{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VTYW66ARDHJOTBYVU2TUKA5UFE","short_pith_number":"pith:VTYW66AR","canonical_record":{"source":{"id":"1705.06687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:44:31Z","cross_cats_sorted":[],"title_canon_sha256":"cc70471e239467cd3d3d98f6d92e8b767df905f1451aa362c3d52f1428d37111","abstract_canon_sha256":"21ca2b5640e8ffb373531795c899d3d924b01a53088c6cd8dce866226a1daa78"},"schema_version":"1.0"},"canonical_sha256":"acf16f781119d2e98715a6a74503b4291d0f6cae97cf6285c9cb6cb59ad5d3d1","source":{"kind":"arxiv","id":"1705.06687","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.06687","created_at":"2026-05-18T00:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"1705.06687v1","created_at":"2026-05-18T00:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.06687","created_at":"2026-05-18T00:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"VTYW66ARDHJO","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VTYW66ARDHJOTBYV","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VTYW66AR","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VTYW66ARDHJOTBYVU2TUKA5UFE","target":"record","payload":{"canonical_record":{"source":{"id":"1705.06687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:44:31Z","cross_cats_sorted":[],"title_canon_sha256":"cc70471e239467cd3d3d98f6d92e8b767df905f1451aa362c3d52f1428d37111","abstract_canon_sha256":"21ca2b5640e8ffb373531795c899d3d924b01a53088c6cd8dce866226a1daa78"},"schema_version":"1.0"},"canonical_sha256":"acf16f781119d2e98715a6a74503b4291d0f6cae97cf6285c9cb6cb59ad5d3d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:14.169441Z","signature_b64":"pATkjGg9vAARFJru45Z5EMGnZz3kfxRrsXkxeiIVtx2Vhmo4yUKMtYuwmQPQse9SvtyHI1q35vL9w1HpoJUFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acf16f781119d2e98715a6a74503b4291d0f6cae97cf6285c9cb6cb59ad5d3d1","last_reissued_at":"2026-05-18T00:44:14.168901Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:14.168901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.06687","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":"2026-05-18T00:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ahyiuqnDuW0zlbzfr+hyTUo2MAW8VeWPMFz5RwRjcp9WxLs46/8v/1m3+8czegBPE87pXp45yiKrbCctZc8vBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:52:57.663746Z"},"content_sha256":"fc7bc841eecd9c7d61af19f7d03f26df6be37ec3931c6c8254f8def6c02a1f4c","schema_version":"1.0","event_id":"sha256:fc7bc841eecd9c7d61af19f7d03f26df6be37ec3931c6c8254f8def6c02a1f4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VTYW66ARDHJOTBYVU2TUKA5UFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Target-Quality Image Compression with Recurrent, Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Damien Vincent, David Minnen, George Toderici, Joel Shor, Michele Covell, Nick Johnston, Saurabh Singh, Sung Jin Hwang","submitted_at":"2017-05-18T16:44:31Z","abstract_excerpt":"We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas. These methods lead to lower true bitrates for a given recursion count, both pre- and post-entropy coding, even using unstructured LZ77 code compression. The pre-LZ77 gains are achieved by trimming stop codes. The post-LZ77 gains are due to the highly unequal distributions of 0/1 codes "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.06687","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":""},"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":"2026-05-18T00:44:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tr8tJtBMGnBhEG5e1bE2GamAknCMH4DhyJQZa0PaP4DkZgn89Qxxjis1DDaoA0YZcgIbhL1CF4zZllGSBkofBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:52:57.664410Z"},"content_sha256":"2609f2b8d40353f38caa770e4812eab00a1c1216309be67974d9612f1a910dbe","schema_version":"1.0","event_id":"sha256:2609f2b8d40353f38caa770e4812eab00a1c1216309be67974d9612f1a910dbe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTYW66ARDHJOTBYVU2TUKA5UFE/bundle.json","state_url":"https://pith.science/pith/VTYW66ARDHJOTBYVU2TUKA5UFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTYW66ARDHJOTBYVU2TUKA5UFE/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":"2026-05-25T08:52:57Z","links":{"resolver":"https://pith.science/pith/VTYW66ARDHJOTBYVU2TUKA5UFE","bundle":"https://pith.science/pith/VTYW66ARDHJOTBYVU2TUKA5UFE/bundle.json","state":"https://pith.science/pith/VTYW66ARDHJOTBYVU2TUKA5UFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTYW66ARDHJOTBYVU2TUKA5UFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VTYW66ARDHJOTBYVU2TUKA5UFE","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":"21ca2b5640e8ffb373531795c899d3d924b01a53088c6cd8dce866226a1daa78","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:44:31Z","title_canon_sha256":"cc70471e239467cd3d3d98f6d92e8b767df905f1451aa362c3d52f1428d37111"},"schema_version":"1.0","source":{"id":"1705.06687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.06687","created_at":"2026-05-18T00:44:14Z"},{"alias_kind":"arxiv_version","alias_value":"1705.06687v1","created_at":"2026-05-18T00:44:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.06687","created_at":"2026-05-18T00:44:14Z"},{"alias_kind":"pith_short_12","alias_value":"VTYW66ARDHJO","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VTYW66ARDHJOTBYV","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VTYW66AR","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:2609f2b8d40353f38caa770e4812eab00a1c1216309be67974d9612f1a910dbe","target":"graph","created_at":"2026-05-18T00:44:14Z","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":"We introduce a stop-code tolerant (SCT) approach to training recurrent convolutional neural networks for lossy image compression. Our methods introduce a multi-pass training method to combine the training goals of high-quality reconstructions in areas around stop-code masking as well as in highly-detailed areas. These methods lead to lower true bitrates for a given recursion count, both pre- and post-entropy coding, even using unstructured LZ77 code compression. The pre-LZ77 gains are achieved by trimming stop codes. The post-LZ77 gains are due to the highly unequal distributions of 0/1 codes ","authors_text":"Damien Vincent, David Minnen, George Toderici, Joel Shor, Michele Covell, Nick Johnston, Saurabh Singh, Sung Jin Hwang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:44:31Z","title":"Target-Quality Image Compression with Recurrent, Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.06687","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:fc7bc841eecd9c7d61af19f7d03f26df6be37ec3931c6c8254f8def6c02a1f4c","target":"record","created_at":"2026-05-18T00:44:14Z","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":"21ca2b5640e8ffb373531795c899d3d924b01a53088c6cd8dce866226a1daa78","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-18T16:44:31Z","title_canon_sha256":"cc70471e239467cd3d3d98f6d92e8b767df905f1451aa362c3d52f1428d37111"},"schema_version":"1.0","source":{"id":"1705.06687","kind":"arxiv","version":1}},"canonical_sha256":"acf16f781119d2e98715a6a74503b4291d0f6cae97cf6285c9cb6cb59ad5d3d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acf16f781119d2e98715a6a74503b4291d0f6cae97cf6285c9cb6cb59ad5d3d1","first_computed_at":"2026-05-18T00:44:14.168901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:44:14.168901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pATkjGg9vAARFJru45Z5EMGnZz3kfxRrsXkxeiIVtx2Vhmo4yUKMtYuwmQPQse9SvtyHI1q35vL9w1HpoJUFDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:44:14.169441Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.06687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc7bc841eecd9c7d61af19f7d03f26df6be37ec3931c6c8254f8def6c02a1f4c","sha256:2609f2b8d40353f38caa770e4812eab00a1c1216309be67974d9612f1a910dbe"],"state_sha256":"3c1b50d3339b40b89fa9c74e4eb1e65e5fb8afd14458b7ee8a6eb01b31c2699b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GpC1cJKBnbrlRvYnyHkWZaY2lJr0AleoRWTNdZjdYhIeqyurTQ5venfC2Tt5/pZGSft51FnvxjlAWQWoHR96Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T08:52:57.667782Z","bundle_sha256":"9568f024b6a2a3a1451975a658f6f6aa63b57c55d004e7c7fa57807bb5fcc7bb"}}