involves the concurrent training of multiple tasks, offering notable advantages for dense prediction tasks in computer vision. MTL not only reduces training and inference time as opposed to having multiple single-task models, but also enhances task accuracy through the interaction of multiple tasks. However, existing methods face limitations. They often rely on suboptimal cross-task interactions, resulting in task-specific predictions with poor geometric and predictive coherence. In addition, many approaches use inadequate loss weighting strategies, which do not addre","authors_text":"Maxime Fontana, Miaojing Shi, Michael Spratling","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03179","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e13d3039969b8f77af4d7a6867d1777960b09ba265073809c4f78893f1f674bd","target":"record","created_at":"2026-07-05T09:44:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1d419ee7b6d6eec5323d366e4d580ebb22b5b14e5fa202776d2b65c19ef72284","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T10:05:47Z","title_canon_sha256":"43e9f1f64c87be73e9dab4632bccdaa64be9d3c3b6c3d8e3d9082a7f898f13c2"},"schema_version":"1.0","source":{"id":"2412.03179","kind":"arxiv","version":1}},"canonical_sha256":"f92189f9520c50380cb833b9cfc6b0f008bc22b43947128bf6a91f18f62ed43e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f92189f9520c50380cb833b9cfc6b0f008bc22b43947128bf6a91f18f62ed43e","first_computed_at":"2026-07-05T09:44:26.004008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:26.004008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MPkuAepNK4fpzwkF2eK7RBT4RD0+ZExfTSha9eWmdu1VjRz9ZZFvcGlJ6aSLkXKWitHM4MXl4CbKHVLJmpqUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:26.004403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e13d3039969b8f77af4d7a6867d1777960b09ba265073809c4f78893f1f674bd","sha256:501a0bde9085d36f8b8081e8e049ba20c736ab989cf8b8e46be73e691bf257da"],"state_sha256":"db608b7e2ec0fcc7b86329e6f9cb1adfc456a1dd3fef97c848eb371177372c7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hsDvlPxIAXuOBTD0bWc+7S64rzF7crutXWyTHf0G5v5ayOn2Rtbl3UhYaS8qO8LugwzNT3O/9Bq/2vNc/DE2Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T20:12:17.631248Z","bundle_sha256":"f00aecc5885aa9d7d461998a682785fd84899bfea583040e62e8aa087c9b44b3"}}