{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:K2GHX466M2XBIZSJAA4BNFK5TT","short_pith_number":"pith:K2GHX466","canonical_record":{"source":{"id":"1612.07307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-21T20:29:26Z","cross_cats_sorted":[],"title_canon_sha256":"704af55156dbb303ef5d42411dfdc72f905c1817ae2576b21944e7d9e8457cee","abstract_canon_sha256":"b1e1c5123f8aaffde630ee6439dced52ccf1819870a8c8005d4db93bcf385618"},"schema_version":"1.0"},"canonical_sha256":"568c7bf3de66ae146649003816955d9cc5b827c6ff22b87c85cc05b2c85023ca","source":{"kind":"arxiv","id":"1612.07307","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.07307","created_at":"2026-05-18T00:49:02Z"},{"alias_kind":"arxiv_version","alias_value":"1612.07307v2","created_at":"2026-05-18T00:49:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07307","created_at":"2026-05-18T00:49:02Z"},{"alias_kind":"pith_short_12","alias_value":"K2GHX466M2XB","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"K2GHX466M2XBIZSJ","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"K2GHX466","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:K2GHX466M2XBIZSJAA4BNFK5TT","target":"record","payload":{"canonical_record":{"source":{"id":"1612.07307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-21T20:29:26Z","cross_cats_sorted":[],"title_canon_sha256":"704af55156dbb303ef5d42411dfdc72f905c1817ae2576b21944e7d9e8457cee","abstract_canon_sha256":"b1e1c5123f8aaffde630ee6439dced52ccf1819870a8c8005d4db93bcf385618"},"schema_version":"1.0"},"canonical_sha256":"568c7bf3de66ae146649003816955d9cc5b827c6ff22b87c85cc05b2c85023ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:02.115230Z","signature_b64":"uPSkUwjrJzy3k72qN4E4TJr3JpJA0W8v7x+x0q14kQYmIgaVfd/0B83U/PVl8ybLo+JXwYNItbtZuvY1DXVmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"568c7bf3de66ae146649003816955d9cc5b827c6ff22b87c85cc05b2c85023ca","last_reissued_at":"2026-05-18T00:49:02.114453Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:02.114453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.07307","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:49:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0TfPAUPRizsRn4LlUEiAuiC2kT8mgr2Uv/SZOvtMq2vQuSGSAkzKAUOn7AoHJLQw8ycj7Y5At+78nwAcpruhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:41:58.021431Z"},"content_sha256":"81a34f0fc0afd964edc4eb7b27939314fb0b6166eefbaae5bed4a5b9c29d2194","schema_version":"1.0","event_id":"sha256:81a34f0fc0afd964edc4eb7b27939314fb0b6166eefbaae5bed4a5b9c29d2194"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:K2GHX466M2XBIZSJAA4BNFK5TT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Loss is its own Reward: Self-Supervision for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Evan Shelhamer, Max Argus, Parsa Mahmoudieh, Trevor Darrell","submitted_at":"2016-12-21T20:29:26Z","abstract_excerpt":"Reinforcement learning optimizes policies for expected cumulative reward. Need the supervision be so narrow? Reward is delayed and sparse for many tasks, making it a difficult and impoverished signal for end-to-end optimization. To augment reward, we consider a range of self-supervised tasks that incorporate states, actions, and successors to provide auxiliary losses. These losses offer ubiquitous and instantaneous supervision for representation learning even in the absence of reward. While current results show that learning from reward alone is feasible, pure reinforcement learning methods ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07307","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:49:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9eHj0revmwd2upNdAHEmxvmP3j2nMq088XehzY84B/WTq0qPuxE91Cx5KCeoXmDX6KA/IaQtgOqld0bmy50BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T02:41:58.021809Z"},"content_sha256":"4a5515cbabfa3c992fa2407c049c47ad92527895ce3559a26f9b61d16277e76e","schema_version":"1.0","event_id":"sha256:4a5515cbabfa3c992fa2407c049c47ad92527895ce3559a26f9b61d16277e76e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2GHX466M2XBIZSJAA4BNFK5TT/bundle.json","state_url":"https://pith.science/pith/K2GHX466M2XBIZSJAA4BNFK5TT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2GHX466M2XBIZSJAA4BNFK5TT/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":"2026-05-26T02:41:58Z","links":{"resolver":"https://pith.science/pith/K2GHX466M2XBIZSJAA4BNFK5TT","bundle":"https://pith.science/pith/K2GHX466M2XBIZSJAA4BNFK5TT/bundle.json","state":"https://pith.science/pith/K2GHX466M2XBIZSJAA4BNFK5TT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2GHX466M2XBIZSJAA4BNFK5TT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:K2GHX466M2XBIZSJAA4BNFK5TT","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":"b1e1c5123f8aaffde630ee6439dced52ccf1819870a8c8005d4db93bcf385618","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-21T20:29:26Z","title_canon_sha256":"704af55156dbb303ef5d42411dfdc72f905c1817ae2576b21944e7d9e8457cee"},"schema_version":"1.0","source":{"id":"1612.07307","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.07307","created_at":"2026-05-18T00:49:02Z"},{"alias_kind":"arxiv_version","alias_value":"1612.07307v2","created_at":"2026-05-18T00:49:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07307","created_at":"2026-05-18T00:49:02Z"},{"alias_kind":"pith_short_12","alias_value":"K2GHX466M2XB","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"K2GHX466M2XBIZSJ","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"K2GHX466","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:4a5515cbabfa3c992fa2407c049c47ad92527895ce3559a26f9b61d16277e76e","target":"graph","created_at":"2026-05-18T00:49:02Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning optimizes policies for expected cumulative reward. Need the supervision be so narrow? Reward is delayed and sparse for many tasks, making it a difficult and impoverished signal for end-to-end optimization. To augment reward, we consider a range of self-supervised tasks that incorporate states, actions, and successors to provide auxiliary losses. These losses offer ubiquitous and instantaneous supervision for representation learning even in the absence of reward. While current results show that learning from reward alone is feasible, pure reinforcement learning methods ar","authors_text":"Evan Shelhamer, Max Argus, Parsa Mahmoudieh, Trevor Darrell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-21T20:29:26Z","title":"Loss is its own Reward: Self-Supervision for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07307","kind":"arxiv","version":2},"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":"sha256:81a34f0fc0afd964edc4eb7b27939314fb0b6166eefbaae5bed4a5b9c29d2194","target":"record","created_at":"2026-05-18T00:49:02Z","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":"b1e1c5123f8aaffde630ee6439dced52ccf1819870a8c8005d4db93bcf385618","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-21T20:29:26Z","title_canon_sha256":"704af55156dbb303ef5d42411dfdc72f905c1817ae2576b21944e7d9e8457cee"},"schema_version":"1.0","source":{"id":"1612.07307","kind":"arxiv","version":2}},"canonical_sha256":"568c7bf3de66ae146649003816955d9cc5b827c6ff22b87c85cc05b2c85023ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"568c7bf3de66ae146649003816955d9cc5b827c6ff22b87c85cc05b2c85023ca","first_computed_at":"2026-05-18T00:49:02.114453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:02.114453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uPSkUwjrJzy3k72qN4E4TJr3JpJA0W8v7x+x0q14kQYmIgaVfd/0B83U/PVl8ybLo+JXwYNItbtZuvY1DXVmAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:02.115230Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.07307","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81a34f0fc0afd964edc4eb7b27939314fb0b6166eefbaae5bed4a5b9c29d2194","sha256:4a5515cbabfa3c992fa2407c049c47ad92527895ce3559a26f9b61d16277e76e"],"state_sha256":"7a47b354f04a6a8629352504db092d5f977f96a14934fb1c73a1c469898a26b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75Om4kpWxFHW7q9PRjRrWzcoGWaC7hS27AWczKTmbMRrQJexENIdLZnmGLUuPThemmFEDo96ZM6wG2le1d3TBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T02:41:58.024150Z","bundle_sha256":"5924e5d3c0424b6d138165c159d24854bc68cd7c5ffe36fc45d1c701aaf969a4"}}